MCPcopy
hub / github.com/Fafa-DL/Awesome-Backbones

github.com/Fafa-DL/Awesome-Backbones @v0.6.3 sqlite

repository ↗ · DeepWiki ↗ · release v0.6.3 ↗
1,238 symbols 3,576 edges 320 files 434 documented · 35%
README

Awesome backbones for image classification

BILIBILI

GitHub forks GitHub stars Visitors

更新日志

2023.03.07 - 新增MobileViTDaViTRepLKNetBEiTEVAMixMIMEfficientNetV2

2022.11.20 - 新增是否将测试集用作验证集选项,若不使用,从训练集按ratio划分验证集数量,随机从训练集某fold挑选作为验证集(类似k-fold但不是,可自己稍改达到k-fold目的),详见Training tutorial

2022.11.06 - 新增HorNet, EfficientFormer, SwinTransformer V2, MViT模型

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

3群:584723646

快速开始

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

教程

模型

预训练权重

名称 权重 名称 权重 名称 权重
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](https://download.openmmlab.com/mmclassification/v0

Core symbols most depended-on inside this repo

get
called by 194
core/datasets/build.py
build_norm_layer
called by 111
configs/basic/build_layer.py
build_conv_layer
called by 34
configs/basic/build_layer.py
update
called by 26
utils/history.py
build_activation_layer
called by 25
configs/basic/build_layer.py
norm1
called by 22
configs/backbones/hrnet.py
norm2
called by 19
configs/backbones/hrnet.py
trunc_normal_
called by 18
core/initialize/weight_init.py

Shape

Method 737
Function 262
Class 239

Languages

Python100%

Modules by API surface

core/datasets/auto_augment.py68 symbols
core/datasets/transforms.py55 symbols
core/initialize/weight_init.py52 symbols
configs/backbones/davit.py33 symbols
utils/flops_counter.py32 symbols
core/datasets/formatting.py29 symbols
configs/backbones/resnet.py29 symbols
configs/backbones/efficientformer.py27 symbols
utils/misc.py24 symbols
configs/backbones/replknet.py24 symbols
core/optimizers/lr_update.py23 symbols
configs/common/attention.py23 symbols

Dependencies from manifests, versioned

Pillow8.4.0 · 1×
albumentations1.2.1 · 1×
h5py3.1.0 · 1×
matplotlib3.2.1 · 1×
numpy1.19.2 · 1×
packaging21.3 · 1×
scipy1.4.1 · 1×
terminaltables3.1.0 · 1×
tqdm4.62.3 · 1×

For agents

$ claude mcp add Awesome-Backbones \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact