Ma Zerun
GitHub
parent
1d6fbe0efe
commit
7c5ddb1e5b
13
README.md
13
README.md
|
|
@ -59,6 +59,12 @@ The master branch works with **PyTorch 1.5+**.
|
|||
|
||||
## What's new
|
||||
|
||||
v0.23.0 was released in 1/5/2022.
|
||||
Highlights of the new version:
|
||||
- Support **DenseNet**, **VAN** and **PoolFormer**, and provide pre-trained models.
|
||||
- Support training on IPU.
|
||||
- New style API docs, welcome [view it](https://mmclassification.readthedocs.io/en/master/api/models.html).
|
||||
|
||||
v0.22.0 was released in 30/3/2022.
|
||||
|
||||
Highlights of the new version:
|
||||
|
|
@ -66,13 +72,6 @@ Highlights of the new version:
|
|||
- A new `CustomDataset` class to help you **build dataset of yourself**!
|
||||
- Support new backbones - **ConvMixer**, **RepMLP** and new dataset - **CUB dataset**.
|
||||
|
||||
v0.21.0 was released in 4/3/2022.
|
||||
|
||||
Highlights of the new version:
|
||||
- Support **ResNetV1c** and **Wide-ResNet**, and provide pre-trained models.
|
||||
- Support **dynamic input shape** for ViT-based algorithms. Now our ViT, DeiT, Swin-Transformer and T2T-ViT support forwarding with any input shape.
|
||||
- Reproduce training results of DeiT. And our DeiT-T and DeiT-S have **higher accuracy** comparing with the official weights.
|
||||
|
||||
Please refer to [changelog.md](docs/en/changelog.md) for more details and other release history.
|
||||
|
||||
## Installation
|
||||
|
|
|
|||
|
|
@ -57,6 +57,13 @@ MMClassification 是一款基于 PyTorch 的开源图像分类工具箱，是 [O
|
|||
|
||||
## 更新日志
|
||||
|
||||
2022/5/1 发布了 v0.23.0 版本
|
||||
|
||||
新版本亮点：
|
||||
- 支持了 **DenseNet**，**VAN** 和 **PoolFormer** 三个网络，并提供了预训练模型。
|
||||
- 支持在 IPU 上进行训练。
|
||||
- 更新了 API 文档的样式，更方便查阅，[欢迎查阅](https://mmclassification.readthedocs.io/en/master/api/models.html)。
|
||||
|
||||
2022/3/30 发布了 v0.22.0 版本
|
||||
|
||||
新版本亮点：
|
||||
|
|
@ -64,13 +71,6 @@ MMClassification 是一款基于 PyTorch 的开源图像分类工具箱，是 [O
|
|||
- 我们提供了一个新的 `CustomDataset` 类，这个类将帮助你轻松使用**自己的数据集**！
|
||||
- 支持了新的主干网络 **ConvMixer**、**RepMLP** 和一个新的数据集 **CUB dataset**。
|
||||
|
||||
2022/3/4 发布了 v0.21.0 版本
|
||||
|
||||
新版本亮点：
|
||||
- 支持了 **ResNetV1c** 和 **Wide-ResNet** 两个 ResNet 变种，并提供了预训练模型
|
||||
- ViT 相关模型支持 **动态输入尺寸**。现在我们的 ViT，DeiT，Swin-Transformer 和 T2T-ViT 支持任意尺寸的输入。
|
||||
- 复现了 DeiT 的训练结果，并且我们的 DeiT-T 和 DeiT-S 拥有比官方权重 **更高的精度**。
|
||||
|
||||
发布历史和更新细节请参考 [更新日志](docs/en/changelog.md)
|
||||
|
||||
## 安装
|
||||
|
|
|
|||
|
|
@ -18,10 +18,10 @@ While originally designed for natural language processing (NLP) tasks, the self-
|
|||
|
||||
| Model | Pretrain | resolution | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download |
|
||||
|:---------:|:------------:|:-----------:|:---------:|:---------:|:---------:|:---------:|:------:|:--------:|
|
||||
| VAN-T\* | From scratch | 224x224 | 4.11 | 0.88 | 75.41 | 93.02 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-tiny_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-tiny_8xb128_in1k_20220427-8ac0feec.pth) |
|
||||
| VAN-S\* | From scratch | 224x224 | 13.86 | 2.52 | 81.01 | 95.63 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-small_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-small_8xb128_in1k_20220427-bd6a9edd.pth) |
|
||||
