代码拉取完成,页面将自动刷新
The ResNeXt101_64x4d is a deep learning model based on the deep residual network architecture, which enhances performance and efficiency through the use of grouped convolutions. With a depth of 101 layers and 64 filter groups, it is particularly suited for complex image recognition tasks. While maintaining excellent accuracy, it can adapt to various input sizes
Iluvatar GPU | IXUCA SDK |
---|---|
MR-V100 | 4.2.0 |
Pretrained model: https://download.pytorch.org/models/resnext101_64x4d-173b62eb.pth
Dataset: https://www.image-net.org/download.php to download the validation dataset.
pip3 install -r requirements.txt
python3 export.py --weight resnext101_64x4d-173b62eb.pth --output resnext101_64x4d.onnx
export DATASETS_DIR=/Path/to/imagenet_val/
# Accuracy
bash scripts/infer_resnext101_64x4d_fp16_accuracy.sh
# Performance
bash scripts/infer_resnext101_64x4d_fp16_performance.sh
Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) |
---|---|---|---|---|---|
ResNext101_64x4d | 32 | FP16 | 663.13 | 82.953 | 96.221 |
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。