Pytorch Implementations of large number classical backbone CNNs, data enhancement, torch loss, attention, visualization and some common algorithms.

Li Shengyan

Last update: Dec 31, 2022

Overview

Torch-template-for-deep-learning

Pytorch implementations of some **classical backbone CNNs, data enhancement, torch loss, attention, visualization and some common algorithms **.

Requirements

· torch, torch-vision

· torchsummary

· other necessary

usage

A training script is supplied in “train_baseline.py”, the arguments are in “args.py

autoaug: Data enhancement and CNNs regularization

- StochDepth
- label smoothing
- Cutout
- DropBlock
- Mixup
- Manifold Mixup
- ShakeDrop
- cutmix

dataset_loader: Loaders for various datasets

from dataloder.scoliosis_dataloder import ScoliosisDataset
from dataloder.facial_attraction_dataloder import FacialAttractionDataset
from dataloder.fa_and_sco_dataloder import ScoandFaDataset
from dataloder.scofaNshot_dataloder import ScoandFaNshotDataset
from dataloder.age_dataloder import MegaAsiaAgeDataset
def load_dataset(data_config):
    if data_config.dataset == 'cifar10':
        training_transform=training_transforms()
        if data_config.autoaug:
            print('auto Augmentation the data !')
            training_transform.transforms.insert(0, Augmentation(fa_reduced_cifar10()))
        train_dataset = torchvision.datasets.CIFAR10(root=data_config.data_path,
                                                     train=True,
                                                     transform=training_transform,
                                                     download=True)
        val_dataset = torchvision.datasets.CIFAR10(root=data_config.data_path,
                                                   train=False,
                                                   transform=validation_transforms(),
                                                   download=True)
        return train_dataset,val_dataset
    elif data_config.dataset == 'cifar100':
        train_dataset = torchvision.datasets.CIFAR100(root=data_config.data_path,
                                                     train=True,
                                                     transform=training_transforms(),
                                                     download=True)
        val_dataset = torchvision.datasets.CIFAR100(root=data_config.data_path,
                                                   train=False,
                                                   transform=validation_transforms(),
                                                   download=True)
        return train_dataset, val_dataset

deployment: Deployment mode of pytorch model

Two deployment modes of pytorch model are provided, one is web deployment and the other is C + + deployment

Store the training weight file in ` flash_ Deployment ` folder

Then modify ' server.py '  path

Leverage ' client.Py ' call

models: Various classical deep learning models

Classical network

- **AlexNet**
- **VGG**
- **ResNet** 
- **ResNext** 
- **InceptionV1**
- **InceptionV2 and InceptionV3**
- **InceptionV4 and Inception-ResNet**
- **GoogleNet**
- **EfficienNet**
- **MNasNet**
- **DPN**

Attention network

- **SE Attention**
- **External Attention**
- **Self Attention**
- **SK Attention**
- **CBAM Attention**
- **BAM Attention**
- **ECA Attention**
- **DANet Attention**
- **Pyramid Split Attention(PSA)**
- **EMSA Attention**
- **A2Attention**
- **Non-Local Attention**
- **CoAtNet**
- **CoordAttention**
- **HaloAttention**
- **MobileViTAttention**
- **MUSEAttention**  
- **OutlookAttention**
- **ParNetAttention**
- **ParallelPolarizedSelfAttention**
- **residual_attention**
- **S2Attention**
- **SpatialGroupEnhance Attention**
- **ShuffleAttention**
- **GFNet Attention**
- **TripletAttention**
- **UFOAttention**
- **VIPAttention**

Lightweight network

- **MobileNets:**
- **MobileNetV2：**
- **MobileNetV3：**
- **ShuffleNet：**
- **ShuffleNet V2:**
- **SqueezeNet**
- **Xception**
- **MixNet**
- **GhostNet**

GAN

- **Auxiliary Classifier GAN**
- **Adversarial Autoencoder**
- **BEGAN**
- **BicycleGAN**
- **Boundary-Seeking GAN**
- **Cluster GAN**
- **Conditional GAN**
- **Context-Conditional GAN**
- **Context Encoder**
- **Coupled GAN**
- **CycleGAN**
- **Deep Convolutional GAN**
- **DiscoGAN**
- **DRAGAN**
- **DualGAN**
- **Energy-Based GAN**
- **Enhanced Super-Resolution GAN**  
- **Least Squares GAN**
- **Enhanced Super-Resolution GAN**
- **GAN**
- **InfoGAN**
- **Pix2Pix**
- **Relativistic GAN**
- **Semi-Supervised GAN**
- **StarGAN**
- **Wasserstein GAN**
- **Wasserstein GAN GP**
- **Wasserstein GAN DIV**

ObjectDetection-network

- **SSD:**
- **YOLO:**
- **YOLOv2:**
- **YOLOv3:**
- **FCOS:**
- **FPN:**
- **RetinaNet**
- **Objects as Points:**
- **FSAF:**
- **CenterNet**
- **FoveaBox**

