Skip to content

imagegpt

mindnlp.transformers.models.imagegpt.configuration_imagegpt

OpenAI ImageGPT configuration

mindnlp.transformers.models.imagegpt.configuration_imagegpt.ImageGPTConfig

Bases: PretrainedConfig

This is the configuration class to store the configuration of a [ImageGPTModel] or a [TFImageGPTModel]. It is used to instantiate a GPT-2 model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the ImageGPT openai/imagegpt-small architecture.

Configuration objects inherit from [PretrainedConfig] and can be used to control the model outputs. Read the documentation from [PretrainedConfig] for more information.

PARAMETER DESCRIPTION
vocab_size

Vocabulary size of the GPT-2 model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling [ImageGPTModel] or [TFImageGPTModel].

TYPE: `int`, *optional*, defaults to 512 DEFAULT: 512 + 1

n_positions

The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048).

TYPE: `int`, *optional*, defaults to 32*32 DEFAULT: 32 * 32

n_embd

Dimensionality of the embeddings and hidden states.

TYPE: `int`, *optional*, defaults to 512 DEFAULT: 512

n_layer

Number of hidden layers in the Transformer encoder.

TYPE: `int`, *optional*, defaults to 24 DEFAULT: 24

n_head

Number of attention heads for each attention layer in the Transformer encoder.

TYPE: `int`, *optional*, defaults to 8 DEFAULT: 8

n_inner

Dimensionality of the inner feed-forward layers. None will set it to 4 times n_embd

TYPE: `int`, *optional*, defaults to None DEFAULT: None

activation_function

Activation function (can be one of the activation functions defined in src/transformers/activations.py). Defaults to "quick_gelu".

TYPE: `str`, *optional*, defaults to `"quick_gelu"` DEFAULT: 'quick_gelu'

resid_pdrop

The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.

TYPE: `float`, *optional*, defaults to 0.1 DEFAULT: 0.1

embd_pdrop

The dropout ratio for the embeddings.

TYPE: `int`, *optional*, defaults to 0.1 DEFAULT: 0.1

attn_pdrop

The dropout ratio for the attention.

TYPE: `float`, *optional*, defaults to 0.1 DEFAULT: 0.1

layer_norm_epsilon

The epsilon to use in the layer normalization layers.

TYPE: `float`, *optional*, defaults to 1e-5 DEFAULT: 1e-05

initializer_range

The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

TYPE: `float`, *optional*, defaults to 0.02 DEFAULT: 0.02

scale_attn_weights

Scale attention weights by dividing by sqrt(hidden_size)..

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

use_cache

Whether or not the model should return the last key/values attentions (not used by all models).

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

scale_attn_by_inverse_layer_idx

Whether to additionally scale attention weights by 1 / layer_idx + 1.

TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False

reorder_and_upcast_attn

Whether to scale keys (K) prior to computing attention (dot-product) and upcast attention dot-product/softmax to float() when training with mixed precision.

TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False

Example 
>>> from transformers import ImageGPTConfig, ImageGPTModel

>>> # Initializing a ImageGPT configuration
>>> configuration = ImageGPTConfig()

>>> # Initializing a model (with random weights) from the configuration
>>> model = ImageGPTModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
Source code in mindnlp/transformers/models/imagegpt/configuration_imagegpt.py 
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
class ImageGPTConfig(PretrainedConfig):
    """
    This is the configuration class to store the configuration of a [`ImageGPTModel`] or a [`TFImageGPTModel`]. It is
    used to instantiate a GPT-2 model according to the specified arguments, defining the model architecture.
    Instantiating a configuration with the defaults will yield a similar configuration to that of the ImageGPT
    [openai/imagegpt-small](https://huggingface.co/openai/imagegpt-small) architecture.

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information.

    Args:
        vocab_size (`int`, *optional*, defaults to 512):
            Vocabulary size of the GPT-2 model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`ImageGPTModel`] or [`TFImageGPTModel`].
        n_positions (`int`, *optional*, defaults to 32*32):
            The maximum sequence length that this model might ever be used with. Typically set this to something large
            just in case (e.g., 512 or 1024 or 2048).
        n_embd (`int`, *optional*, defaults to 512):
            Dimensionality of the embeddings and hidden states.
        n_layer (`int`, *optional*, defaults to 24):
            Number of hidden layers in the Transformer encoder.
        n_head (`int`, *optional*, defaults to 8):
            Number of attention heads for each attention layer in the Transformer encoder.
        n_inner (`int`, *optional*, defaults to None):
            Dimensionality of the inner feed-forward layers. `None` will set it to 4 times n_embd
        activation_function (`str`, *optional*, defaults to `"quick_gelu"`):
            Activation function (can be one of the activation functions defined in src/transformers/activations.py).
            Defaults to "quick_gelu".
        resid_pdrop (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        embd_pdrop (`int`, *optional*, defaults to 0.1):
            The dropout ratio for the embeddings.
        attn_pdrop (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention.
        layer_norm_epsilon (`float`, *optional*, defaults to 1e-5):
            The epsilon to use in the layer normalization layers.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        scale_attn_weights (`bool`, *optional*, defaults to `True`):
            Scale attention weights by dividing by sqrt(hidden_size)..
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).
        scale_attn_by_inverse_layer_idx (`bool`, *optional*, defaults to `False`):
            Whether to additionally scale attention weights by `1 / layer_idx + 1`.
        reorder_and_upcast_attn (`bool`, *optional*, defaults to `False`):
            Whether to scale keys (K) prior to computing attention (dot-product) and upcast attention
            dot-product/softmax to float() when training with mixed precision.

    Example:
        ```python
        >>> from transformers import ImageGPTConfig, ImageGPTModel

        >>> # Initializing a ImageGPT configuration
        >>> configuration = ImageGPTConfig()

        >>> # Initializing a model (with random weights) from the configuration
        >>> model = ImageGPTModel(configuration)

        >>> # Accessing the model configuration
        >>> configuration = model.config
        ```
    """

    model_type = "imagegpt"
    keys_to_ignore_at_inference = ["past_key_values"]
    attribute_map = {
        "hidden_size": "n_embd",
        "max_position_embeddings": "n_positions",
        "num_attention_heads": "n_head",
        "num_hidden_layers": "n_layer",
    }

    def __init__(
        self,
        vocab_size=512 + 1,  # add one for start of sentence (sos) token
        n_positions=32 * 32,
        n_embd=512,
        n_layer=24,
        n_head=8,
        n_inner=None,
        activation_function="quick_gelu",
        resid_pdrop=0.1,
        embd_pdrop=0.1,
        attn_pdrop=0.1,
        layer_norm_epsilon=1e-5,
        initializer_range=0.02,
        scale_attn_weights=True,
        use_cache=True,
        tie_word_embeddings=False,
        scale_attn_by_inverse_layer_idx=False,
        reorder_and_upcast_attn=False,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.n_positions = n_positions
        self.n_embd = n_embd
        self.n_layer = n_layer
        self.n_head = n_head
        self.n_inner = n_inner
        self.activation_function = activation_function
        self.resid_pdrop = resid_pdrop
        self.embd_pdrop = embd_pdrop
        self.attn_pdrop = attn_pdrop
        self.layer_norm_epsilon = layer_norm_epsilon
        self.initializer_range = initializer_range
        self.scale_attn_weights = scale_attn_weights
        self.use_cache = use_cache
        self.scale_attn_by_inverse_layer_idx = scale_attn_by_inverse_layer_idx
        self.reorder_and_upcast_attn = reorder_and_upcast_attn
        self.tie_word_embeddings = tie_word_embeddings

        super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)

mindnlp.transformers.models.imagegpt.feature_extraction_imagegpt

Feature extractor class for ImageGPT.

mindnlp.transformers.models.imagegpt.image_processing_imagegpt

Image processor class for ImageGPT.

mindnlp.transformers.models.imagegpt.image_processing_imagegpt.ImageGPTImageProcessor

Bases: BaseImageProcessor

Constructs a ImageGPT image processor. This image processor can be used to resize images to a smaller resolution (such as 32x32 or 64x64), normalize them and finally color quantize them to obtain sequences of "pixel values" (color clusters).

PARAMETER DESCRIPTION
clusters

The color clusters to use, of shape (n_clusters, 3) when color quantizing. Can be overriden by clusters in preprocess.

TYPE: `np.ndarray` or `List[List[int]]`, *optional* DEFAULT: None

do_resize

Whether to resize the image's dimensions to (size["height"], size["width"]). Can be overridden by do_resize in preprocess.

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

size

256, "width": 256}): Size of the image after resizing. Can be overridden bysizeinpreprocess`.

TYPE: `Dict[str, int]` *optional*, defaults to `{"height" DEFAULT: None

resample

Resampling filter to use if resizing the image. Can be overridden by resample in preprocess.

TYPE: `PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR` DEFAULT: BILINEAR

do_normalize

Whether to normalize the image pixel value to between [-1, 1]. Can be overridden by do_normalize in preprocess.

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

do_color_quantize

Whether to color quantize the image. Can be overridden by do_color_quantize in preprocess.

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

Source code in mindnlp/transformers/models/imagegpt/image_processing_imagegpt.py 
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
class ImageGPTImageProcessor(BaseImageProcessor):
    r"""
    Constructs a ImageGPT image processor. This image processor can be used to resize images to a smaller resolution
    (such as 32x32 or 64x64), normalize them and finally color quantize them to obtain sequences of "pixel values"
    (color clusters).

    Args:
        clusters (`np.ndarray` or `List[List[int]]`, *optional*):
            The color clusters to use, of shape `(n_clusters, 3)` when color quantizing. Can be overriden by `clusters`
            in `preprocess`.
        do_resize (`bool`, *optional*, defaults to `True`):
            Whether to resize the image's dimensions to `(size["height"], size["width"])`. Can be overridden by
            `do_resize` in `preprocess`.
        size (`Dict[str, int]` *optional*, defaults to `{"height": 256, "width": 256}`):
            Size of the image after resizing. Can be overridden by `size` in `preprocess`.
        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`):
            Resampling filter to use if resizing the image. Can be overridden by `resample` in `preprocess`.
        do_normalize (`bool`, *optional*, defaults to `True`):
            Whether to normalize the image pixel value to between [-1, 1]. Can be overridden by `do_normalize` in
            `preprocess`.
        do_color_quantize (`bool`, *optional*, defaults to `True`):
            Whether to color quantize the image. Can be overridden by `do_color_quantize` in `preprocess`.
    """

    model_input_names = ["pixel_values"]

    def __init__(
        self,
        # clusters is a first argument to maintain backwards compatibility with the old ImageGPTImageProcessor
        clusters: Optional[Union[List[List[int]], np.ndarray]] = None,
        do_resize: bool = True,
        size: Dict[str, int] = None,
        resample: PILImageResampling = PILImageResampling.BILINEAR,
        do_normalize: bool = True,
        do_color_quantize: bool = True,
        **kwargs,
    ) -> None:
        super().__init__(**kwargs)
        size = size if size is not None else {"height": 256, "width": 256}
        size = get_size_dict(size)
        self.clusters = np.array(clusters) if clusters is not None else None
        self.do_resize = do_resize
        self.size = size
        self.resample = resample
        self.do_normalize = do_normalize
        self.do_color_quantize = do_color_quantize
        self._valid_processor_keys = [
            "images",
            "do_resize",
            "size",
            "resample",
            "do_normalize",
            "do_color_quantize",
            "clusters",
            "return_tensors",
            "data_format",
            "input_data_format",
        ]

    # Copied from transformers.models.vit.image_processing_vit.ViTImageProcessor.resize
    def resize(
        self,
        image: np.ndarray,
        size: Dict[str, int],
        resample: PILImageResampling = PILImageResampling.BILINEAR,
        data_format: Optional[Union[str, ChannelDimension]] = None,
        input_data_format: Optional[Union[str, ChannelDimension]] = None,
        **kwargs,
    ) -> np.ndarray:
        """
        Resize an image to `(size["height"], size["width"])`.