| VAN-B\* | From scratch | 224x224 | 26.58 | 5.03 | 82.80 | 96.21 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-base_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-base_8xb128_in1k_20220427-5275471d.pth) |
|
||||
| VAN-L\* | From scratch | 224x224 | 44.77 | 8.99 | 83.86 | 96.73 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-large_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-large_8xb128_in1k_20220427-56159105.pth) |
|
||||
| VAN-T\* | From scratch | 224x224 | 4.11 | 0.88 | 75.41 | 93.02 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-tiny_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-tiny_8xb128_in1k_20220501-385941af.pth) |
|
||||
| VAN-S\* | From scratch | 224x224 | 13.86 | 2.52 | 81.01 | 95.63 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-small_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-small_8xb128_in1k_20220501-17bc91aa.pth) |
|
||||
| VAN-B\* | From scratch | 224x224 | 26.58 | 5.03 | 82.80 | 96.21 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-base_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-base_8xb128_in1k_20220501-6a4cc31b.pth) |
|
||||
| VAN-L\* | From scratch | 224x224 | 44.77 | 8.99 | 83.86 | 96.73 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-large_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-large_8xb128_in1k_20220501-f212ba21.pth) |
|
||||
|
||||
*Models with \* are converted from [the official repo](https://github.com/Visual-Attention-Network/VAN-Classification). The config files of these models are only for validation. We don't ensure these config files' training accuracy and welcome you to contribute your reproduction results.
|
||||
|
||||
|
|
|
|||
|
|
@ -27,7 +27,7 @@ Models:
|
|||
Top 1 Accuracy: 75.41
|
||||
Top 5 Accuracy: 93.02
|
||||
Task: Image Classification
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/van/van-tiny_8xb128_in1k_20220427-8ac0feec.pth
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/van/van-tiny_8xb128_in1k_20220501-385941af.pth
|
||||
Config: configs/van/van-tiny_8xb128_in1k.py
|
||||
- Name: van-small_8xb128_in1k
|
||||
Metadata:
|
||||
|
|
@ -40,7 +40,7 @@ Models:
|
|||
Top 1 Accuracy: 81.01
|
||||
Top 5 Accuracy: 95.63
|
||||
Task: Image Classification
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/van/van-small_8xb128_in1k_20220427-bd6a9edd.pth
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/van/van-small_8xb128_in1k_20220501-17bc91aa.pth
|
||||
Config: configs/van/van-small_8xb128_in1k.py
|
||||
- Name: van-base_8xb128_in1k
|
||||
Metadata:
|
||||
|
|
@ -53,7 +53,7 @@ Models:
|
|||
Top 1 Accuracy: 82.80
|
||||
Top 5 Accuracy: 96.21
|
||||
Task: Image Classification
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/van/van-base_8xb128_in1k_20220427-5275471d.pth
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/van/van-base_8xb128_in1k_20220501-6a4cc31b.pth
|
||||
Config: configs/van/van-base_8xb128_in1k.py
|
||||
- Name: van-large_8xb128_in1k
|
||||
Metadata:
|
||||
|
|
@ -66,5 +66,5 @@ Models:
|
|||
Top 1 Accuracy: 83.86
|
||||
Top 5 Accuracy: 96.73
|
||||
Task: Image Classification
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/van/van-large_8xb128_in1k_20220427-56159105.pth
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/van/van-large_8xb128_in1k_20220501-f212ba21.pth
|
||||
Config: configs/van/van-large_8xb128_in1k.py