Semantic Segmentation

- **FCN**
- **Fast-SCNN**
- **LEDNet:**
- **LRNNet**
- **FisheyeMODNet:**

Instance Segmentation

- **PolarMask**

FaceDetectorAndRecognition

- **FaceBoxes**
- **LFFD**
- **VarGFaceNet**

HumanPoseEstimation

- **Stacked Hourglass Networks**
- **Simple Baselines**
- **LPN**

pytorch_loss: loss for training

- label-smooth
- amsoftmax
- focal-loss
- dual-focal-loss 
- triplet-loss
- giou-loss
- affinity-loss
- pc_softmax_cross_entropy
- ohem-loss(softmax based on line hard mining loss)
- large-margin-softmax(bmvc2019)
- lovasz-softmax-loss
- dice-loss(both generalized soft dice loss and batch soft dice loss)

tf_to_pytorch: TensorFlow to PyTorch Conversion

This directory is used to convert TensorFlow weights to PyTorch. 
It was hacked together fairly quickly, so the code is not the most 
beautiful (just a warning!), but it does the job. I will be refactoring it soon.

TorchCAM: Class Activation Mapping

Simple way to leverage the class-specific activation of convolutional layers in PyTorch.

- CAM
- ScoreCAM
- SSCAM
- ISCAM
- GradCAM
- Grad-CAM++
- Smooth Grad-CAM++
- XGradCAM
- LayerCAM

Note

More modules may be added later.
During the implementation process, I read a lot of codes and articles and referred to a lot of contents. Some have added copyright notices, and some don't remember the main references. If there is infringement, please contact to delete.
I wrote some blogs（which are in Chinese） to introduce the models implemented in this project：
Some of My Reference Repositories：

Write at the end

At present, the work organized by this project is indeed not comprehensive enough. As the amount of reading increases, we will continue to improve this project. Welcome everyone star to support. If there are incorrect statements or incorrect code implementations in the article, you are welcome to point out~

This repository provides the official implementation of 'Learning to ignore: rethinking attention in CNNs' accepted in BMVC 2021.

inverse_attention This repository provides the official implementation of 'Learning to ignore: rethinking attention in CNNs' accepted in BMVC 2021. Le

5 Jul 8, 2022

[CVPRW 2022] Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network

Attention Helps CNN See Better: Hybrid Image Quality Assessment Network [CVPRW 2022] Code for Hybrid Image Quality Assessment Network [paper] [code] T

49 Dec 11, 2022

This repository is related to an Arabic tutorial, within the tutorial we discuss the common data structure and algorithms and their worst and best case for each, then implement the code using Python.

Data Structure and Algorithms with Python This repository is related to the Arabic tutorial here, within the tutorial we discuss the common data struc

33 Dec 2, 2022

(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"

Res2Net The official pytorch implemention of the paper "Res2Net: A New Multi-scale Backbone Architecture" Our paper is accepted by IEEE Transactions o

928 Dec 29, 2022

PyTorch Implementation of Backbone of PicoDet

PicoDet-Backbone PyTorch Implementation of Backbone of PicoDet Original Implementation is implemented on PaddlePaddle. Example picodet_l_backbone = ES

7 Jul 12, 2022

Adds timm pretrained backbone to pytorch's FasterRcnn model

timmFasterRcnn model_config.py - it returns the model,feat_sizes,output channel and the feat layer names, which is reqd by the Add_FPN.py file Add_FP

12 Dec 3, 2022

PyTorch implementations of deep reinforcement learning algorithms and environments

Deep Reinforcement Learning Algorithms with PyTorch This repository contains PyTorch implementations of deep reinforcement learning algorithms and env

4.7k Jan 4, 2023

Pytorch implementations of popular off-policy multi-agent reinforcement learning algorithms, including QMix, VDN, MADDPG, and MATD3.

Off-Policy Multi-Agent Reinforcement Learning (MARL) Algorithms This repository contains implementations of various off-policy multi-agent reinforceme

183 Dec 28, 2022

text_recognition_toolbox: The reimplementation of a series of classical scene text recognition papers with Pytorch in a uniform way.

text recognition toolbox 1. 项目介绍该项目是基于pytorch深度学习框架，以统一的改写方式实现了以下6篇经典的文字识别论文，论文的详情如下。该项目会持续进行更新，欢迎大家提出问题以及对代码进行贡献。模型论文标题发表年份模型方法划分 CRNN 《An End-t

168 Dec 24, 2022

Comments

Should be `loss * self.eps/(c-1)`?

Hi,

Based on my understanding, the label smooth loss should be constructed like: for the non-target label, the corresponding value should be set as \epsilon / (num_classes-1)

https://github.com/ZhugeKongan/torch-template-for-deep-learning/blob/4a84444066456c7bb27daeec5e85d512eccc88cf/autoaug/label_smoothing.py#L19

So, this line might be correct as loss*self.eps/(c-1)?

opened by CiaoHe 1