        Args:
            image (`np.ndarray`):
                Image to resize.
            size (`Dict[str, int]`):
                Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image.
            resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`):
                `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BILINEAR`.
            data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format for the output image. If unset, the channel dimension format of the input
                image is used. Can be one of:

                - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
                - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.
            input_data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format for the input image. If unset, the channel dimension format is inferred
                from the input image. Can be one of:

                - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
                - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.

        Returns:
            `np.ndarray`: The resized image.
        """
        size = get_size_dict(size)
        if "height" not in size or "width" not in size:
            raise ValueError(
                f"The `size` dictionary must contain the keys `height` and `width`. Got {size.keys()}")
        output_size = (size["height"], size["width"])
        return resize(
            image,
            size=output_size,
            resample=resample,
            data_format=data_format,
            input_data_format=input_data_format,
            **kwargs,
        )

    def normalize(
        self,
        image: np.ndarray,
        data_format: Optional[Union[str, ChannelDimension]] = None,
        input_data_format: Optional[Union[str, ChannelDimension]] = None,
    ) -> np.ndarray:
        """
        Normalizes an images' pixel values to between [-1, 1].

        Args:
            image (`np.ndarray`):
                Image to normalize.
            data_format (`str` or `ChannelDimension`, *optional*):
                The channel dimension format of the image. If not provided, it will be the same as the input image.
            input_data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format of the input image. If not provided, it will be inferred.
        """
        image = rescale(image=image, scale=1 / 127.5,
                        data_format=data_format, input_data_format=input_data_format)
        image = image - 1
        return image

    def preprocess(
        self,
        images: ImageInput,
        do_resize: bool = None,
        size: Dict[str, int] = None,
        resample: PILImageResampling = None,
        do_normalize: bool = None,
        do_color_quantize: Optional[bool] = None,
        clusters: Optional[Union[List[List[int]], np.ndarray]] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        data_format: Optional[Union[str, ChannelDimension]] = ChannelDimension.FIRST,
        input_data_format: Optional[Union[str, ChannelDimension]] = None,
        **kwargs,
    ) -> PIL.Image.Image:
        """
        Preprocess an image or batch of images.

        Args:
            images (`ImageInput`):
                Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If
                passing in images with pixel values between 0 and 1, set `do_normalize=False`.
            do_resize (`bool`, *optional*, defaults to `self.do_resize`):
                Whether to resize the image.
            size (`Dict[str, int]`, *optional*, defaults to `self.size`):
                Size of the image after resizing.
            resample (`int`, *optional*, defaults to `self.resample`):
                Resampling filter to use if resizing the image. This can be one of the enum `PILImageResampling`, Only
                has an effect if `do_resize` is set to `True`.
            do_normalize (`bool`, *optional*, defaults to `self.do_normalize`):
                Whether to normalize the image
            do_color_quantize (`bool`, *optional*, defaults to `self.do_color_quantize`):
                Whether to color quantize the image.
            clusters (`np.ndarray` or `List[List[int]]`, *optional*, defaults to `self.clusters`):
                Clusters used to quantize the image of shape `(n_clusters, 3)`. Only has an effect if
                `do_color_quantize` is set to `True`.
            return_tensors (`str` or `TensorType`, *optional*):
                The type of tensors to return. Can be one of:

                - Unset: Return a list of `np.ndarray`.
                - `TensorType.TENSORFLOW` or `'tf'`: Return a batch of type `tf.Tensor`.
                - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`.
                - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`.
                - `TensorType.JAX` or `'jax'`: Return a batch of type `jax.numpy.ndarray`.
            data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`):
                The channel dimension format for the output image. Can be one of:

                - `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                - `ChannelDimension.LAST`: image in (height, width, num_channels) format.
                Only has an effect if `do_color_quantize` is set to `False`.
            input_data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format for the input image. If unset, the channel dimension format is inferred
                from the input image. Can be one of:

                - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
                - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.
        """
        do_resize = do_resize if do_resize is not None else self.do_resize
        size = size if size is not None else self.size
        size = get_size_dict(size)
        resample = resample if resample is not None else self.resample
        do_normalize = do_normalize if do_normalize is not None else self.do_normalize
        do_color_quantize = do_color_quantize if do_color_quantize is not None else self.do_color_quantize
        clusters = clusters if clusters is not None else self.clusters
        clusters = np.array(clusters)

        images = make_list_of_images(images)

        validate_kwargs(captured_kwargs=kwargs.keys(),
                        valid_processor_keys=self._valid_processor_keys)

        if not valid_images(images):
            raise ValueError(
                "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "
                "torch.Tensor, tf.Tensor or jax.ndarray."
            )

        # Here, normalize() is using a constant factor to divide pixel values.
        # hence, the method does not need iamge_mean and image_std.
        validate_preprocess_arguments(
            do_resize=do_resize,
            size=size,
            resample=resample,
        )

        if do_color_quantize and clusters is None:
            raise ValueError(
                "Clusters must be specified if do_color_quantize is True.")

        # All transformations expect numpy arrays.
        images = [to_numpy_array(image) for image in images]

        if is_scaled_image(images[0]) and do_normalize:
            logger.warning_once(
                "It looks like you are trying to rescale already rescaled images. If you wish to do this, "
                "make sure to set `do_normalize` to `False` and that pixel values are between [-1, 1].",
            )

        if input_data_format is None:
            # We assume that all images have the same channel dimension format.
            input_data_format = infer_channel_dimension_format(images[0])

        if do_resize:
            images = [
                self.resize(image=image, size=size, resample=resample,
                            input_data_format=input_data_format)
                for image in images
            ]

        if do_normalize:
            images = [self.normalize(
                image=image, input_data_format=input_data_format) for image in images]

        if do_color_quantize:
            images = [to_channel_dimension_format(
                image, ChannelDimension.LAST, input_data_format) for image in images]
            # color quantize from (batch_size, height, width, 3) to (batch_size, height, width)
            images = np.array(images)
            images = color_quantize(
                images, clusters).reshape(images.shape[:-1])

            # flatten to (batch_size, height*width)
            batch_size = images.shape[0]
            images = images.reshape(batch_size, -1)

            # We need to convert back to a list of images to keep consistent behaviour across processors.
            images = list(images)
        else:
            images = [
                to_channel_dimension_format(
                    image, data_format, input_channel_dim=input_data_format)
                for image in images
            ]

        data = {"input_ids": images}
        return BatchFeature(data=data, tensor_type=return_tensors)

mindnlp.transformers.models.imagegpt.image_processing_imagegpt.ImageGPTImageProcessor.normalize(image, data_format=None, input_data_format=None)

Normalizes an images' pixel values to between [-1, 1].

PARAMETER DESCRIPTION
image

Image to normalize.

TYPE: `np.ndarray`

data_format

The channel dimension format of the image. If not provided, it will be the same as the input image.

TYPE: `str` or `ChannelDimension`, *optional* DEFAULT: None

input_data_format

The channel dimension format of the input image. If not provided, it will be inferred.

TYPE: `ChannelDimension` or `str`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/imagegpt/image_processing_imagegpt.py 
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
def normalize(
    self,
    image: np.ndarray,
    data_format: Optional[Union[str, ChannelDimension]] = None,
    input_data_format: Optional[Union[str, ChannelDimension]] = None,
) -> np.ndarray:
    """
    Normalizes an images' pixel values to between [-1, 1].

    Args:
        image (`np.ndarray`):
            Image to normalize.
        data_format (`str` or `ChannelDimension`, *optional*):
            The channel dimension format of the image. If not provided, it will be the same as the input image.
        input_data_format (`ChannelDimension` or `str`, *optional*):
            The channel dimension format of the input image. If not provided, it will be inferred.
    """
    image = rescale(image=image, scale=1 / 127.5,
                    data_format=data_format, input_data_format=input_data_format)
    image = image - 1
    return image

mindnlp.transformers.models.imagegpt.image_processing_imagegpt.ImageGPTImageProcessor.preprocess(images, do_resize=None, size=None, resample=None, do_normalize=None, do_color_quantize=None, clusters=None, return_tensors=None, data_format=ChannelDimension.FIRST, input_data_format=None, **kwargs)

Preprocess an image or batch of images.

PARAMETER DESCRIPTION
images

Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set do_normalize=False.

TYPE: `ImageInput`

do_resize

Whether to resize the image.

TYPE: `bool`, *optional*, defaults to `self.do_resize` DEFAULT: None

size

Size of the image after resizing.

TYPE: `Dict[str, int]`, *optional*, defaults to `self.size` DEFAULT: None

resample

Resampling filter to use if resizing the image. This can be one of the enum PILImageResampling, Only has an effect if do_resize is set to True.

TYPE: `int`, *optional*, defaults to `self.resample` DEFAULT: None

do_normalize

Whether to normalize the image

TYPE: `bool`, *optional*, defaults to `self.do_normalize` DEFAULT: None

do_color_quantize

Whether to color quantize the image.

TYPE: `bool`, *optional*, defaults to `self.do_color_quantize` DEFAULT: None

clusters

Clusters used to quantize the image of shape (n_clusters, 3). Only has an effect if do_color_quantize is set to True.

TYPE: `np.ndarray` or `List[List[int]]`, *optional*, defaults to `self.clusters` DEFAULT: None

return_tensors

The type of tensors to return. Can be one of:

  • Unset: Return a list of np.ndarray.
  • TensorType.TENSORFLOW or 'tf': Return a batch of type tf.Tensor.
  • TensorType.PYTORCH or 'pt': Return a batch of type torch.Tensor.
  • TensorType.NUMPY or 'np': Return a batch of type np.ndarray.
  • TensorType.JAX or 'jax': Return a batch of type jax.numpy.ndarray.

TYPE: `str` or `TensorType`, *optional* DEFAULT: None

data_format

The channel dimension format for the output image. Can be one of:

  • ChannelDimension.FIRST: image in (num_channels, height, width) format.
  • ChannelDimension.LAST: image in (height, width, num_channels) format. Only has an effect if do_color_quantize is set to False.

