120 lines
5.1 KiB
Python
120 lines
5.1 KiB
Python
# coding=utf-8
|
|
# Copyright 2023 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.
|
|
""" ViViT model configuration"""
|
|
|
|
from ...configuration_utils import PretrainedConfig
|
|
from ...utils import logging
|
|
|
|
|
|
logger = logging.get_logger(__name__)
|
|
|
|
|
|
from ..deprecated._archive_maps import VIVIT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402
|
|
|
|
|
|
class VivitConfig(PretrainedConfig):
|
|
r"""
|
|
This is the configuration class to store the configuration of a [`VivitModel`]. It is used to instantiate a ViViT
|
|
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 ViViT
|
|
[google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) 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 size (resolution) of each image.
|
|
num_frames (`int`, *optional*, defaults to 32):
|
|
The number of frames in each video.
|
|
tubelet_size (`List[int]`, *optional*, defaults to `[2, 16, 16]`):
|
|
The size (resolution) of each tubelet.
|
|
num_channels (`int`, *optional*, defaults to 3):
|
|
The number of input channels.
|
|
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_fast"`):
|
|
The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
|
|
`"relu"`, `"selu"`, `"gelu_fast"` 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.
|
|
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 to add a bias to the queries, keys and values.
|
|
|
|
Example:
|
|
|
|
```python
|
|
>>> from transformers import VivitConfig, VivitModel
|
|
|
|
>>> # Initializing a ViViT google/vivit-b-16x2-kinetics400 style configuration
|
|
>>> configuration = VivitConfig()
|
|
|
|
>>> # Initializing a model (with random weights) from the google/vivit-b-16x2-kinetics400 style configuration
|
|
>>> model = VivitModel(configuration)
|
|
|
|
>>> # Accessing the model configuration
|
|
>>> configuration = model.config
|
|
```"""
|
|
|
|
model_type = "vivit"
|
|
|
|
def __init__(
|
|
self,
|
|
image_size=224,
|
|
num_frames=32,
|
|
tubelet_size=[2, 16, 16],
|
|
num_channels=3,
|
|
hidden_size=768,
|
|
num_hidden_layers=12,
|
|
num_attention_heads=12,
|
|
intermediate_size=3072,
|
|
hidden_act="gelu_fast",
|
|
hidden_dropout_prob=0.0,
|
|
attention_probs_dropout_prob=0.0,
|
|
initializer_range=0.02,
|
|
layer_norm_eps=1e-06,
|
|
qkv_bias=True,
|
|
**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.num_frames = num_frames
|
|
self.tubelet_size = tubelet_size
|
|
self.num_channels = num_channels
|
|
self.qkv_bias = qkv_bias
|
|
|
|
super().__init__(**kwargs)
|