ImageGPT
Overview
The ImageGPT model was proposed in Generative Pretraining from Pixels by Mark Chen, Alec Radford, Rewon Child, Jeffrey Wu, Heewoo Jun, David Luan, Ilya Sutskever. ImageGPT (iGPT) is a GPT-2-like model trained to predict the next pixel value, allowing for both unconditional and conditional image generation.
The abstract from the paper is the following:
Inspired by progress in unsupervised representation learning for natural language, we examine whether similar models can learn useful representations for images. We train a sequence Transformer to auto-regressively predict pixels, without incorporating knowledge of the 2D input structure. Despite training on low-resolution ImageNet without labels, we find that a GPT-2 scale model learns strong image representations as measured by linear probing, fine-tuning, and low-data classification. On CIFAR-10, we achieve 96.3% accuracy with a linear probe, outperforming a supervised Wide ResNet, and 99.0% accuracy with full fine-tuning, matching the top supervised pre-trained models. We are also competitive with self-supervised benchmarks on ImageNet when substituting pixels for a VQVAE encoding, achieving 69.0% top-1 accuracy on a linear probe of our features.
The figure below summarizes the approach (taken from the original paper):
Tips:
- ImageGPT is almost exactly the same as GPT-2, with the exception that a different activation function is used (namely βquick geluβ), and the layer normalization layers donβt mean center the inputs. ImageGPT also doesnβt have tied input- and output embeddings.
- As the time- and memory requirements of the attention mechanism of Transformers scales quadratically in the sequence length, the authors pre-trained ImageGPT on smaller input resolutions, such as 32x32 and 64x64. However, feeding a sequence of 32x32x3=3072 tokens from 0..255 into a Transformer is still prohibitively large. Therefore, the authors applied k-means clustering to the (R,G,B) pixel values with k=512. This way, we only have a 32*32 = 1024-long sequence, but now of integers in the range 0..511. So we are shrinking the sequence length at the cost of a bigger embedding matrix. In other words, the vocabulary size of ImageGPT is 512, + 1 for a special βstart of sentenceβ (SOS) token, used at the beginning of every sequence. One can use ImageGPTFeatureExtractor to prepare images for the model.
- Despite being pre-trained entirely unsupervised (i.e. without the use of any labels), ImageGPT produces fairly performant image features useful for downstream tasks, such as image classification. The authors showed that the features in the middle of the network are the most performant, and can be used as-is to train a linear model (such as a sklearn logistic regression model for example). This is also referred to as βlinear probingβ. Features can be easily obtained by first forwarding the image through the model, then specifying output_hidden_states=True, and then average-pool the hidden states at whatever layer you like.
- Alternatively, one can further fine-tune the entire model on a downstream dataset, similar to BERT. For this, you can use ImageGPTForImageClassification.
- ImageGPT comes in different sizes: thereβs ImageGPT-small, ImageGPT-medium and ImageGPT-large. The authors did also train an XL variant, which they didnβt release. The differences in size are summarized in the following table:
| Model variant | Number of layers | Hidden size | Number of heads | # params | | iGPT-small | 24 | 512 | 8 | 76 million | | iGPT-medium | 36 | 1024 | 8 | 455 million | | iGPT-large | 48 | 1536 | 16 | 1.4 million | | iGPT-XL | 60 | 3072 | not specified | 6.8 billion |
This model was contributed by nielsr, based on this issue. The original code can be found here.
ImageGPTConfig
( vocab_size = 513 n_positions = 1024 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-05 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 )
Parameters
-
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 theinputs_ids
passed when calling ImageGPTModel orTFImageGPTModel
. -
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 toTrue
) — Scale attention weights by dividing by sqrt(hidden_size).. -
use_cache (
bool
, optional, defaults toTrue
) — 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 toFalse
) — Whether to additionally scale attention weights by1 / layer_idx + 1
. -
reorder_and_upcast_attn (
bool
, optional, defaults toFalse
) — Whether to scale keys (K) prior to computing attention (dot-product) and upcast attention dot-product/softmax to float() when training with mixed precision.
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 small architecture.
Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
Example:
>>> from transformers import ImageGPTModel, ImageGPTConfig
>>> # Initializing a ImageGPT configuration
>>> configuration = ImageGPTConfig()
>>> # Initializing a model from the configuration
>>> model = ImageGPTModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
ImageGPTFeatureExtractor
( clusters do_resize = True size = 32 resample = 2 do_normalize = True **kwargs )
Parameters
-
clusters (
np.ndarray
) — The color clusters to use, as anp.ndarray
of shape(n_clusters, 3)
. -
do_resize (
bool
, optional, defaults toTrue
) — Whether to resize the input to a certainsize
. -
size (
int
orTuple(int)
, optional, defaults to 32) — Resize the input to the given size. If a tuple is provided, it should be (width, height). If only an integer is provided, then the input will be resized to (size, size). Only has an effect ifdo_resize
is set toTrue
. -
resample (
int
, optional, defaults toPIL.Image.BILINEAR
) — An optional resampling filter. This can be one ofPIL.Image.NEAREST
,PIL.Image.BOX
,PIL.Image.BILINEAR
,PIL.Image.HAMMING
,PIL.Image.BICUBIC
orPIL.Image.LANCZOS
. Only has an effect ifdo_resize
is set toTrue
. -
do_normalize (
bool
, optional, defaults toTrue
) — Whether or not to normalize the input to the range between -1 and +1.
Constructs an ImageGPT feature extractor. This feature extractor 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 βpixel valuesβ (color clusters).
This feature extractor inherits from FeatureExtractionMixin
which contains most of the main
methods. Users should refer to this superclass for more information regarding those methods.
( images: typing.Union[PIL.Image.Image, numpy.ndarray, ForwardRef('torch.Tensor'), typing.List[PIL.Image.Image], typing.List[numpy.ndarray], typing.List[ForwardRef('torch.Tensor')]] return_tensors: typing.Union[str, transformers.file_utils.TensorType, NoneType] = None **kwargs ) β BatchFeature
Parameters
-
images (
PIL.Image.Image
,np.ndarray
,torch.Tensor
,List[PIL.Image.Image]
,List[np.ndarray]
,List[torch.Tensor]
) — The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a number of channels, H and W are image height and width. -
return_tensors (
str
or TensorType, optional, defaults to'np'
) — If set, will return tensors of a particular framework. Acceptable values are:'tf'
: Return TensorFlowtf.constant
objects.'pt'
: Return PyTorchtorch.Tensor
objects.'np'
: Return NumPynp.ndarray
objects.'jax'
: Return JAXjnp.ndarray
objects.
Returns
A BatchFeature with the following fields:
- pixel_values β Pixel values to be fed to a model, of shape (batch_size, num_channels, height, width).
Main method to prepare for the model one or several image(s).
NumPy arrays and PyTorch tensors are converted to PIL images when resizing, so the most efficient is to pass PIL images.
ImageGPTModel
( config )
Parameters
- config (ImageGPTConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The bare ImageGPT Model transformer outputting raw hidden-states without any specific head on top.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
(
pixel_values = 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
)
β
BaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)
Parameters
-
pixel_values (
torch.LongTensor
of shape(batch_size, pixel_values_length)
) —pixel_values_length
=sequence_length
ifpast_key_values
isNone
elsepast_key_values[0][0].shape[-2]
(sequence_length
of input past key value states). Indices of input sequence tokens in the vocabulary.If
past_key_values
is used, onlypixel_values
that do not have their past calculated should be passed aspixel_values
.Indices can be obtained using ImageGPTFeatureExtractor. See transformers.ImageGPTFeatureExtractor.call() for details.
-
past_key_values (
Tuple[Tuple[torch.Tensor]]
of lengthconfig.n_layers
) — Contains precomputed hidden-states (key and values in the attention blocks) as computed by the model (seepast_key_values
output below). Can be used to speed up sequential decoding. Thepixel_values
which have their past given to this model should not be passed aspixel_values
as they have already been computed. -
attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
-
token_type_ids (
torch.LongTensor
of shape(batch_size, pixel_values_length)
, optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in[0, 1]
:- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
-
position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. -
head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) — Optionally, instead of passingpixel_values
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertpixel_values
indices into associated vectors than the model’s internal embedding lookup matrix.If
past_key_values
is used, optionally only the lastinputs_embeds
have to be input (seepast_key_values
). -
use_cache (
bool
, optional) — If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_key_values
). -
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. -
labels (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Labels for language modeling. Note that the labels are shifted inside the model, i.e. you can setlabels = pixel_values
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
BaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)
A BaseModelOutputWithPastAndCrossAttentions or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising
various elements depending on the configuration (ImageGPTConfig) and inputs.
