ConvNeXt-S is a small-sized model in the ConvNeXt family, designed to balance performance and computational complexity. With 50.22M parameters and 8.69G FLOPs, it achieves 83.13% Top-1 accuracy on ImageNet-1k. Modernized from traditional ConvNets, ConvNeXt-S incorporates features such as large convolutional kernels (7x7), LayerNorm, and GELU activations, making it highly efficient and scalable.
| 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
Pretrained model: https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_3rdparty_32xb128_in1k_20220124-d39b5192.pth
Dataset: https://www.image-net.org/download.php to download the validation dataset.
# Install libGL
## CentOS
yum install -y mesa-libGL
## Ubuntu
apt install -y libgl1-mesa-glx
pip3 install -r ../../igie_common/requirements.txt
pip3 install --no-build-isolation mmcv==1.5.3 mmcls==0.24.0# git clone mmpretrain
git clone -b v0.24.0 https://github.com/open-mmlab/mmpretrain.git
# export onnx model
python3 ../../igie_common/export_mmcls.py --cfg mmpretrain/configs/convnext/convnext-small_32xb128_in1k.py --weight convnext-small_3rdparty_32xb128_in1k_20220124-d39b5192.pth --output convnext_s.onnx
# Use onnxsim optimize onnx model
onnxsim convnext_s.onnx convnext_s_opt.onnx
export DATASETS_DIR=/Path/to/imagenet_val/
export RUN_DIR=../../igie_common/# Accuracy
bash scripts/infer_convnext_s_fp16_accuracy.sh
# Performance
bash scripts/infer_convnext_s_fp16_performance.sh| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) |
|---|---|---|---|---|---|
| ConvNext-S | 32 | FP16 | 728.32 | 82.786 | 96.415 |