test/configs/repvgg

• RepVGG
• • Introduction
  • Results
  • • • Notes
  • Quick Start
  • • Preparation
    • • Installation
      • Dataset Preparation
    • Training
    • Validation
    • Deployment
  • References

RepVGG

RepVGG: Making VGG-style ConvNets Great Again

Introduction

The key idea of Repvgg is that by using re-parameterization, the model architecture could be trained in multi-branch but validated in single branch.
Figure 1 shows the basic model architecture of Repvgg. By utilizing different values for a and b, we could get various repvgg models.
Repvgg could achieve better model performance with smaller model parameters on ImageNet-1K dataset compared with previous methods.[1]

Figure 1. Architecture of Repvgg [1]

Results

Our reproduced model performance on ImageNet-1K is reported as follows.

Model	Context	Top-1 (%)	Top-5 (%)	Params (M)	Recipe	Download
repvgg_a0	D910x8-G	72.19	90.75	9.13	yaml	weights
repvgg_a1	D910x8-G	74.19	91.89	14.12	yaml	weights
repvgg_a2	D910x8-G	76.63	93.42	28.25	yaml	weights
repvgg_b0	D910x8-G	74.99	92.40	15.85	yaml	weights
repvgg_b1	D910x8-G	78.81	94.37	57.48	yaml	weights
repvgg_b2	D910x64-G	79.29	94.66	89.11	yaml	weights
repvgg_b3	D910x64-G	80.46	95.34	123.19	yaml	weights
repvgg_b1g2	D910x8-G	78.03	94.09	45.85	yaml	weights
repvgg_b1g4	D910x8-G	77.64	94.03	40.03	yaml	weights
repvgg_b2g4	D910x8-G	78.8	94.36	61.84	yaml	weights

Notes

• Context: Training context denoted as {device}x{pieces}-{MS mode}, where mindspore mode can be G - graph mode or F - pynative mode with ms function. For example, D910x8-G is for training on 8 pieces of Ascend 910 NPU using graph mode.
• Top-1 and Top-5: Accuracy reported on the validation set of ImageNet-1K.

Quick Start

Preparation

Installation

Please refer to the installation instruction in MindCV.

Dataset Preparation

Please download the ImageNet-1K dataset for model training and validation.

Training

• Distributed Training

It is easy to reproduce the reported results with the pre-defined training recipe. For distributed training on multiple Ascend 910 devices, please run

# distributed training on multiple GPU/Ascend devices
mpirun -n 8 python train.py --config configs/repvgg/repvgg_a1_ascend.yaml --data_dir /path/to/imagenet

If the script is executed by the root user, the --allow-run-as-root parameter must be added to mpirun.

Similarly, you can train the model on multiple GPU devices with the above mpirun command.

For detailed illustration of all hyper-parameters, please refer to config.py.

Note: As the global batch size (batch_size x num_devices) is an important hyper-parameter, it is recommended to keep the global batch size unchanged for reproduction or adjust the learning rate linearly to a new global batch size.

• Standalone Training

If you want to train or finetune the model on a smaller dataset without distributed training, please run:

# standalone training on a CPU/GPU/Ascend device
python train.py --config configs/repvgg/repvgg_a1_ascend.yaml --data_dir /path/to/dataset --distribute False

Validation

To validate the accuracy of the trained model, you can use validate.py and parse the checkpoint path with --ckpt_path.

python validate.py -c configs/repvgg/repvgg_a1_ascend.yaml --data_dir /path/to/imagenet --ckpt_path /path/to/ckpt

Deployment

Please refer to the deployment tutorial in MindCV.

References

[1] Ding X, Zhang X, Ma N, et al. Repvgg: Making vgg-style convnets great again[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021: 13733-13742.