代码拉取完成,页面将自动刷新
The YOLOv5 architecture is designed for efficient and accurate object detection tasks in real-time scenarios. It employs a single convolutional neural network to simultaneously predict bounding boxes and class probabilities for multiple objects within an image.
yum install mesa-libGL
pip3 install tqdm
pip3 install onnx
pip3 install onnxsim
pip3 install ultralytics
pip3 install pycocotools
Pretrained model: https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5m.pt
Dataset: http://images.cocodataset.org/zips/val2017.zip to download the validation dataset.
python3 export.py --weight yolov5m.pt --output yolov5m.onnx
# Use onnxsim optimize onnx model
onnxsim yolov5m.onnx yolov5m_opt.onnx
export DATASETS_DIR=/Path/to/coco/
# Accuracy
bash scripts/infer_yolov5_fp16_accuracy.sh
# Performance
bash scripts/infer_yolov5_fp16_performance.sh
# Accuracy
bash scripts/infer_yolov5_int8_accuracy.sh
# Performance
bash scripts/infer_yolov5_int8_performance.sh
Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 |
---|---|---|---|---|---|
YOLOv5m | 32 | FP16 | 533.53 | 0.639 | 0.451 |
YOLOv5m | 32 | INT8 | 969.53 | 0.624 | 0.428 |
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。