Awesome Backbones

Awesome backbones for image classification

Write in front

• If the training effect is not good, the first thing you need to do is to adjust the learning rate and Batch size, which greatly affect convergence. Secondly, starting from turning off image enhancement methods (especially small datasets), some image enhancement methods can contaminate data, such as

How to remove enhancements? If train_pipeline in efficientnetv2-b0 configuration file can be changed to the following

 train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='RandomResizedCrop',
        size=192,
        efficientnet_style=True,
        interpolation='bicubic'),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='ImageToTensor', keys=['img']),
    dict(type='ToTensor', keys=['gt_label']),
    dict(type='Collect', keys=['img', 'gt_label'])
]

If your dataset has changed shape to the network-required size in advance, the Resize operation can also be removed.

Update log

2024.09.06

• Fixed the problem of large floating results during evaluation of high-frequency feedback

2023.12.02

• Added the outputs mentioned by many people in Issue , Train Acc and Val loss

  • metrics_outputs.csv saves train_loss, train_acc, train_precision, train_recall, train_f1-score, val_loss, val_acc, val_precision, val_recall, val_f1-score for everyone to draw
  • The terminal has been upgraded from the original output of Val -related metrics to both Train and Val output

2023.08.05

• Added TinyViT (pretraining weight mismatch), DeiT3 , EdgeNeXt , RevVisionTransformer

2023.03.07

• Added MobileViT , DaViT , RepLKNet , BEiT , EVA , MixMIM , EfficientNetV2

2022.11.20

• Added whether to use the test set as the verification set option. If not, divide the number of verification sets from the training set by ratio, and randomly select it from a certain folder of the training set as the verification set (similar to k-fold but not, you can change it slightly to achieve the purpose of k-fold). See Training tutorial for details

Test environment

• Pytorch 1.7.1+
• Python 3.6+

material

Dataset	Video tutorial	Artificial Intelligence Technology Discussion Group
花卉数据集extraction code: 0zat	Click me to jump	Group 1: 78174903 Group 3: 584723646

Start quickly

• Complete configuration by loop environment construction
• Download MobileNetV3-Small weight to datas
• Terminal input under Awesome-Backbones folder

python tools/single_test.py datas/cat-dog.png models/mobilenet/mobilenet_v3_small.py --classes-map datas/imageNet1kAnnotation.txt

Tutorial

• Environment construction
• Dataset preparation
• Configuration file explanation
• train
• Model evaluation
• Calculate Flops & Params
• Add new model components
• Category activation graph visualization
• Learning rate strategy visualization
• Data Enhancement Policy Visualization

Model

• LeNet5
• AlexNet
• VGG
• DenseNet
• ResNet
• Wide-ResNet
• ResNeXt
• SEResNet
• SEResNeXt
• RegNet
• MobileNetV2
• MobileNetV3
• ShuffleNetV1
• ShuffleNetV2
• EfficientNet
• RepVGG
• Res2Net
• ConvNeXt
• HRNet
• ConvMixer
• CSPNet
• Swin-Transformer
• Vision-Transformer
• Transformer-in-Transformer
• MLP-Mixer
• DeiT
• Conformer
• T2T-ViT
• Twins
• PoolFormer
• VAN
• HorNet
• EfficientFormer
• Swin Transformer V2
• MViT V2
• MobileViT
• DaViT
• replknet
• BEiT
• EVA
• MixMIM
• EfficientNetV2