-
last_hidden_state (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
) β Sequence of hidden-states at the output of the last layer of the model.If
past_key_values
is used only the last hidden-state of the sequences of shape(batch_size, 1, hidden_size)
is output. -
past_key_values (
tuple(tuple(torch.FloatTensor))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(torch.FloatTensor)
of lengthconfig.n_layers
, with each tuple having 2 tensors of shape(batch_size, num_heads, sequence_length, embed_size_per_head)
) and optionally ifconfig.is_encoder_decoder=True
2 additional tensors of shape(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)
.Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if
config.is_encoder_decoder=True
in the cross-attention blocks) that can be used (seepast_key_values
input) to speed up sequential decoding. -
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
-
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
-
cross_attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
andconfig.add_cross_attention=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoderβs cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
The ImageGPTModel forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post
processing steps while the latter silently ignores them.
Examples:
>>> from transformers import ImageGPTFeatureExtractor, ImageGPTModel
>>> from PIL import Image
>>> import requests
>>> url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> feature_extractor = ImageGPTFeatureExtractor.from_pretrained('openai/imagegpt-small')
>>> model = ImageGPTModel.from_pretrained('openai/imagegpt-small')
>>> inputs = feature_extractor(images=image, return_tensors="pt")
>>> outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_state
ImageGPTForCausalImageModeling
( config )
Parameters
- config (ImageGPTConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The ImageGPT Model transformer with a language modeling head on top (linear layer with weights tied to the input embeddings).
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
(
pixel_values = 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
)
β
CausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)
Parameters
-
pixel_values (
torch.LongTensor
of shape(batch_size, pixel_values_length)
) —pixel_values_length
=sequence_length
ifpast_key_values
isNone
elsepast_key_values[0][0].shape[-2]
(sequence_length
of input past key value states). Indices of input sequence tokens in the vocabulary.If
past_key_values
is used, onlypixel_values
that do not have their past calculated should be passed aspixel_values
.Indices can be obtained using ImageGPTFeatureExtractor. See transformers.ImageGPTFeatureExtractor.call() for details.
-
past_key_values (
Tuple[Tuple[torch.Tensor]]
of lengthconfig.n_layers
) — Contains precomputed hidden-states (key and values in the attention blocks) as computed by the model (seepast_key_values
output below). Can be used to speed up sequential decoding. Thepixel_values
which have their past given to this model should not be passed aspixel_values
as they have already been computed. -
attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
-
token_type_ids (
torch.LongTensor
of shape(batch_size, pixel_values_length)
, optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in[0, 1]
:- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
-
position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. -
head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) — Optionally, instead of passingpixel_values
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertpixel_values
indices into associated vectors than the model’s internal embedding lookup matrix.If
past_key_values
is used, optionally only the lastinputs_embeds
have to be input (seepast_key_values
). -
use_cache (
bool
, optional) — If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_key_values
). -
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. -
labels (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Labels for language modeling. Note that the labels are shifted inside the model, i.e. you can setlabels = pixel_values
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
CausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)
A CausalLMOutputWithCrossAttentions or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising
various elements depending on the configuration (ImageGPTConfig) and inputs.
-
loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) β Language modeling loss (for next-token prediction). -
logits (
torch.FloatTensor
of shape(batch_size, sequence_length, config.vocab_size)
) β Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
-
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
-
cross_attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Cross attentions weights after the attention softmax, used to compute the weighted average in the cross-attention heads.
-
past_key_values (
tuple(tuple(torch.FloatTensor))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftorch.FloatTensor
tuples of lengthconfig.n_layers
, with each tuple containing the cached key, value states of the self-attention and the cross-attention layers if model is used in encoder-decoder setting. Only relevant ifconfig.is_decoder = True
.Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see
past_key_values
input) to speed up sequential decoding.
The ImageGPTForCausalImageModeling forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post
processing steps while the latter silently ignores them.