TYPE: `ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST` DEFAULT: FIRST

input_data_format

The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of:

  • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
  • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
  • "none" or ChannelDimension.NONE: image in (height, width) format.

TYPE: `ChannelDimension` or `str`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/imagegpt/image_processing_imagegpt.py 
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
def preprocess(
    self,
    images: ImageInput,
    do_resize: bool = None,
    size: Dict[str, int] = None,
    resample: PILImageResampling = None,
    do_normalize: bool = None,
    do_color_quantize: Optional[bool] = None,
    clusters: Optional[Union[List[List[int]], np.ndarray]] = None,
    return_tensors: Optional[Union[str, TensorType]] = None,
    data_format: Optional[Union[str, ChannelDimension]] = ChannelDimension.FIRST,
    input_data_format: Optional[Union[str, ChannelDimension]] = None,
    **kwargs,
) -> PIL.Image.Image:
    """
    Preprocess an image or batch of images.

    Args:
        images (`ImageInput`):
            Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If
            passing in images with pixel values between 0 and 1, set `do_normalize=False`.
        do_resize (`bool`, *optional*, defaults to `self.do_resize`):
            Whether to resize the image.
        size (`Dict[str, int]`, *optional*, defaults to `self.size`):
            Size of the image after resizing.
        resample (`int`, *optional*, defaults to `self.resample`):
            Resampling filter to use if resizing the image. This can be one of the enum `PILImageResampling`, Only
            has an effect if `do_resize` is set to `True`.
        do_normalize (`bool`, *optional*, defaults to `self.do_normalize`):
            Whether to normalize the image
        do_color_quantize (`bool`, *optional*, defaults to `self.do_color_quantize`):
            Whether to color quantize the image.
        clusters (`np.ndarray` or `List[List[int]]`, *optional*, defaults to `self.clusters`):
            Clusters used to quantize the image of shape `(n_clusters, 3)`. Only has an effect if
            `do_color_quantize` is set to `True`.
        return_tensors (`str` or `TensorType`, *optional*):
            The type of tensors to return. Can be one of:

            - Unset: Return a list of `np.ndarray`.
            - `TensorType.TENSORFLOW` or `'tf'`: Return a batch of type `tf.Tensor`.
            - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`.
            - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`.
            - `TensorType.JAX` or `'jax'`: Return a batch of type `jax.numpy.ndarray`.
        data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`):
            The channel dimension format for the output image. Can be one of:

            - `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
            - `ChannelDimension.LAST`: image in (height, width, num_channels) format.
            Only has an effect if `do_color_quantize` is set to `False`.
        input_data_format (`ChannelDimension` or `str`, *optional*):
            The channel dimension format for the input image. If unset, the channel dimension format is inferred
            from the input image. Can be one of:

            - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
            - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
            - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.
    """
    do_resize = do_resize if do_resize is not None else self.do_resize
    size = size if size is not None else self.size
    size = get_size_dict(size)
    resample = resample if resample is not None else self.resample
    do_normalize = do_normalize if do_normalize is not None else self.do_normalize
    do_color_quantize = do_color_quantize if do_color_quantize is not None else self.do_color_quantize
    clusters = clusters if clusters is not None else self.clusters
    clusters = np.array(clusters)

    images = make_list_of_images(images)

    validate_kwargs(captured_kwargs=kwargs.keys(),
                    valid_processor_keys=self._valid_processor_keys)

    if not valid_images(images):
        raise ValueError(
            "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "
            "torch.Tensor, tf.Tensor or jax.ndarray."
        )

    # Here, normalize() is using a constant factor to divide pixel values.
    # hence, the method does not need iamge_mean and image_std.
    validate_preprocess_arguments(
        do_resize=do_resize,
        size=size,
        resample=resample,
    )

    if do_color_quantize and clusters is None:
        raise ValueError(
            "Clusters must be specified if do_color_quantize is True.")

    # All transformations expect numpy arrays.
    images = [to_numpy_array(image) for image in images]

    if is_scaled_image(images[0]) and do_normalize:
        logger.warning_once(
            "It looks like you are trying to rescale already rescaled images. If you wish to do this, "
            "make sure to set `do_normalize` to `False` and that pixel values are between [-1, 1].",
        )

    if input_data_format is None:
        # We assume that all images have the same channel dimension format.
        input_data_format = infer_channel_dimension_format(images[0])

    if do_resize:
        images = [
            self.resize(image=image, size=size, resample=resample,
                        input_data_format=input_data_format)
            for image in images
        ]

    if do_normalize:
        images = [self.normalize(
            image=image, input_data_format=input_data_format) for image in images]

    if do_color_quantize:
        images = [to_channel_dimension_format(
            image, ChannelDimension.LAST, input_data_format) for image in images]
        # color quantize from (batch_size, height, width, 3) to (batch_size, height, width)
        images = np.array(images)
        images = color_quantize(
            images, clusters).reshape(images.shape[:-1])

        # flatten to (batch_size, height*width)
        batch_size = images.shape[0]
        images = images.reshape(batch_size, -1)

        # We need to convert back to a list of images to keep consistent behaviour across processors.
        images = list(images)
    else:
        images = [
            to_channel_dimension_format(
                image, data_format, input_channel_dim=input_data_format)
            for image in images
        ]

    data = {"input_ids": images}
    return BatchFeature(data=data, tensor_type=return_tensors)

mindnlp.transformers.models.imagegpt.image_processing_imagegpt.ImageGPTImageProcessor.resize(image, size, resample=PILImageResampling.BILINEAR, data_format=None, input_data_format=None, **kwargs)

Resize an image to (size["height"], size["width"]).

PARAMETER DESCRIPTION
image

Image to resize.

TYPE: `np.ndarray`

size

Dictionary in the format {"height": int, "width": int} specifying the size of the output image.

TYPE: `Dict[str, int]`

resample

PILImageResampling filter to use when resizing the image e.g. PILImageResampling.BILINEAR.

TYPE: `PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR` DEFAULT: BILINEAR

data_format

The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. Can be one of:

  • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
  • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
  • "none" or ChannelDimension.NONE: image in (height, width) format.

TYPE: `ChannelDimension` or `str`, *optional* DEFAULT: None

input_data_format

The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of:

  • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
  • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
  • "none" or ChannelDimension.NONE: image in (height, width) format.

TYPE: `ChannelDimension` or `str`, *optional* DEFAULT: None

RETURNS DESCRIPTION
ndarray

np.ndarray: The resized image.
Source code in mindnlp/transformers/models/imagegpt/image_processing_imagegpt.py 
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
def resize(
    self,
    image: np.ndarray,
    size: Dict[str, int],
    resample: PILImageResampling = PILImageResampling.BILINEAR,
    data_format: Optional[Union[str, ChannelDimension]] = None,
    input_data_format: Optional[Union[str, ChannelDimension]] = None,
    **kwargs,
) -> np.ndarray:
    """
    Resize an image to `(size["height"], size["width"])`.

    Args:
        image (`np.ndarray`):
            Image to resize.
        size (`Dict[str, int]`):
            Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image.
        resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`):
            `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BILINEAR`.
        data_format (`ChannelDimension` or `str`, *optional*):
            The channel dimension format for the output image. If unset, the channel dimension format of the input
            image is used. Can be one of:

            - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
            - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
            - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.
        input_data_format (`ChannelDimension` or `str`, *optional*):
            The channel dimension format for the input image. If unset, the channel dimension format is inferred
            from the input image. Can be one of:

            - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
            - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
            - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.

    Returns:
        `np.ndarray`: The resized image.
    """
    size = get_size_dict(size)
    if "height" not in size or "width" not in size:
        raise ValueError(
            f"The `size` dictionary must contain the keys `height` and `width`. Got {size.keys()}")
    output_size = (size["height"], size["width"])
    return resize(
        image,
        size=output_size,
        resample=resample,
        data_format=data_format,
        input_data_format=input_data_format,
        **kwargs,
    )

mindnlp.transformers.models.imagegpt.modeling_imagegpt

MindSpore OpenAI ImageGPT model.

mindnlp.transformers.models.imagegpt.modeling_imagegpt.ImageGPTAttention

Bases: Module

Source code in mindnlp/transformers/models/imagegpt/modeling_imagegpt.py 
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
class ImageGPTAttention(nn.Module):
    def __init__(self, config, is_cross_attention: Optional[bool] = False, layer_idx: Optional[int] = None):
        super().__init__()

        max_positions = config.max_position_embeddings
        self.bias = ops.tril(ops.ones((max_positions, max_positions), dtype=ms.bool_)).view(
            1, 1, max_positions, max_positions
        )
        self.masked_bias = ms.Tensor(-1e4)

        self.embed_dim = config.hidden_size
        self.num_heads = config.num_attention_heads
        self.head_dim = self.embed_dim // self.num_heads
        self.split_size = self.embed_dim
        if self.head_dim * self.num_heads != self.embed_dim:
            raise ValueError(
                f"`embed_dim` must be divisible by num_heads (got `embed_dim`: {self.embed_dim} and `num_heads`:"
                f" {self.num_heads})."
            )

        self.scale_attn_weights = config.scale_attn_weights
        self.is_cross_attention = is_cross_attention

        # Layer-wise attention scaling, reordering, and upcasting
        self.scale_attn_by_inverse_layer_idx = config.scale_attn_by_inverse_layer_idx
        self.layer_idx = layer_idx
        self.reorder_and_upcast_attn = config.reorder_and_upcast_attn

        if self.is_cross_attention:
            self.c_attn = Conv1D(2 * self.embed_dim, self.embed_dim)
            self.q_attn = Conv1D(self.embed_dim, self.embed_dim)
        else:
            self.c_attn = Conv1D(3 * self.embed_dim, self.embed_dim)
        self.c_proj = Conv1D(self.embed_dim, self.embed_dim)

        self.attn_dropout = nn.Dropout(config.attn_pdrop)
        self.resid_dropout = nn.Dropout(config.resid_pdrop)

        self.pruned_heads = set()

    def prune_heads(self, heads):
        if len(heads) == 0:
            return
        heads, index = find_pruneable_heads_and_indices(
            heads, self.num_heads, self.head_dim, self.pruned_heads)
        index_attn = ops.cat(
            [index, index + self.split_size, index + (2 * self.split_size)])

        # Prune conv1d layers
        self.c_attn = prune_conv1d_layer(self.c_attn, index_attn, dim=1)
        self.c_proj = prune_conv1d_layer(self.c_proj, index, dim=0)

        # Update hyper params
        self.split_size = (self.split_size // self.num_heads) * \
            (self.num_heads - len(heads))
        self.num_heads = self.num_heads - len(heads)
        self.pruned_heads = self.pruned_heads.union(heads)

    def _attn(self, query, key, value, attention_mask=None, head_mask=None):
        attn_weights = ops.matmul(query, key.swapaxes(-1, -2))

        if self.scale_attn_weights:
            attn_weights = attn_weights / (float(value.shape[-1]) ** 0.5)

