Vadim2S
Vadim2S
Unfortunate, accelerator='ddp' is not stable. Accelerator='None' is OK. File "/home/assem-vc/synthesizer_trainer.py", line 85, in main(args) File "/home/assem-vc/synthesizer_trainer.py", line 64, in main trainer.fit(model) File "/usr/local/lib/python3.8/dist-packages/pytorch_lightning/trainer/trainer.py", line 439, in fit results = self.accelerator_backend.train()...
I am do some test and found another prerequisite for error: Windows Case 1: Pure Linux or WSL: jpeg = jpegio.read("/mnt/c/!4/bbb/example.jpg") #english only jpeg = jpegio.read("/mnt/c/!4/ббб/example.jpg") #not only english All...
Same error, pip3 install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./ Ubuntu 20.04, Cuda 11.1 P.S. Old Apex june 30 version 0.1 - OK.
It is more complicated. "Full" (human body) image required usage of StyleGAN_Human model what has proportion 2:1 instead 1:1 of face FFHQ model. Moreover StyleGAN_Human has num_ws=16 instead FFHQ num_ws=18....
Sorry. I am clearly missed something. Can you clarify please. What I am must do for getting result video where man from "cnn.mp4" video speak with voice from "english_m.mp4" video?
Small explanation. There ugly antipattern hard-coded path strings in torch_utils/custom_ops.py/_find_compiler_bindir() like `` 'C:/Program Files*/Microsoft Visual Studio/*/Professional/VC/Tools/MSVC/*/bin/Hostx64/x64', `` and of course this do not work if you use another Visual Studio...
About using GCC/CLANG instead MSVC. I am not check it but try change torch_utils/custom_ops.py/_find_compiler_bindir() function. This quite strightforward and simple. Just provide path to you compiler.
The Internet says what "nvcc fatal : Unsupported gpu architecture 'compute_89'" error means old nvcc version what do not known about new GPU like RTX 4090 yet. See: https://github.com/ggerganov/llama.cpp/issues/1420 Try...
In case you still want answer: 1) Go to config.yaml. 2) See input shape parameter like [129, 500, 1]. 3) Set segment_length as 3. This is minimal audio lenght in...
This error raised due this project attempt install python packages from code. Here is simple workaround for it: 1) Goto to folder where "venv" folder resides. This folder contains python...