GTX 1650 error running yolov3

Hello, I’am using Intel UHD 630 or Gigabyte GTX1050TI 4G GDDR5 1 Fan GV-N105TD5-4GD works well with yolov3 pytorch.

But I replace Asus DUAL-GTX1650-O4G 2 Fans and I’m stucking with errors below. Please help! Thanks!

Traceback (most recent call last):
File “video_demo.py”, line 111, in
model(get_test_input(inp_dim, CUDA), CUDA)
File “C:\Users\PC\Anaconda3\envs\yolov3\lib\site-packages\torch\nn\modules\module.py”, line 477, in call
result = self.forward(*input, **kwargs)
File “C:\yolo\pytorch-yolo-v3\darknet.py”, line 319, in forward
x = self.module_listi
File “C:\Users\PC\Anaconda3\envs\yolov3\lib\site-packages\torch\nn\modules\module.py”, line 477, in call
result = self.forward(*input, **kwargs)
File “C:\Users\PC\Anaconda3\envs\yolov3\lib\site-packages\torch\nn\modules\container.py”, line 91, in forward
input = module(input)
File “C:\Users\PC\Anaconda3\envs\yolov3\lib\site-packages\torch\nn\modules\module.py”, line 477, in call
result = self.forward(*input, **kwargs)
File “C:\Users\PC\Anaconda3\envs\yolov3\lib\site-packages\torch\nn\modules\conv.py”, line 301, in forward
self.padding, self.dilation, self.groups)
RuntimeError: CuDNN error: CUDNN_STATUS_SUCCESS