File size: 5,971 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 |
# coding=utf-8
# Copyright 2022 KAIST 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.
"""GLPN model configuration"""
from ...configuration_utils import PretrainedConfig
from ...utils import logging
logger = logging.get_logger(__name__)
class GLPNConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`GLPNModel`]. It is used to instantiate an GLPN
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 GLPN
[vinvino02/glpn-kitti](https://huggingface.co/vinvino02/glpn-kitti) architecture.
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PretrainedConfig`] for more information.
Args:
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.
sr_ratios (`List[int]`, *optional*, defaults to `[8, 4, 2, 1]`):
Sequence reduction ratios in each encoder block.
hidden_sizes (`List[int]`, *optional*, defaults to `[32, 64, 160, 256]`):
Dimension of each of the encoder blocks.
patch_sizes (`List[int]`, *optional*, defaults to `[7, 3, 3, 3]`):
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 `[4, 4, 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 0.1):
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.
decoder_hidden_size (`int`, *optional*, defaults to 64):
The dimension of the decoder.
max_depth (`int`, *optional*, defaults to 10):
The maximum depth of the decoder.
head_in_index (`int`, *optional*, defaults to -1):
The index of the features to use in the head.
Example:
```python
>>> from transformers import GLPNModel, GLPNConfig
>>> # Initializing a GLPN vinvino02/glpn-kitti style configuration
>>> configuration = GLPNConfig()
>>> # Initializing a model from the vinvino02/glpn-kitti style configuration
>>> model = GLPNModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "glpn"
def __init__(
self,
num_channels=3,
num_encoder_blocks=4,
depths=[2, 2, 2, 2],
sr_ratios=[8, 4, 2, 1],
hidden_sizes=[32, 64, 160, 256],
patch_sizes=[7, 3, 3, 3],
strides=[4, 2, 2, 2],
num_attention_heads=[1, 2, 5, 8],
mlp_ratios=[4, 4, 4, 4],
hidden_act="gelu",
hidden_dropout_prob=0.0,
attention_probs_dropout_prob=0.0,
initializer_range=0.02,
drop_path_rate=0.1,
layer_norm_eps=1e-6,
decoder_hidden_size=64,
max_depth=10,
head_in_index=-1,
**kwargs,
):
super().__init__(**kwargs)
self.num_channels = num_channels
self.num_encoder_blocks = num_encoder_blocks
self.depths = depths
self.sr_ratios = sr_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.decoder_hidden_size = decoder_hidden_size
self.max_depth = max_depth
self.head_in_index = head_in_index
|