Skip to content

Latest commit

 

History

History
 
 

ConvMixer

README.md

ConvMixer: Patches Are All You Need? 🤷, OpenReview

PaddlePaddle training/validation code and pretrained models for ConvMixer.

The official pytorch implementation is here.

This implementation is developed by PaddleViT.

drawing

ConvMixer Model Overview

Update

  • Update (2021-11-04): Model weights are updated.
  • Update (2021-10-13): Code is released and ported weights are uploaded.

Models Zoo

Model Acc@1 Acc@5 #Params FLOPs Image Size Crop_pct Interpolation Link
convmixer_1024_20 76.94 93.35 24.5M 9.5G 224 0.96 bicubic google/baidu(qpn9)
convmixer_768_32 80.16 95.08 21.2M 20.8G 224 0.96 bicubic google/baidu(m5s5)
convmixer_1536_20 81.37 95.62 51.8M 72.4G 224 0.96 bicubic google/baidu(xqty)

*The results are evaluated on ImageNet2012 validation set.

Notebooks

We provide a few notebooks in aistudio to help you get started:

*(coming soon)*

Requirements

Data

ImageNet2012 dataset is used in the following folder structure:

│imagenet/
├──train/
│  ├── n01440764
│  │   ├── n01440764_10026.JPEG
│  │   ├── n01440764_10027.JPEG
│  │   ├── ......
│  ├── ......
├──val/
│  ├── n01440764
│  │   ├── ILSVRC2012_val_00000293.JPEG
│  │   ├── ILSVRC2012_val_00002138.JPEG
│  │   ├── ......
│  ├── ......

Usage

To use the model with pretrained weights, download the .pdparam weight file and change related file paths in the following python scripts. The model config files are located in ./configs/.

For example, assume the downloaded weight file is stored in ./convmixer_768_32.pdparams, to use the convmixer_768_32 model in python:

from config import get_config
from convmixer import build_convmixer as build_model
# config files in ./configs/
config = get_config('./configs/convmixer_768_32.yaml')
# build model
model = build_model(config)
# load pretrained weights
model_state_dict = paddle.load('./convmixer_768_32.pdparams')
model.set_dict(model_state_dict)

Evaluation

To evaluate ConvMixer model performance on ImageNet2012 with a single GPU, run the following script using command line:

sh run_eval.sh

or

CUDA_VISIBLE_DEVICES=0 \
python main_single_gpu.py \
    -cfg=./configs/convmixer_768_32.yaml \
    -dataset=imagenet2012 \
    -batch_size=16 \
    -data_path=/path/to/dataset/imagenet/val \
    -eval \
    -pretrained=/path/to/pretrained/model/convmixer_768_32  # .pdparams is NOT needed
Run evaluation using multi-GPUs: 
sh run_eval_multi.sh

or

CUDA_VISIBLE_DEVICES=0,1,2,3 \
python main_multi_gpu.py \
    -cfg=./configs/convmixer_768_32.yaml \
    -dataset=imagenet2012 \
    -batch_size=16 \
    -data_path=/path/to/dataset/imagenet/val \
    -eval \
    -pretrained=/path/to/pretrained/model/convmixer_768_32  # .pdparams is NOT needed

Training

To train the ConvMixer Transformer model on ImageNet2012 with single GPU, run the following script using command line:

sh run_train.sh

or

CUDA_VISIBLE_DEVICES=0 \
python main_single_gpu.py \
  -cfg=./configs/convmixer_768_32.yaml \
  -dataset=imagenet2012 \
  -batch_size=16 \
  -data_path=/path/to/dataset/imagenet/train \
Run training using multi-GPUs: 
sh run_train_multi.sh

or

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
python main_multi_gpu.py \
    -cfg=./configs/convmixer_768_32.yaml \
    -dataset=imagenet2012 \
    -batch_size=32 \
    -data_path=/path/to/dataset/imagenet/train \

Visualization Attention Map

(coming soon)