x-yy0

Results 9 comments of x-yy0

AssertionError: Results do not correspond to current coco set

+1

YOLOv6n RuntimeError: CUDA error: device-side assert triggered

have you solved the problem?

Ubuntu18编译卡壳， c++: internal compiler error: Segmentation fault (program cc1plus)

> linux查看修改线程默认栈空间大小（ulimit -s)，默认空间1024=1M，过小，改为10240=10M，可以编译。 查看ulimit -s > > 1. 修改配置文件 > sudo vim /etc/security/limits.conf > > nvidia hard stack 10240 nvidia soft stack 10240 ubuntu hard stack 10240 ubuntu soft stack...

ModuleNotFoundError: No module named 'models.yolo' #6326

Is there a solution?

ModuleNotFoundError: No module named 'models.yolo' #6326

> Search before asking I have searched the YOLOv5 issues and found no similar bug report. YOLOv5 Component No response > > Bug > > ``` > Namespace(agnostic_nms=False, augment=False, cfg='/content/drive/MyDrive/神様/Augmentedstartups/yolor/cfg/yolor_w6.cfg',...

关于plot_images的索引超出范围的问题

I have the same problem. Did you figure it out?

RuntimeError: cuDNN error: CUDNN_STATUS_INTERNAL_ERROR

Removing the ‘-o’ option will solve this problem.

../aten/src/ATen/native/cuda/Loss.cu:92: operator(): block: [37,0,0], thread: [96,0,0] Assertion `input_val >= zero && input_val <= one` failed.

> Thanks for your fast reply. > > It looks like it's training correctly after changing the fp16 setting to false again. Could that be the cause? First 30 epochs...

In training it's comming a RuntimeError by evolution[Bug]

> Hello, I did a work around to solve this issue, by modifying the file multiclass_nms_rotated.py by : replacing : labels = torch.arange(num_classes, dtype=torch.long) with : labels = torch.arange(num_classes, dtype=torch.long).to(scores.device)...