ShuffleNetV2_x2_0 is a lightweight convolutional neural network introduced in the paper "ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design" by Megvii (Face++). It is designed to achieve high performance with low computational cost, making it ideal for mobile and embedded devices.The x2_0 in its name indicates a width multiplier of 2.0, meaning the model has twice as many channels compared to the baseline ShuffleNetV2_x1_0. It employs Channel Shuffle to enable efficient information exchange between grouped convolutions, addressing the limitations of group convolutions. The core building block, the ShuffleNetV2 block, features a split-merge design and channel shuffle mechanism, ensuring both high efficiency and accuracy.
Iluvatar GPU | IXUCA SDK |
---|---|
MR-V100 | 4.2.0 |
Pretrained model: https://download.pytorch.org/models/shufflenetv2_x2_0-8be3c8ee.pth
Dataset: https://www.image-net.org/download.php to download the validation dataset.
pip3 install -r requirements.txt
python3 export.py --weight shufflenetv2_x2_0-8be3c8ee.pth --output shufflenetv2_x2_0.onnx
export DATASETS_DIR=/Path/to/imagenet_val/
# Accuracy
bash scripts/infer_shufflenetv2_x2_0_fp16_accuracy.sh
# Performance
bash scripts/infer_shufflenetv2_x2_0_fp16_performance.sh
Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) |
---|---|---|---|---|---|
ShuffleNetV2_x2_0 | 32 | FP16 | 5439.098 | 76.176 | 92.860 |
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。