代码拉取完成,页面将自动刷新
ShuffleNet V2_x1_0 is an efficient convolutional neural network (CNN) architecture that emphasizes a balance between computational efficiency and accuracy, particularly suited for deployment on mobile and embedded devices. The model refines the ShuffleNet series by introducing structural innovations that enhance feature reuse and reduce redundancy, all while maintaining simplicity and performance.
pip3 install onnx
pip3 install tqdm
Pretrained model: https://download.pytorch.org/models/shufflenetv2_x1-5666bf0f80.pth
Dataset: https://www.image-net.org/download.php to download the validation dataset.
python3 export.py --weight shufflenetv2_x1-5666bf0f80.pth --output shufflenetv2_x1_0.onnx
export DATASETS_DIR=/Path/to/imagenet_val/
# Accuracy
bash scripts/infer_shufflenetv2_x1_0_fp16_accuracy.sh
# Performance
bash scripts/infer_shufflenetv2_x1_0_fp16_performance.sh
Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) |
---|---|---|---|---|---|
ShuffleNetV2_x1_0 | 32 | FP16 | 8232.980 | 69.308 | 88.302 |
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。