python video_demo.py --video 1.avi has no results

[lonngxiang]

File "video_demo.py", line 111, in model(get_test_input(inp_dim, CUDA), CUDA) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\Desktop\imageai\pytorch-yolo-v3-master\darknet.py", line 346, in forward x = outputs[i-1] + outputs[i+from_] RuntimeError: CUDA out of memory. Tried to allocate 1.38 MiB (GPU 0; 1024.00 MiB total capacity; 520.90 MiB already allocated; 496.00 KiB free; 3.72 MiB cached)

Traceback (most recent call last): File "video_demo_half.py", line 112, in model(get_test_input(inp_dim, CUDA), CUDA) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\Desktop\imageai\pytorch-yolo-v3-master\darknet.py", line 319, in forward x = self.module_listi File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\container.py", line 92, in forward input = module(input) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\conv.py", line 320, in forward self.padding, self.dilation, self.groups) RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the same

[Paumila]

Hello,

I have the same error on both cases.

The first problem, I think you can solve using less --reso (resolution)

For the secon one, I have the same and I don't know how to solve it.

If someone can help to solve this issue?

Traceback (most recent call last): File "video_demo_half.py", line 112, in model(get_test_input(inp_dim, CUDA), CUDA) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\Desktop\imageai\pytorch-yolo-v3-master\darknet.py", line 319, in forward x = self.module_listi File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\container.py", line 92, in forward input = module(input) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\conv.py", line 320, in forward self.padding, self.dilation, self.groups) RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the same

[hyhyni]

File "video_demo.py", line 111, in model(get_test_input(inp_dim, CUDA), CUDA) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\Desktop\imageai\pytorch-yolo-v3-master\darknet.py", line 346, in forward x = outputs[i-1] + outputs[i+from_] RuntimeError: CUDA out of memory. Tried to allocate 1.38 MiB (GPU 0; 1024.00 MiB total capacity; 520.90 MiB already allocated; 496.00 KiB free; 3.72 MiB cached)

Traceback (most recent call last): File "video_demo_half.py", line 112, in model(get_test_input(inp_dim, CUDA), CUDA) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\Desktop\imageai\pytorch-yolo-v3-master\darknet.py", line 319, in forward x = self.module_listi File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\container.py", line 92, in forward input = module(input) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\conv.py", line 320, in forward self.padding, self.dilation, self.groups) RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the same

Hi, Do you have solve this problem?

[hyhyni]

File "video_demo.py", line 111, in model(get_test_input(inp_dim, CUDA), CUDA) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\Desktop\imageai\pytorch-yolo-v3-master\darknet.py", line 346, in forward x = outputs[i-1] + outputs[i+from_] RuntimeError: CUDA out of memory. Tried to allocate 1.38 MiB (GPU 0; 1024.00 MiB total capacity; 520.90 MiB already allocated; 496.00 KiB free; 3.72 MiB cached)

Traceback (most recent call last): File "video_demo_half.py", line 112, in model(get_test_input(inp_dim, CUDA), CUDA) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\Desktop\imageai\pytorch-yolo-v3-master\darknet.py", line 319, in forward x = self.module_listi File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\container.py", line 92, in forward input = module(input) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Lavector\python3\lib\site-packages\torch\nn\modules\conv.py", line 320, in forward self.padding, self.dilation, self.groups) RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the same

Hi, Do you have solve this problem?