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@ ARG CUDNN="7"
|
|||
FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel
|
||||
|
||||
ARG MMCV="1.4.2"
|
||||
ARG MMCLS="0.22.1"
|
||||
ARG MMCLS="0.23.0"
|
||||
|
||||
ENV PYTHONUNBUFFERED TRUE
|
||||
|
||||
|
|
|
|||
|
|
@ -1,5 +1,20 @@
|
|||
# Changelog
|
||||
|
||||
## v0.23.0(1/5/2022)
|
||||
|
||||
### New Features
|
||||
|
||||
- Support DenseNet. ([#750](https://github.com/open-mmlab/mmclassification/pull/750))
|
||||
- Support VAN. ([#739](https://github.com/open-mmlab/mmclassification/pull/739))
|
||||
|
||||
### Improvements
|
||||
|
||||
- Support training on IPU and add fine-tuning configs of ViT. ([#723](https://github.com/open-mmlab/mmclassification/pull/723))
|
||||
|
||||
### Docs Update
|
||||
|
||||
- New style API reference, and easier to use! Welcome [view it](https://mmclassification.readthedocs.io/en/master/api/models.html). ([#774](https://github.com/open-mmlab/mmclassification/pull/774))
|
||||
|
||||
## v0.22.1(15/4/2022)
|
||||
|
||||
### New Features
|
||||
|
|
|
|||
|
|
@ -10,8 +10,9 @@ The compatible MMClassification and MMCV versions are as below. Please install t
|
|||
|
||||
| MMClassification version | MMCV version |
|
||||
|:------------------------:|:---------------------:|
|
||||
| dev | mmcv>=1.4.8, <1.6.0 |
|
||||
| 0.22.1 (master) | mmcv>=1.4.2, <1.6.0 |
|
||||
| dev | mmcv>=1.5.0, <1.6.0 |
|
||||
| 0.23.0 (master) | mmcv>=1.4.2, <1.6.0 |
|
||||
| 0.22.1 | mmcv>=1.4.2, <1.6.0 |
|
||||
| 0.21.0 | mmcv>=1.4.2, <=1.5.0 |
|
||||
| 0.20.1 | mmcv>=1.4.2, <=1.5.0 |
|
||||
| 0.19.0 | mmcv>=1.3.16, <=1.5.0 |
|
||||
|
|
|
|||
|
|
@ -137,10 +137,10 @@ The ResNet family models below are trained by standard data augmentations, i.e.,
|
|||
| DenseNet169\* | 14.15 | 3.42 | 76.08 | 93.11 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/densenet/densenet169_4xb256_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/densenet/densenet169_4xb256_in1k_20220426-a2889902.pth) |
|
||||
| DenseNet201\* | 20.01 | 4.37 | 77.32 | 93.64 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/densenet/densenet201_4xb256_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/densenet/densenet201_4xb256_in1k_20220426-05cae4ef.pth) |
|
||||
| DenseNet161\* | 28.68 | 7.82 | 77.61 | 93.83 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/densenet/densenet161_4xb256_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/densenet/densenet161_4xb256_in1k_20220426-ee6a80a9.pth) |
|
||||
| VAN-T\* | 4.11 | 0.88 | 75.41 | 93.02 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-tiny_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-tiny_8xb128_in1k_20220427-8ac0feec.pth) |
|
||||
| VAN-S\* | 13.86 | 2.52 | 81.01 | 95.63 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-small_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-small_8xb128_in1k_20220427-bd6a9edd.pth) |
|
||||
| VAN-B\* | 26.58 | 5.03 | 82.80 | 96.21 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-base_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-base_8xb128_in1k_20220427-5275471d.pth) |
|
||||
| VAN-L\* | 44.77 | 8.99 | 83.86 | 96.73 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-large_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-large_8xb128_in1k_20220427-56159105.pth) |
