ixrt

RepVGG (ixRT)

Model Description

REPVGG is a family of convolutional neural network (CNN) architectures designed for image classification tasks. It was developed by researchers at the University of Oxford and introduced in their paper titled "REPVGG: Making VGG-style ConvNets Great Again" in 2021.

Supported Environments

GPU	IXUCA SDK	Release	Branch
MR-V100	4.4.0	26.03	release/26.03
MR-V100	4.3.0	25.12	release/25.12

Note: 请切换到与您的 SDK 版本对应的 Release 分支进行测试。请勿直接在 master 分支上运行测试，因为 master 分支可能包含与您的本地 SDK 版本不兼容的最新更改。

切换分支命令示例：git checkout release/26.03

Model Preparation

Prepare Resources

Dataset: https://www.image-net.org/download.php to download the validation dataset.

Install Dependencies

# Install libGL
## CentOS
yum install -y mesa-libGL
## Ubuntu
apt install -y libgl1-mesa-glx

pip3 install -r ../../ixrt_common/requirements.txt
pip3 install --no-build-isolation mmcv==1.5.3 mmcls==0.24.0

Model Conversion

mkdir checkpoints 
git clone -b v0.24.0 https://github.com/open-mmlab/mmpretrain.git

python3 ../../ixrt_common/export_mmcls.py   \
    --cfg ./mmpretrain/configs/repvgg/repvgg-A0_4xb64-coslr-120e_in1k.py \
    --weight repvgg-A0_3rdparty_4xb64-coslr-120e_in1k_20210909-883ab98c.pth \
    --output repvgg_A0.onnx

onnxsim repvgg_A0.onnx checkpoints/repvgg_A0.onnx

Model Inference

export PROJ_DIR=./
export DATASETS_DIR=/path/to/imagenet_val/
export CHECKPOINTS_DIR=./checkpoints
export RUN_DIR=../../ixrt_common/
export CONFIG_DIR=../../ixrt_common/config/REPVGG_CONFIG

FP16

# Accuracy
bash scripts/infer_repvgg_fp16_accuracy.sh
# Performance
bash scripts/infer_repvgg_fp16_performance.sh

Model Results

Model	BatchSize	Precision	FPS	Top-1(%)	Top-5(%)
RepVGG	32	FP16	5725.37	72.41	90.49