        # Layer-wise attention scaling
        if self.scale_attn_by_inverse_layer_idx:
            attn_weights = attn_weights / float(self.layer_idx + 1)

        if not self.is_cross_attention:
            # if only "normal" attention layer implements causal mask
            query_length, key_length = query.shape[-2], key.shape[-2]
            causal_mask = self.bias[:, :, key_length -
                                    query_length: key_length, :key_length]
            mask_value = np.finfo(ms.dtype_to_nptype(attn_weights.dtype)).min
            # Need to be a tensor, otherwise we get error: `RuntimeError: expected scalar type float but found double`.
            mask_value = ms.Tensor(mask_value, dtype=attn_weights.dtype)
            attn_weights = ops.where(causal_mask, attn_weights, mask_value)

        if attention_mask is not None:
            # Apply the attention mask
            attn_weights = attn_weights + attention_mask

        attn_weights = nn.Softmax(axis=-1)(attn_weights)

        # Downcast (if necessary) back to V's dtype (if in mixed-precision) -- No-Op otherwise
        attn_weights = attn_weights.type(value.dtype)
        attn_weights = self.attn_dropout(attn_weights)

        # Mask heads if we want to
        if head_mask is not None:
            attn_weights = attn_weights * head_mask

        attn_output = ops.matmul(attn_weights, value)

        return attn_output, attn_weights

    def _upcast_and_reordered_attn(self, query, key, value, attention_mask=None, head_mask=None):
        # Use `torch.baddbmm` (a bit more efficient w/ alpha param for scaling -- from Megatron-LM)
        bsz, num_heads, q_seq_len, dk = query.shape
        _, _, k_seq_len, _ = key.shape

        # Preallocate attn_weights for `baddbmm`
        attn_weights = mnp.empty((
            bsz * num_heads, q_seq_len, k_seq_len), dtype=ms.float32)

        # Compute Scale Factor
        scale_factor = 1.0
        if self.scale_attn_weights:
            scale_factor /= float(value.shape[-1]) ** 0.5

        if self.scale_attn_by_inverse_layer_idx:
            scale_factor /= float(self.layer_idx + 1)

        # Upcast (turn off autocast) and reorder (Scale K by 1 / root(dk))
        q, k = query.reshape(-1, q_seq_len,
                             dk), key.swapaxes(-1, -2).reshape(-1, dk, k_seq_len)
        attn_weights = ops.baddbmm(attn_weights, q.astype(
            ms.float32), k.astype(ms.float32), beta=0, alpha=scale_factor)
        attn_weights = attn_weights.reshape(
            bsz, num_heads, q_seq_len, k_seq_len)

        if not self.is_cross_attention:
            # if only "normal" attention layer implements causal mask
            query_length, key_length = query.shape[-2], key.shape[-2]
            causal_mask = self.bias[:, :, key_length -
                                    query_length: key_length, :key_length]
            mask_value = np.finfo(ms.dtype_to_nptype(attn_weights.dtype)).min
            # Need to be a tensor, otherwise we get error: `RuntimeError: expected scalar type float but found double`.
            mask_value = ms.Tensor(mask_value, dtype=attn_weights.dtype)
            attn_weights = ops.where(causal_mask, attn_weights, mask_value)

        if attention_mask is not None:
            # Apply the attention mask
            attn_weights = attn_weights + attention_mask

        attn_weights = nn.Softmax(axis=-1)(attn_weights)

        # Downcast (if necessary) back to V's dtype (if in mixed-precision) -- No-Op if otherwise
        if attn_weights.dtype != ms.float32:
            raise RuntimeError(
                "Error with upcasting, attn_weights does not have dtype ms.float32")
        attn_weights = attn_weights.type(value.dtype)
        attn_weights = self.attn_dropout(attn_weights)

        # Mask heads if we want to
        if head_mask is not None:
            attn_weights = attn_weights * head_mask

        attn_output = ops.matmul(attn_weights, value)

        return attn_output, attn_weights

    def _split_heads(self, tensor, num_heads, attn_head_size):
        """
        Splits hidden_size dim into attn_head_size and num_heads
        """
        new_shape = tensor.shape[:-1] + (num_heads, attn_head_size)
        tensor = tensor.view(*new_shape)
        # (batch, head, seq_length, head_features)
        return tensor.permute(0, 2, 1, 3)

    def _merge_heads(self, tensor, num_heads, attn_head_size):
        """
        Merges attn_head_size dim and num_attn_heads dim into hidden_size
        """
        tensor = tensor.permute(0, 2, 1, 3)
        new_shape = tensor.shape[:-2] + (num_heads * attn_head_size,)
        return tensor.view(new_shape)

    def forward(
        self,
        hidden_states: ms.Tensor,
        layer_past: Optional[bool] = None,
        attention_mask: Optional[ms.Tensor] = None,
        head_mask: Optional[ms.Tensor] = None,
        encoder_hidden_states: Optional[ms.Tensor] = None,
        encoder_attention_mask: Optional[ms.Tensor] = None,
        use_cache: Optional[bool] = False,
        output_attentions: Optional[bool] = False,
    ) -> tuple:
        if encoder_hidden_states is not None:
            if not hasattr(self, "q_attn"):
                raise ValueError(
                    "If class is used as cross attention, the weights `q_attn` have to be defined. "
                    "Please make sure to instantiate class with `ImageGPTAttention(..., is_cross_attention=True)`."
                )

            query = self.q_attn(hidden_states)
            key, value = self.c_attn(encoder_hidden_states).split(
                self.split_size, dim=2)
            attention_mask = encoder_attention_mask
        else:
            query, key, value = self.c_attn(hidden_states.astype(
                self.c_attn.weight.data.dtype)).split(self.split_size, axis=2)

        query = self._split_heads(query, self.num_heads, self.head_dim)
        key = self._split_heads(key, self.num_heads, self.head_dim)
        value = self._split_heads(value, self.num_heads, self.head_dim)

        if layer_past is not None:
            past_key, past_value = layer_past
            key = ops.cat((past_key, key), axis=-2)
            value = ops.cat((past_value, value), axis=-2)

        if use_cache is True:
            present = (key, value)
        else:
            present = None

        if self.reorder_and_upcast_attn:
            attn_output, attn_weights = self._upcast_and_reordered_attn(
                query, key, value, attention_mask, head_mask)
        else:
            attn_output, attn_weights = self._attn(
                query, key, value, attention_mask, head_mask)

        attn_output = self._merge_heads(
            attn_output, self.num_heads, self.head_dim)
        attn_output = self.c_proj(attn_output)
        attn_output = self.resid_dropout(attn_output)

        outputs = (attn_output, present)
        if output_attentions:
            outputs += (attn_weights,)

        return outputs  # a, present, (attentions)

mindnlp.transformers.models.imagegpt.modeling_imagegpt.ImageGPTForCausalImageModeling

Bases: ImageGPTPreTrainedModel

Source code in mindnlp/transformers/models/imagegpt/modeling_imagegpt.py 
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
class ImageGPTForCausalImageModeling(ImageGPTPreTrainedModel):
    _tied_weights_keys = ["lm_head.weight"]

    def __init__(self, config: ImageGPTConfig):
        super().__init__(config)
        self.transformer = ImageGPTModel(config)
        self.lm_head = nn.Linear(
            config.n_embd, config.vocab_size - 1, bias=False)

        # Model parallel
        # Initialize weights and apply final processing
        self.post_init()

    def get_output_embeddings(self):
        return self.lm_head

    def set_output_embeddings(self, new_embeddings):
        self.lm_head = new_embeddings

    def prepare_inputs_for_generation(self, input_ids: ms.Tensor, past_key_values: Optional[bool] = None, **kwargs):
        token_type_ids = kwargs.get("token_type_ids", None)
        # Omit tokens covered by past_key_values
        if past_key_values:
            past_length = past_key_values[0][0].shape[2]

            # Some generation methods already pass only the last input ID
            if input_ids.shape[1] > past_length:
                remove_prefix_length = past_length
            else:
                # Default to old behavior: keep only final ID
                remove_prefix_length = input_ids.shape[1] - 1

            input_ids = input_ids[:, remove_prefix_length:]
            if token_type_ids is not None:
                token_type_ids = token_type_ids[:, -input_ids.shape[1]:]

        attention_mask = kwargs.get("attention_mask", None)
        position_ids = kwargs.get("position_ids", None)

        if attention_mask is not None and position_ids is None:
            # create position_ids on the fly for batch generation
            position_ids = attention_mask.long().cumsum(-1) - 1
            position_ids = position_ids.masked_fill(attention_mask == 0, 1)
            if past_key_values:
                position_ids = position_ids[:, -input_ids.shape[1]:]
        else:
            position_ids = None
        return {
            "input_ids": input_ids,
            "past_key_values": past_key_values,
            "use_cache": kwargs.get("use_cache"),
            "position_ids": position_ids,
            "attention_mask": attention_mask,
            "token_type_ids": token_type_ids,
        }

    def forward(
        self,
        input_ids: Optional[ms.Tensor] = None,
        past_key_values: Optional[Tuple[Tuple[ms.Tensor]]] = None,
        attention_mask: Optional[ms.Tensor] = None,
        token_type_ids: Optional[ms.Tensor] = None,
        position_ids: Optional[ms.Tensor] = None,
        head_mask: Optional[ms.Tensor] = None,
        inputs_embeds: Optional[ms.Tensor] = None,
        encoder_hidden_states: Optional[ms.Tensor] = None,
        encoder_attention_mask: Optional[ms.Tensor] = None,
        labels: Optional[ms.Tensor] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        **kwargs: Any,
    ) -> Union[Tuple, CausalLMOutputWithCrossAttentions]:
        r"""
        Args:
            labels (`ms.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
                Labels for language modeling. Note that the labels **are shifted** inside the model, i.e. you can set
                `labels = input_ids` Indices are selected in `[-100, 0, ..., config.vocab_size]` All labels set to `-100`
                are ignored (masked), the loss is only computed for labels in `[0, ..., config.vocab_size]`

