Skip to content
This repository has been archived by the owner on Aug 27, 2022. It is now read-only.
/ CNN Public archive

pytorch implementation of several CNNs for image classification

Notifications You must be signed in to change notification settings

syt2/CNN

Repository files navigation

CNNs for image classification

Train CNNs for image classification from scratch.

I post several pretrained weights below.

Requirement

  • pytorch 1.4.0+
  • torchvision
  • tensorboard 1.14+
  • numpy
  • pyyaml
  • tqdm
  • pillow

Dataset

  • CIFAR-10
  • CIFAR-100
  • ImageNet 2012

Usage

  • Add configuration file under configs folder as follows
    • cuda: "all"  # if not specified, use cpu. or specified as "0", "0,1"
      model:
          arch: resnet
          depth: 50
      data:
          dataset: imagenet
          train_dir: /PATH/TO/ILSVRC/train
          val_dir: /PATH/TO/ILSVRC/val
          workers: 16
      training:
          runid: xxxx  # recommended specified during validation and testing
          epochs: 100
          batch_size: 256
          loss:
              name: 'label_smooth'
              smoothing: 0.1
          optimizer:
              name: 'sgd'
              lr: 0.1
              weight_decay: 0.0001
              momentum: 0.9
          lr_schedule:
              name: 'multi_step'
              milestones: [30,60,90]
              gamma: 0.1
          save_interval: 1
          resume: save_model.pkl
          best_model: best_model.pkl
      
  • run train.py, validate.py or test.py as follows
    • python train.py --config configs/aaaa.yml

Pretrained Model on ImageNet 2012

Architecture Top-1 error Params FLOPs Pretrained weights
ResNet18
(My Imp.)
29.72 11.69M 1.82G Google Drive
Baidu Netdisk
ResNet18
(paper)
30.43 - - -
ResNet50
(My Imp.)
23.30 25.56M 4.11G Google Drive
Baidu Netdisk
ResNet50
(paper)
24.7 - - -
ResNet101
(My Imp.)
22.18 44.55M 7.84G Google Drive
ResNet101
(paper)
22.44 - - -
ResNeXt50
(My Imp.)
22.35 25.03M 4.26G Google Drive
Baidu Netdisk
ResNeXt50
(paper)
22.2 - - -
SE ResNet50
(My Imp.)
22.64 28.09M 4.12G Google Drive
Baidu Netdisk
SE ResNet50
(paper)
23.29 - - -
CBAM ResNet50
(My Imp.)
22.40 28.07M 4.13G Google Drive
CBAM ResNet50
(paper)
22.66 - - -
SKNet50
(My Imp.)
21.26 27.49M 4.50G Google Drive
Baidu Netdisk
SKNet50
(paper)
20.79 - - -
MobileNet V2 0.5x
(My Imp.)
35.62 1.97M 138.46M Google Drive
MobileNet V2 0.5x
(paper)
35.6 - - -
MobileNet V2 1x
(My Imp.)
28.09 3.50M 315.41M Google Drive
Baidu Netdisk
MobileNet V2 1x
(paper)
28.0 - - -
MobileNet V3 large
(My Imp.)
26.79 5.48M 230.05M Google Drive
MobileNet V3 large
(paper)
24.8 - - -

The hyperparameters and settings during my training for ResNet, ResNeXt, SENet, SKNet are the same as the paper, except I use label smooth loss.

And for MobileNet V2 and MobileNet V3, I follow the setup in this project, and use label smooth loss too.

Pretrained weights usage

  1. place the downloaded pretrained model in runs/aaaa/xxxx folder under this project, where aaaa is the name of configuration file and xxxx is runid in configuration file.
  2. run validate.py or test.py as above.