VGG13 is a classic deep convolutional neural network model consisting of 13 convolutional layers and multiple pooling layers. It utilizes 3×3 small convolution kernels to extract image features and completes classification through fully connected layers. Known for its simple structure and high performance, it is well-suited for image classification tasks but requires significant computational resources due to its large parameter size.
| 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.pytorch.org/models/vgg13-19584684.pth
Dataset: https://www.image-net.org/download.php to download the validation dataset.
pip3 install -r ../../igie_common/requirements.txtpython3 ../../igie_common/export.py --model-name vgg13 --weight vgg13-19584684.pth --output vgg13.onnxexport DATASETS_DIR=/Path/to/imagenet_val/
export RUN_DIR=../../igie_common/# Accuracy
bash scripts/infer_vgg13_fp16_accuracy.sh
# Performance
bash scripts/infer_vgg13_fp16_performance.sh| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) |
|---|---|---|---|---|---|
| VGG13 | 32 | FP16 | 2598.51 | 69.894 | 89.233 |