# coding=utf-8
# Copyright 2021 Google AI and The HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" ViT model configuration """
from ...configuration_utils import PretrainedConfig
from ...utils import logging
logger = logging.get_logger(__name__)
VIT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
"nielsr/vit-base-patch16-224": "https://huggingface.co/vit-base-patch16-224/resolve/main/config.json",
# See all ViT models at https://huggingface.co/models?filter=vit
}
[docs]class ViTConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a :class:`~transformers.ViTModel`. It is used to
instantiate an ViT 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 ViT `google/vit-base-patch16-224
<https://huggingface.co/google/vit-base-patch16-224>`__ architecture.
Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
Args:
hidden_size (:obj:`int`, `optional`, defaults to 768):
Dimensionality of the encoder layers and the pooler layer.
num_hidden_layers (:obj:`int`, `optional`, defaults to 12):
Number of hidden layers in the Transformer encoder.
num_attention_heads (:obj:`int`, `optional`, defaults to 12):
Number of attention heads for each attention layer in the Transformer encoder.
intermediate_size (:obj:`int`, `optional`, defaults to 3072):
Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
hidden_act (:obj:`str` or :obj:`function`, `optional`, defaults to :obj:`"gelu"`):
The non-linear activation function (function or string) in the encoder and pooler. If string,
:obj:`"gelu"`, :obj:`"relu"`, :obj:`"selu"` and :obj:`"gelu_new"` are supported.
hidden_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
attention_probs_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
The dropout ratio for the attention probabilities.
initializer_range (:obj:`float`, `optional`, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
layer_norm_eps (:obj:`float`, `optional`, defaults to 1e-12):
The epsilon used by the layer normalization layers.
gradient_checkpointing (:obj:`bool`, `optional`, defaults to :obj:`False`):
If True, use gradient checkpointing to save memory at the expense of slower backward pass.
image_size (:obj:`int`, `optional`, defaults to :obj:`224`):
The size (resolution) of each image.
patch_size (:obj:`int`, `optional`, defaults to :obj:`16`):
The size (resolution) of each patch.
num_channels (:obj:`int`, `optional`, defaults to :obj:`3`):
The number of input channels.
Example::
>>> from transformers import ViTModel, ViTConfig
>>> # Initializing a ViT vit-base-patch16-224 style configuration
>>> configuration = ViTConfig()
>>> # Initializing a model from the vit-base-patch16-224 style configuration
>>> model = ViTModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
"""
model_type = "vit"
def __init__(
self,
hidden_size=768,
num_hidden_layers=12,
num_attention_heads=12,
intermediate_size=3072,
hidden_act="gelu",
hidden_dropout_prob=0.0,
attention_probs_dropout_prob=0.0,
initializer_range=0.02,
layer_norm_eps=1e-12,
is_encoder_decoder=False,
image_size=224,
patch_size=16,
num_channels=3,
**kwargs
):
super().__init__(**kwargs)
self.hidden_size = hidden_size
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
self.intermediate_size = intermediate_size
self.hidden_act = hidden_act
self.hidden_dropout_prob = hidden_dropout_prob
self.attention_probs_dropout_prob = attention_probs_dropout_prob
self.initializer_range = initializer_range
self.layer_norm_eps = layer_norm_eps
self.image_size = image_size
self.patch_size = patch_size
self.num_channels = num_channels