mindyolo
mindyolo copied to clipboard
MindSpore YOLO series toolbox and benchmark
**If this is your first time, please read our contributor guidelines:** https://gitee.com/mindspore/mindspore/blob/master/CONTRIBUTING.md **Is your feature request related to a problem? Please describe.** A clear and concise description of what the...
**If this is your first time, please read our contributor guidelines:** https://gitee.com/mindspore/mindspore/blob/master/CONTRIBUTING.md **Is your feature request related to a problem? Please describe.** A clear and concise description of what the...
``` (MindSpore) [ma-user mindyolo]$python demo/predict.py --config ./configs/yolov3/yolov3.yaml --weight=/home/ma-user/yolov7-x_300e_mAP524-e2f58741.ckpt --image_path /home/ma-user/work/dog.jpg Traceback (most recent call last): File "demo/predict.py", line 335, in infer(args) File "demo/predict.py", line 274, in infer set_default_infer(args) File "demo/predict.py",...
The first epoch will be compiled for the graph, which may take a long time; You can come back later
  在modelArts上使用yolov5训练模型,使用CPU,载入时把32G内存都占满了,后面就直接报错
 推理v5时没有出现这个错误,但是v8时出现了,我调式后输出pred预测内容,v8的明显就是不正确的,coco索引甚至达到了6000: 
运行命令后 python deploy/predict.py --model_type MindIR --model_path ./yolov5s.mindir --config ./configs/yolov5/yolov5s.yaml --image_path ~/001.jpg 大概运行一分钟出现Killed 再过几秒出现错误提示如下  runs_infer出现2024.......时间文件夹,其中有cfg.yaml文件和logs文件夹,logs文件夹中有MindYOLO_2024.txt文件,但txt文件中没有任何内容 环境Mindspore=2.2.14,Mindyolo=0.3.0,硬件香橙派Ascend310
芯片310b4,mindspore2.2.14,cann7.0.0,python3.9.2 问题如下: 执行代码: python ./deploy/export.py --config ./configs/yolov8/yolov8n.yaml --weight yolov8-n_500e_mAP372-cc07f5bd.ckpt --per_batch_size 1 --file_format ONNX --device_target CPU  网上查资料说是:脚本在导出过程中遇到了一个错误,提示 FillV2 操作符不支持导出。这通常是由于模型中使用了某些 MindSpore 特有的操作符,而这些操作符在 ONNX 中没有直接对应的实现。 如何解决此问题(v5没问题)
型号:香橙派aipro 芯片310b4 cann7.0.0 mindspore 2.2.14 mindspore lite 2.2.14 python3.9.2 根据readme进行环境配置  现在进行完用cpu来模型转换(因为用Acend只支持910),成功转换为yolov5n.mindir  在运行推理时出现错误: python deploy/predict.py --model_type Lite --model_path ./yolov5n.mindir --config ./configs/yolov5/yolov5n.yaml --image_path ./coco/image/val2017/image.jpg ![fd9f51884a1d4b60807a6c2308130bc7 20240724135130...