        Returns:
            `Union[Tuple, CausalLMOutputWithCrossAttentions]`

        Example:
            ```python
            >>> from transformers import AutoImageProcessor, ImageGPTForCausalImageModeling
            >>> import torch
            >>> import matplotlib.pyplot as plt
            >>> import numpy as np
            ...
            >>> image_processor = AutoImageProcessor.from_pretrained("openai/imagegpt-small")
            >>> model = ImageGPTForCausalImageModeling.from_pretrained("openai/imagegpt-small")
            >>> device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
            >>> model.to(device)  # doctest: +IGNORE_RESULT
            ...
            >>> # unconditional generation of 8 images
            >>> batch_size = 4
            >>> context = torch.full((batch_size, 1), model.config.vocab_size - 1)  # initialize with SOS token
            >>> context = context.to(device)
            >>> output = model.generate(
            ...     input_ids=context, max_length=model.config.n_positions + 1, temperature=1.0, do_sample=True, top_k=40
            ... )
            ...
            >>> clusters = image_processor.clusters
            >>> height = image_processor.size["height"]
            >>> width = image_processor.size["width"]
            ...
            >>> samples = output[:, 1:].cpu().detach().numpy()
            >>> samples_img = [
            ...     np.reshape(np.rint(127.5 * (clusters[s] + 1.0)), [height, width, 3]).astype(np.uint8) for s in samples
            ... ]  # convert color cluster tokens back to pixels
            >>> f, axes = plt.subplots(1, batch_size, dpi=300)
            ...
            >>> for img, ax in zip(samples_img, axes):  # doctest: +IGNORE_RESULT
            ...     ax.axis("off")
            ...     ax.imshow(img)
            ```
        """

        if "pixel_values" in kwargs:
            warnings.warn(
                "The `pixel_values` argument is deprecated and will be removed in a future version, use `input_ids`"
                " instead.",
                FutureWarning,
            )

            if input_ids is not None:
                raise ValueError(
                    "You cannot pass both `pixel_values` and `input_ids`. Please make sure to only pass `input_ids`."
                )

            input_ids = kwargs.pop("pixel_values")

        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        transformer_outputs = self.transformer(
            input_ids,
            past_key_values=past_key_values,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            encoder_hidden_states=encoder_hidden_states,
            encoder_attention_mask=encoder_attention_mask,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )
        hidden_states = transformer_outputs[0].astype(ms.float32)

        lm_logits = self.lm_head(hidden_states)

        loss = None
        if labels is not None:
            labels = labels.astype(ms.int32)
            # Shift so that tokens < n predict n
            shift_logits = lm_logits[..., :-1, :]
            shift_labels = labels[..., 1:]
            # Flatten the tokens
            loss_fct = CrossEntropyLoss()
            loss = loss_fct(
                shift_logits.view(-1, shift_logits.shape[-1]), shift_labels.view(-1))

        if not return_dict:
            output = (lm_logits,) + transformer_outputs[1:]
            return ((loss,) + output) if loss is not None else output

        return CausalLMOutputWithCrossAttentions(
            loss=loss,
            logits=lm_logits,
            past_key_values=transformer_outputs.past_key_values,
            hidden_states=transformer_outputs.hidden_states,
            attentions=transformer_outputs.attentions,
            cross_attentions=transformer_outputs.cross_attentions,
        )

    @staticmethod
    def _reorder_cache(
        past_key_values: Tuple[Tuple[ms.Tensor]], beam_idx: ms.Tensor
    ) -> Tuple[Tuple[ms.Tensor]]:
        """
        This function is used to re-order the `past_key_values` cache if [`~PreTrainedModel.beam_search`] or
        [`~PreTrainedModel.beam_sample`] is called. This is required to match `past_key_values` with the correct
        beam_idx at every generation step.
        """
        return tuple(
            tuple(past_state.index_select(0, beam_idx)
                  for past_state in layer_past)
            for layer_past in past_key_values
        )

mindnlp.transformers.models.imagegpt.modeling_imagegpt.ImageGPTForCausalImageModeling.forward(input_ids=None, past_key_values=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, encoder_hidden_states=None, encoder_attention_mask=None, labels=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None, **kwargs)

PARAMETER DESCRIPTION
labels

Labels for language modeling. Note that the labels are shifted inside the model, i.e. you can set labels = input_ids Indices are selected in [-100, 0, ..., config.vocab_size] All labels set to -100 are ignored (masked), the loss is only computed for labels in [0, ..., config.vocab_size]

TYPE: `ms.Tensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

RETURNS DESCRIPTION
Union[Tuple, CausalLMOutputWithCrossAttentions]

Union[Tuple, CausalLMOutputWithCrossAttentions]
Example 
>>> from transformers import AutoImageProcessor, ImageGPTForCausalImageModeling
>>> import torch
>>> import matplotlib.pyplot as plt
>>> import numpy as np
...
>>> image_processor = AutoImageProcessor.from_pretrained("openai/imagegpt-small")
>>> model = ImageGPTForCausalImageModeling.from_pretrained("openai/imagegpt-small")
>>> device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
>>> model.to(device)  # doctest: +IGNORE_RESULT
...
>>> # unconditional generation of 8 images
>>> batch_size = 4
>>> context = torch.full((batch_size, 1), model.config.vocab_size - 1)  # initialize with SOS token
>>> context = context.to(device)
>>> output = model.generate(
...     input_ids=context, max_length=model.config.n_positions + 1, temperature=1.0, do_sample=True, top_k=40
... )
...
>>> clusters = image_processor.clusters
>>> height = image_processor.size["height"]
>>> width = image_processor.size["width"]
...
>>> samples = output[:, 1:].cpu().detach().numpy()
>>> samples_img = [
...     np.reshape(np.rint(127.5 * (clusters[s] + 1.0)), [height, width, 3]).astype(np.uint8) for s in samples
... ]  # convert color cluster tokens back to pixels
>>> f, axes = plt.subplots(1, batch_size, dpi=300)
...
>>> for img, ax in zip(samples_img, axes):  # doctest: +IGNORE_RESULT
...     ax.axis("off")
...     ax.imshow(img)
Source code in mindnlp/transformers/models/imagegpt/modeling_imagegpt.py 
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
def forward(
    self,
    input_ids: Optional[ms.Tensor] = None,
    past_key_values: Optional[Tuple[Tuple[ms.Tensor]]] = None,
    attention_mask: Optional[ms.Tensor] = None,
    token_type_ids: Optional[ms.Tensor] = None,
    position_ids: Optional[ms.Tensor] = None,
    head_mask: Optional[ms.Tensor] = None,
    inputs_embeds: Optional[ms.Tensor] = None,
    encoder_hidden_states: Optional[ms.Tensor] = None,
    encoder_attention_mask: Optional[ms.Tensor] = None,
    labels: Optional[ms.Tensor] = None,
    use_cache: Optional[bool] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
    **kwargs: Any,
) -> Union[Tuple, CausalLMOutputWithCrossAttentions]:
    r"""
    Args:
        labels (`ms.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for language modeling. Note that the labels **are shifted** inside the model, i.e. you can set
            `labels = input_ids` Indices are selected in `[-100, 0, ..., config.vocab_size]` All labels set to `-100`
            are ignored (masked), the loss is only computed for labels in `[0, ..., config.vocab_size]`

    Returns:
        `Union[Tuple, CausalLMOutputWithCrossAttentions]`

    Example:
        ```python
        >>> from transformers import AutoImageProcessor, ImageGPTForCausalImageModeling
        >>> import torch
        >>> import matplotlib.pyplot as plt
        >>> import numpy as np
        ...
        >>> image_processor = AutoImageProcessor.from_pretrained("openai/imagegpt-small")
        >>> model = ImageGPTForCausalImageModeling.from_pretrained("openai/imagegpt-small")
        >>> device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
        >>> model.to(device)  # doctest: +IGNORE_RESULT
        ...
        >>> # unconditional generation of 8 images
        >>> batch_size = 4
        >>> context = torch.full((batch_size, 1), model.config.vocab_size - 1)  # initialize with SOS token
        >>> context = context.to(device)
        >>> output = model.generate(
        ...     input_ids=context, max_length=model.config.n_positions + 1, temperature=1.0, do_sample=True, top_k=40
        ... )
        ...
        >>> clusters = image_processor.clusters
        >>> height = image_processor.size["height"]
        >>> width = image_processor.size["width"]
        ...
        >>> samples = output[:, 1:].cpu().detach().numpy()
        >>> samples_img = [
        ...     np.reshape(np.rint(127.5 * (clusters[s] + 1.0)), [height, width, 3]).astype(np.uint8) for s in samples
        ... ]  # convert color cluster tokens back to pixels
        >>> f, axes = plt.subplots(1, batch_size, dpi=300)
        ...
        >>> for img, ax in zip(samples_img, axes):  # doctest: +IGNORE_RESULT
        ...     ax.axis("off")
        ...     ax.imshow(img)
        ```
    """

    if "pixel_values" in kwargs:
        warnings.warn(
            "The `pixel_values` argument is deprecated and will be removed in a future version, use `input_ids`"
            " instead.",
            FutureWarning,
        )

        if input_ids is not None:
            raise ValueError(
                "You cannot pass both `pixel_values` and `input_ids`. Please make sure to only pass `input_ids`."
            )

        input_ids = kwargs.pop("pixel_values")

    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    transformer_outputs = self.transformer(
        input_ids,
        past_key_values=past_key_values,
        attention_mask=attention_mask,
        token_type_ids=token_type_ids,
        position_ids=position_ids,
        head_mask=head_mask,
        inputs_embeds=inputs_embeds,
        encoder_hidden_states=encoder_hidden_states,
        encoder_attention_mask=encoder_attention_mask,
        use_cache=use_cache,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )
    hidden_states = transformer_outputs[0].astype(ms.float32)

    lm_logits = self.lm_head(hidden_states)

    loss = None
    if labels is not None:
        labels = labels.astype(ms.int32)
        # Shift so that tokens < n predict n
        shift_logits = lm_logits[..., :-1, :]
        shift_labels = labels[..., 1:]
        # Flatten the tokens
        loss_fct = CrossEntropyLoss()
        loss = loss_fct(
            shift_logits.view(-1, shift_logits.shape[-1]), shift_labels.view(-1))

    if not return_dict:
        output = (lm_logits,) + transformer_outputs[1:]
        return ((loss,) + output) if loss is not None else output

    return CausalLMOutputWithCrossAttentions(
        loss=loss,
        logits=lm_logits,
        past_key_values=transformer_outputs.past_key_values,
        hidden_states=transformer_outputs.hidden_states,
        attentions=transformer_outputs.attentions,
        cross_attentions=transformer_outputs.cross_attentions,
    )

mindnlp.transformers.models.imagegpt.modeling_imagegpt.ImageGPTForImageClassification

Bases: ImageGPTPreTrainedModel

Source code in mindnlp/transformers/models/imagegpt/modeling_imagegpt.py 
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
class ImageGPTForImageClassification(ImageGPTPreTrainedModel):
    def __init__(self, config: ImageGPTConfig):
        super().__init__(config)
        self.num_labels = config.num_labels
        self.transformer = ImageGPTModel(config)
        self.score = nn.Linear(config.n_embd, self.num_labels, bias=False)

        # Initialize weights and apply final processing
        self.post_init()

    def forward(
        self,
        input_ids: Optional[ms.Tensor] = None,
        past_key_values: Optional[Tuple[Tuple[ms.Tensor]]] = None,
        attention_mask: Optional[ms.Tensor] = None,
        token_type_ids: Optional[ms.Tensor] = None,
        position_ids: Optional[ms.Tensor] = None,
        head_mask: Optional[ms.Tensor] = None,
        inputs_embeds: Optional[ms.Tensor] = None,
        labels: Optional[ms.Tensor] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        **kwargs: Any,
    ) -> Union[Tuple, SequenceClassifierOutputWithPast]:
        r"""
        Args:
            labels (`ms.Tensor` of shape `(batch_size,)`, *optional*):
                Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
                config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
                `config.num_labels > 1` a classification loss is computed (Cross-Entropy).

