Yep, will try. I've seen artifacts when interpolating high resolution video with Normal Data Precision, and the artifacts go away when bumping Data Precision up, so I have been using Data Precision as high as my VRAM will allow.
I'll stop that. :)
Ran into the following error during interpolation:
Exception ignored in thread started by: <function queue_file_save at 0x000001D9FF244C10> Traceback (most recent call last): File "my_DAIN_class.py", line 754, in queue_file_save File "my_DAIN_class.py", line 665, in PipeFrame BrokenPipeError: [Errno 32] Broken pipe
Logs prior to the error:
FPS: 24000/1001 FPS Eval: 23.976023976023978 Using Benchmark: True
Batch Size: -1 Input FPS: 23.976023976023978 Use all GPUS: False Scale: 1.0 Render Mode: 0 Interpolations: 2X Use Smooth: 0 Use Alpha: 0 Use YUV: 1 Encode: libsvtav1 Device: cuda:0 Using Half-Precision: False Resolution: 3840x2160 Using Model: 3_1 Selected auto batch size, testing a good batch size. Setting new batch size to 1 Resolution: 3840x2160 RunTime: 2453.803000 Total Frames: 58832 0%| | 2/58832 [00:04<43:53:18, 2.69s/it, file=File 0]------------------------------------------- SVT [version]: SVT-AV1 Encoder Lib v0.8.6-72-gec7ac87f SVT [build] : GCC 10.2.0 64 bit LIB Build date: Feb 7 2021 13:13:12 ------------------------------------------- Number of logical cores available: 24 Number of PPCS 53 [asm level on system : up to avx2] [asm level selected : up to avx2] ------------------------------------------- SVT [config]: Main Profile Tier (auto) Level (auto) SVT [config]: Preset : 7 SVT [config]: EncoderBitDepth / EncoderColorFormat / CompressedTenBitFormat : 10 / 1 / 0 SVT [config]: SourceWidth / SourceHeight : 3840 / 2160 SVT [config]: Fps_Numerator / Fps_Denominator / Gop Size / IntraRefreshType : 48000 / 1001 / 49 / 2 SVT [config]: HierarchicalLevels / PredStructure : 4 / 2 SVT [config]: BRC Mode / QP / LookaheadDistance / SceneChange : CQP / 50 / 0 / 0 ------------------------------------------- 54%|████████▌ | 31489/58832 [3:39:56<2:49:33, 2.69it/s, file=File 31487]
Error when starting interpolation:
Using Benchmark: True Batch Size: -1 Input FPS: 23.976023976023978 Use all GPUS: False Scale: 1.0 Render Mode: 0 Interpolations: 4X Use Smooth: 0 Use Alpha: 0 Use YUV: 0 Encode: libsvtav1 Device: cuda:0 Using Half-Precision: False Resolution: 3840x2160 Loading Pre-train Using Model: rl_regular2 Traceback (most recent call last): File "my_design.py", line 86, in run File "my_DAIN_class.py", line 1436, in RenderVideo File "my_DAIN_class.py", line 1495, in RenderVideoWithModel File "my_DAIN_class.py", line 143, in make_inference File "model\flow_slow2.py", line 442, in inference File "torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "model\flow_slow2.py", line 165, in forward File "torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "torch\nn\modules\container.py", line 139, in forward input = module(input) File "torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "torch\nn\modules\container.py", line 139, in forward input = module(input) File "torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "torch\nn\modules\conv.py", line 443, in forward return self._conv_forward(input, self.weight, self.bias) File "torch\nn\modules\conv.py", line 439, in _conv_forward return F.conv2d(input, weight, bias, self.stride, RuntimeError: Input type (torch.cuda.DoubleTensor) and weight type (torch.cuda.FloatTensor) should be the same QObject::setParent: Cannot set parent, new parent is in a different thread