Pre-training weights

name	Weight	name	Weight	name	Weight
LeNet5	None	AlexNet	None	VGG	VGG-11 VGG-13 VGG-16 VGG-19 VGG-11-BN VGG-13-BN VGG-16-BN VGG-19-BN
ResNet	ResNet-18 ResNet-34 ResNet-50 ResNet-101 ResNet-152	ResNetV1C	ResNetV1C-50 ResNetV1C-101 ResNetV1C-152	ResNetV1D	ResNetV1D-50 ResNetV1D-101 ResNetV1D-152
ResNeXt	ResNeXt-50 ResNeXt-101 ResNeXt-152	SEResNet	SEResNet-50 SEResNet-101	SEResNeXt	None
RegNet	RegNetX-400MF RegNetX-800MF RegNetX-1.6GF RegNetX-3.2GF RegNetX-4.0GF RegNetX-6.4GF RegNetX-8.0GF RegNetX-12GF	MobileNetV2	MobileNetV2	MobileNetV3	MobileNetV3-Small MobileNetV3-Large
ShuffleNetV1	ShuffleNetV1	ShuffleNetV2	ShuffleNetV2	EfficientNet	EfficientNet-B0 EfficientNet-B1 EfficientNet-B2 EfficientNet-B3 EfficientNet-B4 EfficientNet-B5 EfficientNet-B6 EfficientNet-B7 EfficientNet-B8
RepVGG	RepVGG-A0 RepVGG-A1 RepVGG-A2 RepVGG-B0 RepVGG-B1 RepVGG-A1 RepVGG-B1g2 RepVGG-B1g4 RepVGG-B2 RepVGG-B2g4 RepVGG-B2g4 RepVGG-B3 RepVGG-B3g4 RepVGG-D2se	Res2Net	Res2Net-50-14w-8s Res2Net-50-26w-8s Res2Net-101-26w-4s	ConvNeXt	ConvNeXt-Tiny ConvNeXt-Small ConvNeXt-Base ConvNeXt-Large ConvNeXt-XLarge
HRNet	HRNet-W18 HRNet-W30 HRNet-W32 HRNet-W40 HRNet-W44 HRNet-W48 HRNet-W64	ConvMixer	ConvMixer-768/32 ConvMixer-1024/20 ConvMixer-1536/20	CSPNet	CSPDarkNet50 CSPResNet50 CSPResNeXt50
Swin Transformer	tiny-224 small-224 base-224 large-224 base-384 large-384	Vision Transformer	vit_base_p16_224 vit_base_p32_224 vit_large_p16_224 vit_base_p16_384 vit_base_p32_384 vit_large_p16_384	Transformer in Transformer	TNT-small
MLP Mixer	base_p16 large_p16	Deit	DeiT-tiny DeiT-tiny distilled DeiT-small DeiT-small distilled DeiT-base DeiT-base distilled DeiT-base 384px DeiT-base distilled 384px	Conformer	Conformer-tiny-p16 Conformer-small-p32 Conformer-small-p16 Conformer-base-p16
T2T-ViT	T2T-ViT_t-14 T2T-ViT_t-19 T2T-ViT_t-24	Twins	PCPVT-small PCPVT-base PCPVT-large SVT-small SVT-base SVT-large	PoolFormer	PoolFormer-S12 PoolFormer-S24 PoolFormer-S36 PoolFormer-M36 PoolFormer-M48
DenseNet	DenseNet121 DenseNet161 DenseNet169 DenseNet201	Visual Attention Network(VAN)	VAN-Tiny VAN-Small VAN-Base VAN-Large	Wide-ResNet	WRN-50 WRN-101
HorNet	HorNet-Tiny HorNet-Tiny-GF HorNet-Small HorNet-Small-GF HorNet-Base HorNet-Base-GF HorNet-Large HorNet-Large-GF HorNet-Large-GF384	EfficientFormer	efficientformer-l1 efficientformer-l3 efficientformer-l7	Swin Transformer v2	tiny-256 window 8 tiny-256 window 16 small-256 window 8 small-256 window 16 base-256 window 8 base-256 window 16 large-256 window 16 large-384 window 24
MViTv2	MViTv2-Tiny MViTv2-Small MViTv2-Base MViTv2-Large	MobileVit	MobileViT-XXSmall MobileViT-XSmall MobileViT-Small	DaViT	DaViT-T DaViT-S DaViT-B
RepLKNet	RepLKNet-31B-224 RepLKNet-31B-384 RepLKNet-31L-384 RepLKNet-XL	BEiT	BEiT-base	EVA	EVA-G-p14-224 EVA-G-p14-336 EVA-G-p14-560 EVA-G-p16-224 EVA-L-p14-224 EVA-L-p14-196 EVA-L-p14-336
MixMIM	mixmim-base	EfficientNetV2	EfficientNetV2-b0 EfficientNetV2-b1 EfficientNetV2-b2 EfficientNetV2-b3 EfficientNetV2-s EfficientNetV2-m EfficientNetV2-l EfficientNetV2-xl	DeiT3	deit3_small_p16 deit3_small_p16_384 deit3_base_p16 deit3_base_p16_384 deit3_medium_p16 deit3_large_p16 deit3_large_p16_384 deit3_huge_p16
EdgeNeXt	edgeext-base edgeext-small edgeext-X-small edgeext-XX-small	RevVisionTransformer	revvit-small revvit-base

Other projects I maintain

• Insufficient image data? I made an image enhancement software
• One-click conversion and editing image labeling files software greatly improves efficiency

refer to

 @repo{2020mmclassification,
    title={OpenMMLab's Image Classification Toolbox and Benchmark},
    author={MMClassification Contributors},
    howpublished = {url{https://github.com/open-mmlab/mmclassification}},
    year={2020}
}