        Returns:
            `Union[Tuple, SequenceClassifierOutputWithPast]`

        Example:
            ```python
            >>> from transformers import AutoImageProcessor, ImageGPTForImageClassification
            >>> from PIL import Image
            >>> import requests
            ...
            >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
            >>> image = Image.open(requests.get(url, stream=True).raw)
            ...
            >>> image_processor = AutoImageProcessor.from_pretrained("openai/imagegpt-small")
            >>> model = ImageGPTForImageClassification.from_pretrained("openai/imagegpt-small")
            ...
            >>> inputs = image_processor(images=image, return_tensors="pt")
            >>> outputs = model(**inputs)
            >>> logits = outputs.logits
            ```
        """

        if "pixel_values" in kwargs:
            warnings.warn(
                "The `pixel_values` argument is deprecated and will be removed in a future version, use `input_ids`"
                " instead.",
                FutureWarning,
            )

            if input_ids is not None:
                raise ValueError(
                    "You cannot pass both `pixel_values` and `input_ids`. Please make sure to only pass `input_ids`."
                )

            input_ids = kwargs.pop("pixel_values")

        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        transformer_outputs = self.transformer(
            input_ids,
            past_key_values=past_key_values,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )
        hidden_states = transformer_outputs[0].astype(ms.float32)
        # average-pool the hidden states along the sequence dimension
        pooled_hidden_states = hidden_states.mean(axis=1)
        # project from (batch_size, hidden_size) to (batch_size, num_labels)
        logits = self.score(pooled_hidden_states)

        loss = None
        if labels is not None:
            labels = labels.astype(ms.int32)
            if self.config.problem_type is None:
                if self.num_labels == 1:
                    self.config.problem_type = "regression"
                elif self.num_labels > 1 and (labels.dtype in (ms.int64, ms.int32)):
                    self.config.problem_type = "single_label_classification"
                else:
                    self.config.problem_type = "multi_label_classification"

            if self.config.problem_type == "regression":
                loss_fct = MSELoss()
                if self.num_labels == 1:
                    loss = loss_fct(logits.squeeze(), labels.squeeze())
                else:
                    loss = loss_fct(logits, labels)
            elif self.config.problem_type == "single_label_classification":
                loss_fct = CrossEntropyLoss()

                l_result = logits.view(-1, self.num_labels)
                lab = labels.view(-1)

                loss = loss_fct(l_result, lab)
            elif self.config.problem_type == "multi_label_classification":
                loss_fct = BCEWithLogitsLoss()
                loss = loss_fct(logits, labels)
        if not return_dict:
            output = (logits,) + transformer_outputs[1:]
            return ((loss,) + output) if loss is not None else output

        return SequenceClassifierOutputWithPast(
            loss=loss,
            logits=logits,
            past_key_values=transformer_outputs.past_key_values,
            hidden_states=transformer_outputs.hidden_states,
            attentions=transformer_outputs.attentions,
        )

mindnlp.transformers.models.imagegpt.modeling_imagegpt.ImageGPTForImageClassification.forward(input_ids=None, past_key_values=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None, **kwargs)

PARAMETER DESCRIPTION
labels

Labels for computing the sequence classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels == 1 a regression loss is computed (Mean-Square loss), If config.num_labels > 1 a classification loss is computed (Cross-Entropy).

TYPE: `ms.Tensor` of shape `(batch_size,)`, *optional* DEFAULT: None

RETURNS DESCRIPTION
Union[Tuple, SequenceClassifierOutputWithPast]

Union[Tuple, SequenceClassifierOutputWithPast]
Example 
>>> from transformers import AutoImageProcessor, ImageGPTForImageClassification
>>> from PIL import Image
>>> import requests
...
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)
...
>>> image_processor = AutoImageProcessor.from_pretrained("openai/imagegpt-small")
>>> model = ImageGPTForImageClassification.from_pretrained("openai/imagegpt-small")
...
>>> inputs = image_processor(images=image, return_tensors="pt")
>>> outputs = model(**inputs)
>>> logits = outputs.logits
Source code in mindnlp/transformers/models/imagegpt/modeling_imagegpt.py 
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
def forward(
    self,
    input_ids: Optional[ms.Tensor] = None,
    past_key_values: Optional[Tuple[Tuple[ms.Tensor]]] = None,
    attention_mask: Optional[ms.Tensor] = None,
    token_type_ids: Optional[ms.Tensor] = None,
    position_ids: Optional[ms.Tensor] = None,
    head_mask: Optional[ms.Tensor] = None,
    inputs_embeds: Optional[ms.Tensor] = None,
    labels: Optional[ms.Tensor] = None,
    use_cache: Optional[bool] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
    **kwargs: Any,
) -> Union[Tuple, SequenceClassifierOutputWithPast]:
    r"""
    Args:
        labels (`ms.Tensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).

    Returns:
        `Union[Tuple, SequenceClassifierOutputWithPast]`

    Example:
        ```python
        >>> from transformers import AutoImageProcessor, ImageGPTForImageClassification
        >>> from PIL import Image
        >>> import requests
        ...
        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
        >>> image = Image.open(requests.get(url, stream=True).raw)
        ...
        >>> image_processor = AutoImageProcessor.from_pretrained("openai/imagegpt-small")
        >>> model = ImageGPTForImageClassification.from_pretrained("openai/imagegpt-small")
        ...
        >>> inputs = image_processor(images=image, return_tensors="pt")
        >>> outputs = model(**inputs)
        >>> logits = outputs.logits
        ```
    """

    if "pixel_values" in kwargs:
        warnings.warn(
            "The `pixel_values` argument is deprecated and will be removed in a future version, use `input_ids`"
            " instead.",
            FutureWarning,
        )

        if input_ids is not None:
            raise ValueError(
                "You cannot pass both `pixel_values` and `input_ids`. Please make sure to only pass `input_ids`."
            )

        input_ids = kwargs.pop("pixel_values")

    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    transformer_outputs = self.transformer(
        input_ids,
        past_key_values=past_key_values,
        attention_mask=attention_mask,
        token_type_ids=token_type_ids,
        position_ids=position_ids,
        head_mask=head_mask,
        inputs_embeds=inputs_embeds,
        use_cache=use_cache,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )
    hidden_states = transformer_outputs[0].astype(ms.float32)
    # average-pool the hidden states along the sequence dimension
    pooled_hidden_states = hidden_states.mean(axis=1)
    # project from (batch_size, hidden_size) to (batch_size, num_labels)
    logits = self.score(pooled_hidden_states)

    loss = None
    if labels is not None:
        labels = labels.astype(ms.int32)
        if self.config.problem_type is None:
            if self.num_labels == 1:
                self.config.problem_type = "regression"
            elif self.num_labels > 1 and (labels.dtype in (ms.int64, ms.int32)):
                self.config.problem_type = "single_label_classification"
            else:
                self.config.problem_type = "multi_label_classification"

        if self.config.problem_type == "regression":
            loss_fct = MSELoss()
            if self.num_labels == 1:
                loss = loss_fct(logits.squeeze(), labels.squeeze())
            else:
                loss = loss_fct(logits, labels)
        elif self.config.problem_type == "single_label_classification":
            loss_fct = CrossEntropyLoss()

            l_result = logits.view(-1, self.num_labels)
            lab = labels.view(-1)

            loss = loss_fct(l_result, lab)
        elif self.config.problem_type == "multi_label_classification":
            loss_fct = BCEWithLogitsLoss()
            loss = loss_fct(logits, labels)
    if not return_dict:
        output = (logits,) + transformer_outputs[1:]
        return ((loss,) + output) if loss is not None else output

    return SequenceClassifierOutputWithPast(
        loss=loss,
        logits=logits,
        past_key_values=transformer_outputs.past_key_values,
        hidden_states=transformer_outputs.hidden_states,
        attentions=transformer_outputs.attentions,
    )

mindnlp.transformers.models.imagegpt.modeling_imagegpt.ImageGPTModel

Bases: ImageGPTPreTrainedModel

Source code in mindnlp/transformers/models/imagegpt/modeling_imagegpt.py 
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
class ImageGPTModel(ImageGPTPreTrainedModel):
    def __init__(self, config: ImageGPTConfig):
        super().__init__(config)

        self.embed_dim = config.hidden_size

        self.wte = nn.Embedding(config.vocab_size, self.embed_dim)
        self.wpe = nn.Embedding(config.max_position_embeddings, self.embed_dim)

        self.drop = nn.Dropout(config.embd_pdrop)
        self.h = nn.ModuleList([ImageGPTBlock(config, layer_idx=i)
                             for i in range(config.num_hidden_layers)])
        self.ln_f = ImageGPTLayerNorm(
            self.embed_dim, eps=config.layer_norm_epsilon)

        # Model parallel
        self.gradient_checkpointing = False
        # Initialize weights and apply final processing
        self.post_init()

    def get_input_embeddings(self):
        return self.wte

    def set_input_embeddings(self, new_embeddings):
        self.wte = new_embeddings

    def _prune_heads(self, heads_to_prune):
        """
        Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer}
        """
        for layer, heads in heads_to_prune.items():
            self.h[layer].attn.prune_heads(heads)

    def forward(
        self,
        input_ids: Optional[ms.Tensor] = None,
        past_key_values: Optional[Tuple[Tuple[ms.Tensor]]] = None,
        attention_mask: Optional[ms.Tensor] = None,
        token_type_ids: Optional[ms.Tensor] = None,
        position_ids: Optional[ms.Tensor] = None,
        head_mask: Optional[ms.Tensor] = None,
        inputs_embeds: Optional[ms.Tensor] = None,
        encoder_hidden_states: Optional[ms.Tensor] = None,
        encoder_attention_mask: Optional[ms.Tensor] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        **kwargs: Any,
    ) -> Union[Tuple, BaseModelOutputWithPastAndCrossAttentions]:
        r"""
        Args:
            labels (`ms.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
                Labels for language modeling. Note that the labels **are shifted** inside the model, i.e. you can set
                `labels = input_ids` Indices are selected in `[-100, 0, ..., config.vocab_size]` All labels set to `-100`
                are ignored (masked), the loss is only computed for labels in `[0, ..., config.vocab_size]`

        Returns:
            `Union[Tuple, BaseModelOutputWithPastAndCrossAttentions]`

        Example:
            ```python
            >>> from transformers import AutoImageProcessor, ImageGPTModel
            >>> from PIL import Image
            >>> import requests
            ...
            >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
            >>> image = Image.open(requests.get(url, stream=True).raw)
            ...
            >>> image_processor = AutoImageProcessor.from_pretrained("openai/imagegpt-small")
            >>> model = ImageGPTModel.from_pretrained("openai/imagegpt-small")
            ...
            >>> inputs = image_processor(images=image, return_tensors="pt")
            >>> outputs = model(**inputs)
            >>> last_hidden_states = outputs.last_hidden_state
            ```
        """

        if "pixel_values" in kwargs:
            warnings.warn(
                "The `pixel_values` argument is deprecated and will be removed in a future version, use `input_ids`"
                " instead.",
                FutureWarning,
            )

            if input_ids is not None:
                raise ValueError(
                    "You cannot pass both `pixel_values` and `input_ids`. Please make sure to only pass `input_ids`."
                )

            input_ids = kwargs.pop("pixel_values")

