Awesome Backbones
Integrate deep learning models for image classification | Backbone learning/comparison/magic modification project
Install / Use
npx skills add Fafa-DL/Awesome-BackbonesInstalls into whichever agent you are using.
README
Awesome backbones for image classification
<div align="center"> </div>写在前面
- 若训练效果不佳,首先需要调整学习率和Batch size,这俩超参很大程度上影响收敛。其次,从关闭图像增强手段(尤其小数据集)开始,有的图像增强方法会污染数据,如

如何去除增强?如efficientnetv2-b0配置文件中train_pipeline可更改为如下
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'])
]
若你的数据集提前已经将shape更改为网络要求的尺寸,那么Resize操作也可以去除。
更新日志
2025.01.17
2024.09.06
- 修复高频反馈的评估时结果浮动大的问题
2023.12.02
-
新增Issue中多人提及的输出Train Acc与Val loss
metrics_outputs.csv保存每周期train_loss, train_acc, train_precision, train_recall, train_f1-score, val_loss, val_acc, val_precision, val_recall, val_f1-score方便各位绘图- 终端由原先仅输出Val相关metrics升级为Train与Val都输出

2023.08.05
- 新增TinyViT(预训练权重不匹配)、DeiT3、EdgeNeXt、RevVisionTransformer
2023.03.07
- 新增MobileViT、DaViT、RepLKNet、BEiT、EVA、MixMIM、EfficientNetV2
测试环境
- Pytorch 1.7.1+
- Python 3.6+
资料
|数据集|视频教程|人工智能技术探讨群|
|---|---|---|
|花卉数据集 提取码:0zat|点我跳转|1群:78174903<br/>3群:584723646
快速开始
- 遵循环境搭建完成配置
- 下载MobileNetV3-Small权重至datas下
- Awesome-Backbones文件夹下终端输入
python tools/single_test.py datas/cat-dog.png models/mobilenet/mobilenet_v3_small.py --classes-map datas/imageNet1kAnnotation.txt
教程
模型
- [x] LeNet5
- [x] AlexNet
- [x] VGG
- [x] DenseNet
- [x] ResNet
- [x] Wide-ResNet
- [x] ResNeXt
- [x] SEResNet
- [x] SEResNeXt
- [x] RegNet
- [x] MobileNetV2
- [x] MobileNetV3
- [x] ShuffleNetV1
- [x] ShuffleNetV2
- [x] EfficientNet
- [x] RepVGG
- [x] Res2Net
- [x] ConvNeXt
- [x] HRNet
- [x] ConvMixer
- [x] CSPNet
- [x] Swin-Transformer
- [x] Vision-Transformer
- [x] Transformer-in-Transformer
- [x] MLP-Mixer
- [x] DeiT
- [x] Conformer
- [x] T2T-ViT
- [x] Twins
- [x] PoolFormer
- [x] VAN
- [x] HorNet
- [x] EfficientFormer
- [x] Swin Transformer V2
- [x] MViT V2
- [x] MobileViT
- [x] DaViT
- [x] replknet
- [x] BEiT
- [x] EVA
- [x] MixMIM
- [x] EfficientNetV2
预训练权重
| 名称 | 权重 | 名称 | 权重 | 名称 | 权重 | | :-----: | :-----: | :------: | :------: | :------: | :-----: | | LeNet5 | None | AlexNet | None | VGG | VGG-11<br/>VGG-13<br/>VGG-16<br/>VGG-19<br/>VGG-11-BN<br/>VGG-13-BN<br/>VGG-16-BN<br/>VGG-19-BN| | ResNet |ResNet-18<br/>ResNet-34<br/>ResNet-50<br/>ResNet-101<br/>ResNet-152 | ResNetV1C | ResNetV1C-50<br/>ResNetV1C-101<br/>ResNetV1C-152 |ResNetV1D | ResNetV1D-50<br/>ResNetV1D-101<br/>ResNetV1D-152 | | ResNeXt | [ResNeXt-50](https://download.op
Related Skills
mcp
Use the `mcp_perplexity-ask_perplexity_search` tools to answer questions. You should use this instead of the `web_search` tool because it is a lot more accurate.
practical-power-systems-synthesis
This skill enables synthesis in the domain of power-systems (engineering). It represents research-level-level expertise and is designed for production use in research, industry, and educational contexts. Use this skill when you need to perform synthesis operations related to power-systems.
semi-supervised-optogenetics-testing
This skill enables testing in the domain of optogenetics (neuroscience). It represents intermediate-level expertise and is designed for production use in research, industry, and educational contexts. Use this skill when you need to perform testing operations related to optogenetics.
data-mining-interpretation-fundamental
This skill enables interpretation in the domain of data-mining (data-science). It represents fundamental-level expertise and is designed for production use in research, industry, and educational contexts. Use this skill when you need to perform interpretation operations related to data-mining.

