10 Star 20 Fork 12

DeepSpark/DeepSparkInference

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
克隆/下载
贡献代码
同步代码
取消
提示: 由于 Git 不支持空文件夾,创建文件夹后会生成空的 .keep 文件
Loading...
README

ResNext101_64x4d (IGIE)

Model Description

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

Supported Environments

Iluvatar GPU IXUCA SDK
MR-V100 4.2.0

Model Preparation

Prepare Resources

Pretrained model: https://download.pytorch.org/models/resnext101_64x4d-173b62eb.pth

Dataset: https://www.image-net.org/download.php to download the validation dataset.

Install Dependencies

pip3 install -r requirements.txt

Model Conversion

python3 export.py --weight resnext101_64x4d-173b62eb.pth --output resnext101_64x4d.onnx

Model Inference

export DATASETS_DIR=/Path/to/imagenet_val/

FP16

# Accuracy
bash scripts/infer_resnext101_64x4d_fp16_accuracy.sh
# Performance
bash scripts/infer_resnext101_64x4d_fp16_performance.sh

Model Results

Model BatchSize Precision FPS Top-1(%) Top-5(%)
ResNext101_64x4d 32 FP16 663.13 82.953 96.221
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
Python
1
https://gitee.com/deep-spark/deepsparkinference.git
git@gitee.com:deep-spark/deepsparkinference.git
deep-spark
deepsparkinference
DeepSparkInference
master

搜索帮助

371d5123 14472233 46e8bd33 14472233