        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
        output_hidden_states = (
            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
        )
        use_cache = use_cache if use_cache is not None else self.config.use_cache
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if input_ids is not None and inputs_embeds is not None:
            raise ValueError(
                "You cannot specify both input_ids and inputs_embeds at the same time")
        elif input_ids is not None:
            self.warn_if_padding_and_no_attention_mask(
                input_ids, attention_mask)
            input_shape = input_ids.shape
            input_ids = input_ids.view(-1, input_shape[-1])
            batch_size = input_ids.shape[0]
        elif inputs_embeds is not None:
            input_shape = inputs_embeds.shape[:-1]
            batch_size = inputs_embeds.shape[0]
        else:
            raise ValueError(
                "You have to specify either input_ids or inputs_embeds")

        if token_type_ids is not None:
            token_type_ids = token_type_ids.view(-1, input_shape[-1])

        if past_key_values is None:
            past_length = 0
            past_key_values = tuple([None] * len(self.h))
        else:
            past_length = past_key_values[0][0].shape[-2]
        if position_ids is None:
            position_ids = ops.arange(
                past_length, input_shape[-1] + past_length, dtype=ms.int64)
            position_ids = position_ids.unsqueeze(0)

        # ImageGPTAttention mask.
        if attention_mask is not None:
            if batch_size <= 0:
                raise ValueError("batch_size has to be defined and > 0")
            attention_mask = attention_mask.view(batch_size, -1)
            # We create a 3D attention mask from a 2D tensor mask.
            # Sizes are [batch_size, 1, 1, to_seq_length]
            # So we can broadcast to [batch_size, num_heads, from_seq_length, to_seq_length]
            # this attention mask is more simple than the triangular masking of causal attention
            # used in OpenAI GPT, we just need to prepare the broadcast dimension here.
            attention_mask = attention_mask[:, None, None, :]

            # Since attention_mask is 1.0 for positions we want to attend and 0.0 for
            # masked positions, this operation will create a tensor which is 0.0 for
            # positions we want to attend and the dtype's smallest value for masked positions.
            # Since we are adding it to the raw scores before the softmax, this is
            # effectively the same as removing these entirely.
            attention_mask = (1.0 - attention_mask) * \
                np.finfo(ms.dtype_to_nptype(self.dtype)).min

        # If a 2D or 3D attention mask is provided for the cross-attention
        # we need to make broadcastable to [batch_size, num_heads, seq_length, seq_length]
        if self.config.add_cross_attention and encoder_hidden_states is not None:
            encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states.shape
            encoder_hidden_shape = (
                encoder_batch_size, encoder_sequence_length)
            if encoder_attention_mask is None:
                encoder_attention_mask = ops.ones(encoder_hidden_shape)
            encoder_attention_mask = self.invert_attention_mask(
                encoder_attention_mask)
        else:
            encoder_attention_mask = None

        # Prepare head mask if needed
        # 1.0 in head_mask indicate we keep the head
        # attention_probs has shape bsz x n_heads x N x N
        # head_mask has shape n_layer x batch x n_heads x N x N
        head_mask = self.get_head_mask(head_mask, self.config.n_layer)

        if inputs_embeds is None:
            inputs_embeds = self.wte(input_ids)
        position_embeds = self.wpe(position_ids)
        hidden_states = inputs_embeds + position_embeds

        if token_type_ids is not None:
            token_type_embeds = self.wte(token_type_ids)
            hidden_states = hidden_states + token_type_embeds

        hidden_states = self.drop(hidden_states)

        output_shape = input_shape + (hidden_states.shape[-1],)

        if self.gradient_checkpointing and self.training:
            if use_cache:
                logger.warning_once(
                    "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
                )
                use_cache = False

        presents = () if use_cache else None
        all_self_attentions = () if output_attentions else None
        all_cross_attentions = () if output_attentions and self.config.add_cross_attention else None
        all_hidden_states = () if output_hidden_states else None
        for i, (block, layer_past) in enumerate(zip(self.h, past_key_values)):
            # Model parallel
            if output_hidden_states:
                all_hidden_states = all_hidden_states + (hidden_states,)

            if self.gradient_checkpointing and self.training:
                outputs = self._gradient_checkpointing_func(
                    block.__call__,
                    hidden_states,
                    None,
                    attention_mask,
                    head_mask[i],
                    encoder_hidden_states,
                    encoder_attention_mask,
                    use_cache,
                    output_attentions,
                )
            else:
                outputs = block(
                    hidden_states,
                    layer_past=layer_past,
                    attention_mask=attention_mask,
                    head_mask=head_mask[i],
                    encoder_hidden_states=encoder_hidden_states,
                    encoder_attention_mask=encoder_attention_mask,
                    use_cache=use_cache,
                    output_attentions=output_attentions,
                )

            hidden_states = outputs[0]
            if use_cache is True:
                presents = presents + (outputs[1],)

            if output_attentions:
                all_self_attentions = all_self_attentions + \
                    (outputs[2 if use_cache else 1],)
                if self.config.add_cross_attention:
                    all_cross_attentions = all_cross_attentions + \
                        (outputs[3 if use_cache else 2],)

        hidden_states = self.ln_f(hidden_states)

        hidden_states = hidden_states.view(*output_shape)
        # Add last hidden state
        if output_hidden_states:
            all_hidden_states = all_hidden_states + (hidden_states,)

        if not return_dict:
            return tuple(
                v
                for v in [hidden_states, presents, all_hidden_states, all_self_attentions, all_cross_attentions]
                if v is not None
            )

        return BaseModelOutputWithPastAndCrossAttentions(
            last_hidden_state=hidden_states,
            past_key_values=presents,
            hidden_states=all_hidden_states,
            attentions=all_self_attentions,
            cross_attentions=all_cross_attentions,
        )

mindnlp.transformers.models.imagegpt.modeling_imagegpt.ImageGPTModel.forward(input_ids=None, past_key_values=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, encoder_hidden_states=None, encoder_attention_mask=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None, **kwargs)

PARAMETER DESCRIPTION
labels

Labels for language modeling. Note that the labels are shifted inside the model, i.e. you can set labels = input_ids Indices are selected in [-100, 0, ..., config.vocab_size] All labels set to -100 are ignored (masked), the loss is only computed for labels in [0, ..., config.vocab_size]

TYPE: `ms.Tensor` of shape `(batch_size, sequence_length)`, *optional*

RETURNS DESCRIPTION
Union[Tuple, BaseModelOutputWithPastAndCrossAttentions]

Union[Tuple, BaseModelOutputWithPastAndCrossAttentions]
Example 
>>> from transformers import AutoImageProcessor, ImageGPTModel
>>> from PIL import Image
>>> import requests
...
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)
...
>>> image_processor = AutoImageProcessor.from_pretrained("openai/imagegpt-small")
>>> model = ImageGPTModel.from_pretrained("openai/imagegpt-small")
...
>>> inputs = image_processor(images=image, return_tensors="pt")
>>> outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_state
Source code in mindnlp/transformers/models/imagegpt/modeling_imagegpt.py 
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
def forward(
    self,
    input_ids: Optional[ms.Tensor] = None,
    past_key_values: Optional[Tuple[Tuple[ms.Tensor]]] = None,
    attention_mask: Optional[ms.Tensor] = None,
    token_type_ids: Optional[ms.Tensor] = None,
    position_ids: Optional[ms.Tensor] = None,
    head_mask: Optional[ms.Tensor] = None,
    inputs_embeds: Optional[ms.Tensor] = None,
    encoder_hidden_states: Optional[ms.Tensor] = None,
    encoder_attention_mask: Optional[ms.Tensor] = None,
    use_cache: Optional[bool] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
    **kwargs: Any,
) -> Union[Tuple, BaseModelOutputWithPastAndCrossAttentions]:
    r"""
    Args:
        labels (`ms.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for language modeling. Note that the labels **are shifted** inside the model, i.e. you can set
            `labels = input_ids` Indices are selected in `[-100, 0, ..., config.vocab_size]` All labels set to `-100`
            are ignored (masked), the loss is only computed for labels in `[0, ..., config.vocab_size]`

    Returns:
        `Union[Tuple, BaseModelOutputWithPastAndCrossAttentions]`

    Example:
        ```python
        >>> from transformers import AutoImageProcessor, ImageGPTModel
        >>> from PIL import Image
        >>> import requests
        ...
        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
        >>> image = Image.open(requests.get(url, stream=True).raw)
        ...
        >>> image_processor = AutoImageProcessor.from_pretrained("openai/imagegpt-small")
        >>> model = ImageGPTModel.from_pretrained("openai/imagegpt-small")
        ...
        >>> inputs = image_processor(images=image, return_tensors="pt")
        >>> outputs = model(**inputs)
        >>> last_hidden_states = outputs.last_hidden_state
        ```
    """

    if "pixel_values" in kwargs:
        warnings.warn(
            "The `pixel_values` argument is deprecated and will be removed in a future version, use `input_ids`"
            " instead.",
            FutureWarning,
        )

        if input_ids is not None:
            raise ValueError(
                "You cannot pass both `pixel_values` and `input_ids`. Please make sure to only pass `input_ids`."
            )

        input_ids = kwargs.pop("pixel_values")

    output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
    output_hidden_states = (
        output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
    )
    use_cache = use_cache if use_cache is not None else self.config.use_cache
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    if input_ids is not None and inputs_embeds is not None:
        raise ValueError(
            "You cannot specify both input_ids and inputs_embeds at the same time")
    elif input_ids is not None:
        self.warn_if_padding_and_no_attention_mask(
            input_ids, attention_mask)
        input_shape = input_ids.shape
        input_ids = input_ids.view(-1, input_shape[-1])
        batch_size = input_ids.shape[0]
    elif inputs_embeds is not None:
        input_shape = inputs_embeds.shape[:-1]
        batch_size = inputs_embeds.shape[0]
    else:
        raise ValueError(
            "You have to specify either input_ids or inputs_embeds")

    if token_type_ids is not None:
        token_type_ids = token_type_ids.view(-1, input_shape[-1])

    if past_key_values is None:
        past_length = 0
        past_key_values = tuple([None] * len(self.h))
    else:
        past_length = past_key_values[0][0].shape[-2]
    if position_ids is None:
        position_ids = ops.arange(
            past_length, input_shape[-1] + past_length, dtype=ms.int64)
        position_ids = position_ids.unsqueeze(0)

