Hi,
How can I fix this error?
Thanks!
Changed the video to a mp4 and it started working but now I get this:
['E:/testfps/Take_30fps.mp4']
FPS: 30000/1001
FPS Eval: 29.97002997002997
G:/60fps/Take_30fps
Using Benchmark: True
Batch Size: -1
Input FPS: 29.97002997002997
Use all GPUS: False
Scale: 1.0
Render Mode: 0
Interpolations: 2X
Use Smooth: 0
Use Alpha: 0
Use YUV: 0
Encode: libx264
Using Half-Precision: True
Loading Data
Using Model: 3_1
Selected auto batch size, testing a good batch size.
Resolution: 7680x3840
Setting new batch size to 1
Resolution: 7680x3840
RunTime: 95.317333
Total Frames: 2857
0%| | 4/2857 [00:02<26:36, 1.79it/s, file=File 2]Exception ignored in thread started by: <function queue_model at 0x000002302F3E9940>
Traceback (most recent call last):
File "my_DAIN_class.py", line 407, in queue_model
File "my_DAIN_class.py", line 135, in make_inference
File "model\RIFE_HDv3.py", line 391, in inference
File "model\RIFE_HDv3.py", line 298, in predict
File "torch\nn\modules\module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
RuntimeError: The following operation failed in the TorchScript interpreter.
Traceback of TorchScript, serialized code (most recent call last):
File "code/__torch__/model/RIFE_HDv3.py", line 20, in forward
flow0 = torch.mul(_1, 0.5)
f1 = __torch__.model.warplayer.warp(x1, flow0, )
x2 = (self.conv2).forward(x1, )
~~~~~~~~~~~~~~~~~~~ <--- HERE
_2 = _0(flow0, None, 0.5, "bilinear", False, True, )
flow1 = torch.mul(_2, 0.5)
File "code/__torch__/model/RIFE_HDv3/___torch_mangle_27.py", line 11, in forward
x: Tensor) -> Tensor:
x0 = (self.conv1).forward(x, )
return (self.conv2).forward(x0, )
~~~~~~~~~~~~~~~~~~~ <--- HERE
File "code/__torch__/torch/nn/modules/container/___torch_mangle_26.py", line 12, in forward
_0 = getattr(self, "0")
_1 = getattr(self, "1")
input0 = (_0).forward(input, )
~~~~~~~~~~~ <--- HERE
return (_1).forward(input0, )
def __len__(self: __torch__.torch.nn.modules.container.___torch_mangle_26.Sequential) -> int:
File "code/__torch__/torch/nn/modules/conv/___torch_mangle_25.py", line 21, in forward
def forward(self: __torch__.torch.nn.modules.conv.___torch_mangle_25.Conv2d,
input: Tensor) -> Tensor:
_0 = (self)._conv_forward(input, self.weight, self.bias, )
~~~~~~~~~~~~~~~~~~~ <--- HERE
return _0
def _conv_forward(self: __torch__.torch.nn.modules.conv.___torch_mangle_25.Conv2d,
File "code/__torch__/torch/nn/modules/conv/___torch_mangle_25.py", line 27, in _conv_forward
weight: Tensor,
bias: Optional[Tensor]) -> Tensor:
_1 = torch.conv2d(input, weight, bias, [1, 1], [1, 1], [1, 1])
~~~~~~~~~~~~ <--- HERE
return _1
Traceback of TorchScript, original code (most recent call last):
File "C:\Users\Gabriel\Downloads\torch19\lib\site-packages\torch\nn\modules\container.py", line 139, in forward
def forward(self, input):
for module in self:
input = module(input)
~~~~~~ <--- HERE
return input
File "C:\Users\Gabriel\Downloads\torch19\lib\site-packages\torch\nn\modules\conv.py", line 443, in forward
def forward(self, input: Tensor) -> Tensor:
return self._conv_forward(input, self.weight, self.bias)
~~~~~~~~~~~~~~~~~~ <--- HERE
File "C:\Users\Gabriel\Downloads\torch19\lib\site-packages\torch\nn\modules\conv.py", line 439, in _conv_forward
weight, bias, self.stride,
_pair(0), self.dilation, self.groups)
return F.conv2d(input, weight, bias, self.stride,
~~~~~~~~ <--- HERE
self.padding, self.dilation, self.groups)
RuntimeError: CUDA out of memory. Tried to allocate 7.91 GiB (GPU 0; 24.00 GiB total capacity; 2.66 GiB already allocated; 18.15 GiB free; 3.82 GiB reserved in total by PyTorch)
RuntimeError: CUDA out of memory. Tried to allocate 7.91 GiB (GPU 0; 24.00 GiB total capacity; 2.66 GiB already allocated; 18.15 GiB free; 3.82 GiB reserved in total by PyTorch)
This is the real problem. Your computer is running out of memory, a 7680x3840 input is to big of a resolution for your computer. You can try to set Inner Scale to 0.25 (it will generate worse results) and turn on "Try to save memory" at the botton to improve memory a little, but at such high resolution, it might still create this problem.