Examples:
>>> from transformers import ImageGPTFeatureExtractor, ImageGPTForCausalImageModeling
>>> import torch
>>> import matplotlib.pyplot as plt
>>> import numpy as np
>>> feature_extractor = ImageGPTFeatureExtractor.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)
>>> # unconditional generation of 8 images
>>> batch_size = 8
>>> context = torch.full((batch_size, 1), model.config.vocab_size - 1) #initialize with SOS token
>>> context = torch.tensor(context).to(device)
>>> output = model.generate(pixel_values=context, max_length=model.config.n_positions + 1, temperature=1.0, do_sample=True, top_k=40)
>>> clusters = feature_extractor.clusters
>>> n_px = feature_extractor.size
>>> samples = output[:,1:].cpu().detach().numpy()
>>> samples_img = [np.reshape(np.rint(127.5 * (clusters[s] + 1.0)), [n_px, n_px, 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):
... ax.axis('off')
... ax.imshow(img)
ImageGPTForImageClassification
( config )
Parameters
- config (ImageGPTConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The ImageGPT Model transformer with an image classification head on top (linear layer). ImageGPTForImageClassification average-pools the hidden states in order to do the classification.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
(
pixel_values = 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
)
β
SequenceClassifierOutputWithPast
or tuple(torch.FloatTensor)
Parameters
-
pixel_values (
torch.LongTensor
of shape(batch_size, pixel_values_length)
) —pixel_values_length
=sequence_length
ifpast_key_values
isNone
elsepast_key_values[0][0].shape[-2]
(sequence_length
of input past key value states). Indices of input sequence tokens in the vocabulary.If
past_key_values
is used, onlypixel_values
that do not have their past calculated should be passed aspixel_values
.Indices can be obtained using ImageGPTFeatureExtractor. See transformers.ImageGPTFeatureExtractor.call() for details.
-
past_key_values (
Tuple[Tuple[torch.Tensor]]
of lengthconfig.n_layers
) — Contains precomputed hidden-states (key and values in the attention blocks) as computed by the model (seepast_key_values
output below). Can be used to speed up sequential decoding. Thepixel_values
which have their past given to this model should not be passed aspixel_values
as they have already been computed. -
attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
-
token_type_ids (
torch.LongTensor
of shape(batch_size, pixel_values_length)
, optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in[0, 1]
:- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
-
position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. -
head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) — Optionally, instead of passingpixel_values
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertpixel_values
indices into associated vectors than the model’s internal embedding lookup matrix.If
past_key_values
is used, optionally only the lastinputs_embeds
have to be input (seepast_key_values
). -
use_cache (
bool
, optional) — If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_key_values
). -
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. -
labels (
torch.LongTensor
of shape(batch_size,)
, optional) — Labels for computing the sequence classification/regression loss. Indices should be in[0, ..., config.num_labels - 1]
. Ifconfig.num_labels == 1
a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1
a classification loss is computed (Cross-Entropy).
Returns
SequenceClassifierOutputWithPast
or tuple(torch.FloatTensor)
A SequenceClassifierOutputWithPast
or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising
various elements depending on the configuration (ImageGPTConfig) and inputs.
-
loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) β Classification (or regression if config.num_labels==1) loss. -
logits (
torch.FloatTensor
of shape(batch_size, config.num_labels)
) β Classification (or regression if config.num_labels==1) scores (before SoftMax). -
past_key_values (
tuple(tuple(torch.FloatTensor))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(torch.FloatTensor)
of lengthconfig.n_layers
, with each tuple having 2 tensors of shape(batch_size, num_heads, sequence_length, embed_size_per_head)
)Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see
past_key_values
input) to speed up sequential decoding. -
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
-
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The ImageGPTForImageClassification forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post
processing steps while the latter silently ignores them.
Examples:
>>> from transformers import ImageGPTFeatureExtractor, ImageGPTForImageClassification
>>> from PIL import Image
>>> import requests
>>> url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> feature_extractor = ImageGPTFeatureExtractor.from_pretrained('openai/imagegpt-small')
>>> model = ImageGPTForImageClassification.from_pretrained('openai/imagegpt-small')
>>> inputs = feature_extractor(images=image, return_tensors="pt")
>>> outputs = model(**inputs)
>>> logits = outputs.logits