代码拉取完成，页面将自动刷新
YOLOv4 employs a two-step process, involving regression for bounding box positioning and classification for object categorization. it amalgamates past YOLO family research contributions with novel features like WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, DropBlock regularization, and CIoU loss.
# Install libGL
## CentOS
yum install -y mesa-libGL
## Ubuntu
apt install -y libgl1-mesa-dev
pip3 install tqdm
pip3 install onnx
pip3 install onnxsim
pip3 install pycocotools
Pretrained cfg: https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov4.cfg Pretrained model: https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v3_optimal/yolov4.weights
Dataset: http://images.cocodataset.org/zips/val2017.zip to download the validation dataset.
# clone yolov4
git clone https://github.com/Tianxiaomo/pytorch-YOLOv4.git yolov4
# export onnx model
python3 export.py --cfg yolov4.cfg --weight yolov4.weights --output yolov4.onnx
# Use onnxsim optimize onnx model
onnxsim yolov4.onnx yolov4_opt.onnx
export DATASETS_DIR=/Path/to/coco/
# Accuracy
bash scripts/infer_yolov4_fp16_accuracy.sh
# Performance
bash scripts/infer_yolov4_fp16_performance.sh
# Accuracy
bash scripts/infer_yolov4_int8_accuracy.sh
# Performance
bash scripts/infer_yolov4_int8_performance.sh
| Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 |
|---|---|---|---|---|---|
| yolov4 | 32 | FP16 | 285.218 | 0.741 | 0.506 |
| yolov4 | 32 | INT8 | 413.320 | 0.721 | 0.463 |
DarkNet: https://github.com/AlexeyAB/darknet Pytorch-YOLOv4: https://github.com/Tianxiaomo/pytorch-YOLOv4
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。
马建仓 AI 助手
