yuqilol

Results 29 comments of yuqilol

RuntimeError: CUDA error: an illegal memory access was encountered terminate called after throwing an instance of 'c10::Error'

超出显卡内存了吧，workers调小一点

人物动作变化快就会闪烁，怎么优化

滤波

how to enhance the model‘s performence when running on cpu ？

openvino加速cpu最快，能有个3-5倍

Inference code is not running on my GPU

如果你是在用onnx跑的，那就注意你的模型是cpu版本还是gpu版本的

Hello, how do I change the dimensions of the output structure,

Hello, I used your structure, but when I used summary to view the structure, the following error occurred. I guess it was a mistake in my yaml file. The error...

Hello, how do I change the dimensions of the output structure,

![1705484883190(1)](https://github.com/ultralytics/yolov5/assets/52739016/60fe98d2-47a1-4ccd-ad13-aa8063160cc0) It seems that there is no problem with indentation of my yaml file, but the following error problem occurs when I train, I don't know why. train: weights=yolov5s.pt, cfg=models\yolov5s.yaml,...

Hello, how do I change the dimensions of the output structure,

I printed the structure of the model and found nothing in reshape, is that normal？ ![Uploading 1705485197167(1).jpg…]()

Hello, how do I change the dimensions of the output structure,

DetectionModel( (model): Sequential( (0): Conv( (conv): Conv2d(3, 32, kernel_size=(6, 6), stride=(2, 2), padding=(2, 2)) (act): SiLU(inplace=True) ) (1): Conv( (conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)) (act): SiLU(inplace=True)...

Hello, how do I change the dimensions of the output structure,

Thanks for your reply, I found that there was no tpu on our device, so the task of changing the structure was cancelled, but there was npu on the device,...

Hello, how do I change the dimensions of the output structure,

Thank you for your answer, I have solved the problem. The first solution is to convert yolo's export.py into onnx, and then convert onnx into tflite. During this process, I...