xiaoroulian/deeplearning_models_classifier_tutorial

使用常见的CNN架构实现CIFAR分类。

pytorch_image_classifier_tutorial

This repository uses Pytorch to implement the popular CNN architectures, using the dataset CIFAR. The following is the reference paper:

Architecture

• (lenet)LeNet-5, convolutional neural networks
• (alexnet) ImageNet Classification with Deep Convolutional Neural Networks
• (vgg) Very Deep Convolutional Networks for Large-Scale Image Recognition
• (resnet) Deep Residual Learning for Image Recognition
• (preresnet) Identity Mappings in Deep Residual Networks
• (resnext) Aggregated Residual Transformations for Deep Neural Networks
• (densenet) Densely Connected Convolutional Networks
• (senet) Squeeze-and-Excitation Networks
• (bam) BAM: Bottleneck Attention Module
• (cbam) CBAM: Convolutional Block Attention Module
• (genet) Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks
• (sknet) SKNet: Selective Kernel Networks
• (mobilenetV1)MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• (mobilenetV2)MobileNetV2: Inverted Residuals and Linear Bottlenecks

Regularization

• (shake-shake) Shake-Shake regularization
• (cutout) Improved Regularization of Convolutional Neural Networks with Cutout
• (mixup) mixup: Beyond Empirical Risk Minimization

Learning Rate Scheduler

• (cos_lr) SGDR: Stochastic Gradient Descent with Warm Restarts
• (htd_lr) Stochastic Gradient Descent with Hyperbolic-Tangent Decay on Classification

Requirements

• Python >= 3.5
• PyTorch = 0.4 or 1.0
• Tensorboard (if you want to use the tensorboard for visualization)
• pyyaml, easydict, tensorboardX

Usage

Run the command for training as following:

##1 GPU for lenet
python -u train.py --work-path ./experiments/cifar10/lenet
##resume from checkpoint
python -u train.py --work-path ./experiments/cifar10/lenet --resume
##2 GPUs for resnet1202
CUDA_VISIBLE_DEVICES=0,1 python -u train.py --work-path ./experiments/cifar10/preresnet20
##4 GPUs for densenet190bc
CUDA_VISIBLE_DEVICES=0,1,2,3 python -u train.py --work-path ./experiments/cifar10/densenet100bc

Feel free to contact me if you have any suggestions or questions, issues are welcome, create a PR if you find any bugs or you want to contribute.:smile: