master
/ transformers / models / deit / configuration_deit.py

configuration_deit.py @3c11360 — raw · history · blame 

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 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
# coding=utf-8
# Copyright 2021 Facebook AI Research (FAIR) 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.
""" DeiT model configuration """

from ...configuration_utils import PretrainedConfig
from ...utils import logging


logger = logging.get_logger(__name__)

DEIT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "facebook/deit-base-distilled-patch16-224": "https://huggingface.co/facebook/deit-base-patch16-224/resolve/main/config.json",
    # See all DeiT models at https://huggingface.co/models?filter=deit
}


class DeiTConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`DeiTModel`]. It is used to
    instantiate an DeiT 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 DeiT
    [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224)
    architecture.

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


    Args:
        hidden_size (`int`, *optional*, defaults to 768):
            Dimensionality of the encoder layers and the pooler layer.
        num_hidden_layers (`int`, *optional*, defaults to 12):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        intermediate_size (`int`, *optional*, defaults to 3072):
            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string,
            `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported.
        hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention probabilities.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
            The epsilon used by the layer normalization layers.
        image_size (`int`, *optional*, defaults to `224`):
            The size (resolution) of each image.
        patch_size (`int`, *optional*, defaults to `16`):
            The size (resolution) of each patch.
        num_channels (`int`, *optional*, defaults to `3`):
            The number of input channels.
        qkv_bias (`bool`, *optional*, defaults to `True`):
            Whether to add a bias to the queries, keys and values.


    Example:

    ```python
    >>> from transformers import DeiTModel, DeiTConfig

    >>> # Initializing a DeiT deit-base-distilled-patch16-224 style configuration
    >>> configuration = DeiTConfig()

    >>> # Initializing a model from the deit-base-distilled-patch16-224 style configuration
    >>> model = DeiTModel(configuration)

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

    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,
        qkv_bias=True,
        **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
        self.qkv_bias = qkv_bias