    # ImageGPTAttention mask.
    if attention_mask is not None:
        if batch_size <= 0:
            raise ValueError("batch_size has to be defined and > 0")
        attention_mask = attention_mask.view(batch_size, -1)
        # We create a 3D attention mask from a 2D tensor mask.
        # Sizes are [batch_size, 1, 1, to_seq_length]
        # So we can broadcast to [batch_size, num_heads, from_seq_length, to_seq_length]
        # this attention mask is more simple than the triangular masking of causal attention
        # used in OpenAI GPT, we just need to prepare the broadcast dimension here.
        attention_mask = attention_mask[:, None, None, :]

        # Since attention_mask is 1.0 for positions we want to attend and 0.0 for
        # masked positions, this operation will create a tensor which is 0.0 for
        # positions we want to attend and the dtype's smallest value for masked positions.
        # Since we are adding it to the raw scores before the softmax, this is
        # effectively the same as removing these entirely.
        attention_mask = (1.0 - attention_mask) * \
            np.finfo(ms.dtype_to_nptype(self.dtype)).min

    # If a 2D or 3D attention mask is provided for the cross-attention
    # we need to make broadcastable to [batch_size, num_heads, seq_length, seq_length]
    if self.config.add_cross_attention and encoder_hidden_states is not None:
        encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states.shape
        encoder_hidden_shape = (
            encoder_batch_size, encoder_sequence_length)
        if encoder_attention_mask is None:
            encoder_attention_mask = ops.ones(encoder_hidden_shape)
        encoder_attention_mask = self.invert_attention_mask(
            encoder_attention_mask)
    else:
        encoder_attention_mask = None

    # Prepare head mask if needed
    # 1.0 in head_mask indicate we keep the head
    # attention_probs has shape bsz x n_heads x N x N
    # head_mask has shape n_layer x batch x n_heads x N x N
    head_mask = self.get_head_mask(head_mask, self.config.n_layer)

    if inputs_embeds is None:
        inputs_embeds = self.wte(input_ids)
    position_embeds = self.wpe(position_ids)
    hidden_states = inputs_embeds + position_embeds

    if token_type_ids is not None:
        token_type_embeds = self.wte(token_type_ids)
        hidden_states = hidden_states + token_type_embeds

    hidden_states = self.drop(hidden_states)

    output_shape = input_shape + (hidden_states.shape[-1],)

    if self.gradient_checkpointing and self.training:
        if use_cache:
            logger.warning_once(
                "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
            )
            use_cache = False

    presents = () if use_cache else None
    all_self_attentions = () if output_attentions else None
    all_cross_attentions = () if output_attentions and self.config.add_cross_attention else None
    all_hidden_states = () if output_hidden_states else None
    for i, (block, layer_past) in enumerate(zip(self.h, past_key_values)):
        # Model parallel
        if output_hidden_states:
            all_hidden_states = all_hidden_states + (hidden_states,)

        if self.gradient_checkpointing and self.training:
            outputs = self._gradient_checkpointing_func(
                block.__call__,
                hidden_states,
                None,
                attention_mask,
                head_mask[i],
                encoder_hidden_states,
                encoder_attention_mask,
                use_cache,
                output_attentions,
            )
        else:
            outputs = block(
                hidden_states,
                layer_past=layer_past,
                attention_mask=attention_mask,
                head_mask=head_mask[i],
                encoder_hidden_states=encoder_hidden_states,
                encoder_attention_mask=encoder_attention_mask,
                use_cache=use_cache,
                output_attentions=output_attentions,
            )

        hidden_states = outputs[0]
        if use_cache is True:
            presents = presents + (outputs[1],)

        if output_attentions:
            all_self_attentions = all_self_attentions + \
                (outputs[2 if use_cache else 1],)
            if self.config.add_cross_attention:
                all_cross_attentions = all_cross_attentions + \
                    (outputs[3 if use_cache else 2],)

    hidden_states = self.ln_f(hidden_states)

    hidden_states = hidden_states.view(*output_shape)
    # Add last hidden state
    if output_hidden_states:
        all_hidden_states = all_hidden_states + (hidden_states,)

    if not return_dict:
        return tuple(
            v
            for v in [hidden_states, presents, all_hidden_states, all_self_attentions, all_cross_attentions]
            if v is not None
        )

    return BaseModelOutputWithPastAndCrossAttentions(
        last_hidden_state=hidden_states,
        past_key_values=presents,
        hidden_states=all_hidden_states,
        attentions=all_self_attentions,
        cross_attentions=all_cross_attentions,
    )

mindnlp.transformers.models.imagegpt.modeling_imagegpt.ImageGPTPreTrainedModel

Bases: PreTrainedModel

An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.

Source code in mindnlp/transformers/models/imagegpt/modeling_imagegpt.py 
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
class ImageGPTPreTrainedModel(PreTrainedModel):
    """
    An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained
    models.
    """

    config_class = ImageGPTConfig
    load_tf_weights = load_tf_weights_in_imagegpt
    base_model_prefix = "transformer"
    main_input_name = "input_ids"
    supports_gradient_checkpointing = True
    _no_split_cells = ["ImageGPTBlock"]

    def __init__(self, *inputs, **kwargs):
        super().__init__(*inputs)

    def _init_weights(self, cell):
        """Initialize the weights."""
        if isinstance(cell, (nn.Linear, Conv1D)):
            # Slightly different from the TF version which uses truncated_normal for initialization
            # cf https://github.com/pytorch/pytorch/pull/5617
            cell.weight.data.initialize(Normal(self.config.initializer_range))
            if cell.bias is not None:
                cell.bias.initialize('zeros')

        elif isinstance(cell, nn.Embedding):
            cell.weight.data.initialize(Normal(self.config.initializer_range))
            if cell.padding_idx is not None:
                cell.weight.data[cell.padding_idx].initialize('zeros')

        elif isinstance(cell, ImageGPTLayerNorm):
            cell.weight.data.fill(1.0)

        # Reinitialize selected weights subject to the OpenAI GPT-2 Paper Scheme:
        #   > A modified initialization which accounts for the accumulation on the residual path with model depth. Scale
        #   > the weights of residual layers at initialization by a factor of 1/√N where N is the # of residual layers.
        #   >   -- GPT-2 :: https://openai.com/blog/better-language-models/
        #
        # Reference (Megatron-LM): https://github.com/NVIDIA/Megatron-LM/blob/main/megatron/model/gpt_model.py
        for name, p in cell.parameters_and_names():
            if "c_proj" in name and "weight" in name:
                # Special Scaled Initialization --> There are 2 Layer Norms per Transformer Block
                p.data.initialize(
                    Normal((self.config.initializer_range / math.sqrt(2 * self.config.n_layer))))

mindnlp.transformers.models.imagegpt.modeling_imagegpt.load_tf_weights_in_imagegpt(model, config, imagegpt_checkpoint_path)

Load tf checkpoints in a pytorch model

Source code in mindnlp/transformers/models/imagegpt/modeling_imagegpt.py 
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
def load_tf_weights_in_imagegpt(model, config, imagegpt_checkpoint_path):
    """
    Load tf checkpoints in a pytorch model
    """
    try:
        import re

        import tensorflow as tf
    except ImportError:
        logger.error(
            "Loading a TensorFlow model in PyTorch, requires TensorFlow to be installed. Please see "
            "https://www.tensorflow.org/install/ for installation instructions."
        )
        raise
    tf_path = os.path.abspath(imagegpt_checkpoint_path)
    logger.info("Converting TensorFlow checkpoint from {}".format(tf_path))
    # Load weights from TF model
    init_vars = tf.train.list_variables(tf_path)
    names = []
    arrays = []

    for name, shape in init_vars:
        logger.info("Loading TF weight {} with shape {}".format(name, shape))
        array = tf.train.load_variable(tf_path, name)
        names.append(name)
        arrays.append(array.squeeze())

    for name, array in zip(names, arrays):
        name = name[6:]  # skip "model/"
        name = name.split("/")

        # adam_v and adam_m are variables used in AdamWeightDecayOptimizer to calculated m and v
        # which are not required for using pretrained model
        if any(
            n in ["adam_v", "adam_m", "AdamWeightDecayOptimizer",
                  "AdamWeightDecayOptimizer_1", "global_step"]
            for n in name
        ) or name[-1] in ["_step"]:
            logger.info("Skipping {}".format("/".join(name)))
            continue

        pointer = model
        if name[-1] not in ["wtet"]:
            pointer = getattr(pointer, "transformer")

        for m_name in name:
            if re.fullmatch(r"[A-Za-z]+\d+", m_name):
                scope_names = re.split(r"(\d+)", m_name)
            else:
                scope_names = [m_name]

            if scope_names[0] == "w" or scope_names[0] == "g":
                pointer = getattr(pointer, "weight")
            elif scope_names[0] == "b":
                pointer = getattr(pointer, "bias")
            elif scope_names[0] == "wpe" or scope_names[0] == "wte":
                pointer = getattr(pointer, scope_names[0])
                pointer = getattr(pointer, "weight")
            elif scope_names[0] in ["q_proj", "k_proj", "v_proj"]:
                pointer = getattr(pointer, "c_attn")
                pointer = getattr(pointer, "weight")
            elif len(name) == 3 and name[1] == "attn" and scope_names[0] == "c_proj":
                pointer = getattr(pointer, scope_names[0])
                pointer = getattr(pointer, "weight")
            elif scope_names[0] == "wtet":
                pointer = getattr(pointer, "lm_head")
                pointer = getattr(pointer, "weight")
            elif scope_names[0] == "sos":
                pointer = getattr(pointer, "wte")
                pointer = getattr(pointer, "weight")
            else:
                pointer = getattr(pointer, scope_names[0])
            if len(scope_names) >= 2:
                num = int(scope_names[1])
                pointer = pointer[num]

        if len(name) > 1 and name[1] == "attn" or name[-1] == "wtet" or name[-1] == "sos" or name[-1] == "wte":
            pass  # array is used to initialize only part of the pointer so sizes won't match
        else:
            try:
                assert pointer.shape == array.shape
            except AssertionError as e:
                e.args += (pointer.shape, array.shape)
                raise

        logger.info("Initialize PyTorch weight {}".format(name))

        if name[-1] == "q_proj":
            pointer.data[:, : config.n_embd] = ms.Tensor(
                array.reshape(config.n_embd, config.n_embd)).T
        elif name[-1] == "k_proj":
            pointer.data[:, config.n_embd: 2 * config.n_embd] = ms.Tensor(
                array.reshape(config.n_embd, config.n_embd)
            ).T
        elif name[-1] == "v_proj":
            pointer.data[:, 2 * config.n_embd:] = ms.Tensor(
                array.reshape(config.n_embd, config.n_embd)).T
        elif len(name) == 3 and name[1] == "attn" and name[2] == "c_proj":
            pointer.data = ms.Tensor(
                array.reshape(config.n_embd, config.n_embd))
        elif name[-1] == "wtet":
            pointer.data = ms.Tensor(array)
        elif name[-1] == "wte":
            pointer.data[: config.vocab_size - 1, :] = ms.Tensor(array)
        elif name[-1] == "sos":
            pointer.data[-1] = ms.Tensor(array)
        else:
            pointer.data = ms.Tensor(array)

    return model