File size: 5,957 Bytes
ed01e82 |
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 Facebook 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 SiT model configuration"""
from transformers import PretrainedConfig
from transformers import logging
logger = logging.get_logger(__name__)
VIT_SiT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
"erow/vit-SiT-base": "https://huggingface.co/erow/SiT/resolve/main/config.json",
}
class ViTSiTConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`ViTSiTModel`]. It is used to instantiate an ViT
SiT 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
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 0.0):
The dropout probabilitiy 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.
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.
decoder_num_attention_heads (`int`, *optional*, defaults to 16):
Number of attention heads for each attention layer in the decoder.
decoder_hidden_size (`int`, *optional*, defaults to 512):
Dimensionality of the decoder.
decoder_num_hidden_layers (`int`, *optional*, defaults to 8):
Number of hidden layers in the decoder.
decoder_intermediate_size (`int`, *optional*, defaults to 2048):
Dimensionality of the "intermediate" (i.e., feed-forward) layer in the decoder.
mask_ratio (`float`, *optional*, defaults to 0.75):
The ratio of the number of masked tokens in the input sequence.
norm_pix_loss (`bool`, *optional*, defaults to `False`):
Whether or not to train with normalized pixels (see Table 3 in the paper). Using normalized pixels improved
representation quality in the experiments of the authors.
Example:
```python
>>> from transformers import ViTSiTConfig, ViTSiTModel
>>> # Initializing a ViT SiT vit-SiT-base style configuration
>>> configuration = ViTSiTConfig()
>>> # Initializing a model (with random weights) from the vit-SiT-base style configuration
>>> model = ViTSiTModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "vit_sit"
def __init__(
self,
hidden_size=768,
out_dim = 256,
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,
image_size=224,
patch_size=16,
num_channels=3,
qkv_bias=True,
mask_ratio=0.75,
**kwargs,
):
super().__init__(**kwargs)
self.hidden_size = hidden_size
self.out_dim = out_dim
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
self.mask_ratio = mask_ratio
|