|
||||
| VAN-T\* | 4.11 | 0.88 | 75.41 | 93.02 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-tiny_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-tiny_8xb128_in1k_20220501-385941af.pth) |
|
||||
| VAN-S\* | 13.86 | 2.52 | 81.01 | 95.63 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-small_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-small_8xb128_in1k_20220501-17bc91aa.pth) |
|
||||
| VAN-B\* | 26.58 | 5.03 | 82.80 | 96.21 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-base_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-base_8xb128_in1k_20220501-6a4cc31b.pth) |
|
||||
| VAN-L\* | 44.77 | 8.99 | 83.86 | 96.73 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/van/van-large_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/van/van-large_8xb128_in1k_20220501-f212ba21.pth) |
|
||||
|
||||
*Models with \* are converted from other repos, others are trained by ourselves.*
|
||||
|
||||
|
|
|
|||
|
|
@ -11,7 +11,8 @@ MMClassification 和 MMCV 的适配关系如下，请安装正确版本的 MMCV
|
|||
| MMClassification 版本 | MMCV 版本 |
|
||||
|:------------------------:|:---------------------:|
|
||||
| dev | mmcv>=1.4.8, <1.6.0 |
|
||||
| 0.22.1 (master) | mmcv>=1.4.2, <1.6.0 |
|
||||
| 0.23.0 (master) | mmcv>=1.4.2, <1.6.0 |
|
||||
| 0.22.1 | mmcv>=1.4.2, <1.6.0 |
|
||||
| 0.21.0 | mmcv>=1.4.2, <=1.5.0 |
|
||||
| 0.20.1 | mmcv>=1.4.2, <=1.5.0 |
|
||||
| 0.19.0 | mmcv>=1.3.16, <=1.5.0 |
|
||||
|
|
|
|||
|
|
@ -506,11 +506,14 @@ class SwinTransformer(BaseBackbone):
|
|||
|
||||
def _prepare_relative_position_bias_table(self, state_dict, prefix, *args,
|
||||
**kwargs):
|
||||
all_keys = list(state_dict.keys())
|
||||
state_dict_model = self.state_dict()
|
||||
all_keys = list(state_dict_model.keys())
|
||||
for key in all_keys:
|
||||
if 'relative_position_bias_table' in key:
|
||||
relative_position_bias_table_pretrained = state_dict[key]
|
||||
ckpt_key = prefix + key
|
||||
if ckpt_key not in state_dict:
|
||||
continue
|
||||
relative_position_bias_table_pretrained = state_dict[ckpt_key]
|
||||
relative_position_bias_table_current = state_dict_model[key]
|
||||
L1, nH1 = relative_position_bias_table_pretrained.size()
|
||||
L2, nH2 = relative_position_bias_table_current.size()
|
||||
|
|
@ -522,11 +525,11 @@ class SwinTransformer(BaseBackbone):
|
|||
relative_position_bias_table_pretrained, nH1)
|
||||
from mmcls.utils import get_root_logger
|
||||
logger = get_root_logger()
|
||||
logger.info(
|
||||
f'Resize the relative_position_bias_table from \
|
||||
{state_dict[key].shape} to {new_rel_pos_bias.shape}')
|
||||
state_dict[key] = new_rel_pos_bias
|
||||
logger.info('Resize the relative_position_bias_table from '
|
||||
f'{state_dict[ckpt_key].shape} to '
|
||||
f'{new_rel_pos_bias.shape}')
|
||||
state_dict[ckpt_key] = new_rel_pos_bias
|
||||
|
||||
# The index buffer need to be re-generated.
|
||||
index_buffer = key.replace('bias_table', 'index')
|
||||
index_buffer = ckpt_key.replace('bias_table', 'index')
|
||||
del state_dict[index_buffer]
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# Copyright (c) OpenMMLab. All rights reserved
|
||||
|
||||
__version__ = '0.22.1'
|
||||
__version__ = '0.23.0'
|
||||
|
||||
|
||||
def parse_version_info(version_str):
|
||||
|
|
|
|||
Loading…
Reference in New Issue