File size: 6,919 Bytes
d1ceb73
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
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
# coding=utf-8
# Copyright 2023 Authors: Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan,
# Kaitao Song, Ding Liang, Tong Lu, Ping Luo, Ling Shao 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.
"""Pvt model configuration"""

from collections import OrderedDict
from typing import Callable, List, Mapping

from packaging import version

from ...configuration_utils import PretrainedConfig
from ...onnx import OnnxConfig
from ...utils import logging


logger = logging.get_logger(__name__)


class PvtConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`PvtModel`]. It is used to instantiate an Pvt
    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 Pvt
    [Xrenya/pvt-tiny-224](https://huggingface.co/Xrenya/pvt-tiny-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:
        image_size (`int`, *optional*, defaults to 224):
            The input image size
        num_channels (`int`, *optional*, defaults to 3):
            The number of input channels.
        num_encoder_blocks (`int`, *optional*, defaults to 4):
            The number of encoder blocks (i.e. stages in the Mix Transformer encoder).
        depths (`List[int]`, *optional*, defaults to `[2, 2, 2, 2]`):
            The number of layers in each encoder block.
        sequence_reduction_ratios (`List[int]`, *optional*, defaults to `[8, 4, 2, 1]`):
            Sequence reduction ratios in each encoder block.
        hidden_sizes (`List[int]`, *optional*, defaults to `[64, 128, 320, 512]`):
            Dimension of each of the encoder blocks.
        patch_sizes (`List[int]`, *optional*, defaults to `[4, 2, 2, 2]`):
            Patch size before each encoder block.
        strides (`List[int]`, *optional*, defaults to `[4, 2, 2, 2]`):
            Stride before each encoder block.
        num_attention_heads (`List[int]`, *optional*, defaults to `[1, 2, 5, 8]`):
            Number of attention heads for each attention layer in each block of the Transformer encoder.
        mlp_ratios (`List[int]`, *optional*, defaults to `[8, 8, 4, 4]`):
            Ratio of the size of the hidden layer compared to the size of the input layer of the Mix FFNs in the
            encoder blocks.
        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 0.0):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0):
            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.
        drop_path_rate (`float`, *optional*, defaults to 0.0):
            The dropout probability for stochastic depth, used in the blocks of the Transformer encoder.
        layer_norm_eps (`float`, *optional*, defaults to 1e-06):
            The epsilon used by the layer normalization layers.
        qkv_bias (`bool`, *optional*, defaults to `True`):
            Whether or not a learnable bias should be added to the queries, keys and values.
        num_labels ('int', *optional*, defaults to 1000):
            The number of classes.
    Example:

    ```python
    >>> from transformers import PvtModel, PvtConfig

    >>> # Initializing a PVT Xrenya/pvt-tiny-224 style configuration
    >>> configuration = PvtConfig()

    >>> # Initializing a model from the Xrenya/pvt-tiny-224 style configuration
    >>> model = PvtModel(configuration)

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

    model_type = "pvt"

    def __init__(
        self,
        image_size: int = 224,
        num_channels: int = 3,
        num_encoder_blocks: int = 4,
        depths: List[int] = [2, 2, 2, 2],
        sequence_reduction_ratios: List[int] = [8, 4, 2, 1],
        hidden_sizes: List[int] = [64, 128, 320, 512],
        patch_sizes: List[int] = [4, 2, 2, 2],
        strides: List[int] = [4, 2, 2, 2],
        num_attention_heads: List[int] = [1, 2, 5, 8],
        mlp_ratios: List[int] = [8, 8, 4, 4],
        hidden_act: Mapping[str, Callable] = "gelu",
        hidden_dropout_prob: float = 0.0,
        attention_probs_dropout_prob: float = 0.0,
        initializer_range: float = 0.02,
        drop_path_rate: float = 0.0,
        layer_norm_eps: float = 1e-6,
        qkv_bias: bool = True,
        num_labels: int = 1000,
        **kwargs,
    ):
        super().__init__(**kwargs)

        self.image_size = image_size
        self.num_channels = num_channels
        self.num_encoder_blocks = num_encoder_blocks
        self.depths = depths
        self.sequence_reduction_ratios = sequence_reduction_ratios
        self.hidden_sizes = hidden_sizes
        self.patch_sizes = patch_sizes
        self.strides = strides
        self.mlp_ratios = mlp_ratios
        self.num_attention_heads = num_attention_heads
        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.drop_path_rate = drop_path_rate
        self.layer_norm_eps = layer_norm_eps
        self.num_labels = num_labels
        self.qkv_bias = qkv_bias


class PvtOnnxConfig(OnnxConfig):
    torch_onnx_minimum_version = version.parse("1.11")

    @property
    def inputs(self) -> Mapping[str, Mapping[int, str]]:
        return OrderedDict(
            [
                ("pixel_values", {0: "batch", 1: "num_channels", 2: "height", 3: "width"}),
            ]
        )

    @property
    def atol_for_validation(self) -> float:
        return 1e-4

    @property
    def default_onnx_opset(self) -> int:
        return 12