Unofficial EfficientNetV2 pytorch implementation repository.

It contains:

• Simple Implementation of model (here)
• Pretrained Model (numpy weight, we upload numpy files converted from official tensorflow checkout point)
• Training code (here)
• Tutorial (Colab EfficientNetV2-predict tutorial, Colab EfficientNetV2-finetuning tutorial)
• Experiment results

1. Tutorial
2. Experiment results
3. Experiment Setup
4. References

Colab Tutorial

• How to use model on colab? please check Colab EfficientNetV2-predict tutorial

• How to train model on colab? please check Colab EfficientNetV2-finetuning tutorial

• See how cutmix, cutout, mixup works in Colab Data augmentation tutorial

If you just want to use pretrained model, load model by torch.hub.load

import torch

model = torch.hub.load('hankyul2/EfficientNetV2-pytorch', 'efficientnet_v2_s', pretrained=True, nclass=1000)
print(model)

Available Model Names: efficientnet_v2_{s|m|l}(ImageNet), efficientnet_v2_{s|m|l}_in21k(ImageNet21k)

If you want to finetuning on cifar, use this repository.

1. Clone this repo and install dependency

   git clone https://github.com/hankyul2/EfficientNetV2-pytorch.git
   pip3 install requirements.txt

2. Train & Test model

   python3 main.py fit --config config/base.yaml --trainer.gpus 2, --data.dataset_name cifar100 --model.model_name efficientnet_v2_s  --seed_everything 2021

Note

1. Training Results are not good enough to match with paper results
2. All models are trained using same setup in experiment setup section (which is adapted from paper)

ImageNet Setup

Cifar Setup

Note

1. For progressive learning, ImageSize, RandAugmentation, Mixup, Dropout are going to be changed along with epoch.
2. Evaluation Size is different for each model
3. epoch=100 in Cifar Stepup is calculated from paper like this: 10,000 step * 512 batch size / 50,000 images = 102.4
4. To see more model specific details, check efficientnet_v2_config.py
5. To see more train hyperparameter, check cifar.yaml

EfficientNetV2

• Title: EfficientNetV2: Smaller models and Faster Training

• Author: Minxing Tan

• Publication: ICML, 2021

• Link: Paper | official tensorflow repo | other pytorch repo

• Other references:

  • Training ImageNet in 3 hours for USD 25; and CIFAR10 for USD 0.26