No sample video output

[firingthoughts]

Hello, I'm trying to run the "sample_video.mp4" or any video and i get this result. Is it because i have AMD GPU? (5700 XT).

Displaying results.. WARNING: You are using a SMPL model, with only 10 shape coefficients. Traceback (most recent call last): File "demo_alter.py", line 405, in main(args) File "demo_alter.py", line 108, in main use_residual=True, File "E:\vibe\VIBE-master\lib\models\vibe.py", line 147, in init checkpoint = torch.load(pretrained) File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\torch\serialization.py", line 529, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\torch\serialization.py", line 702, in _legacy_load result = unpickler.load() File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\torch\serialization.py", line 665, in persistent_load deserialized_objects[root_key] = restore_location(obj, location) File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\torch\serialization.py", line 156, in default_restore_location result = fn(storage, location) File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\torch\serialization.py", line 132, in _cuda_deserialize device = validate_cuda_device(location) File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\torch\serialization.py", line 116, in validate_cuda_device raise RuntimeError('Attempting to deserialize object on a CUDA ' RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

[firingthoughts]

And when i ran a youtube video it came up with this.

(venv_vibe) E:\vibe\VIBE-master>python demo.py --vid_file https://www.youtube.com/watch?v=wPZP8Bwxplo --output_folder output/ --display Traceback (most recent call last): File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\OpenGL\platform\egl.py", line 70, in EGL mode=ctypes.RTLD_GLOBAL File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\OpenGL\platform\ctypesloader.py", line 45, in loadLibrary return dllType( name, mode ) File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\ctypes_init_.py", line 364, in init self._handle = _dlopen(self._name, mode) OSError: [WinError 126] The specified module could not be found

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "demo.py", line 33, in from lib.utils.renderer import Renderer File "E:\vibe\VIBE-master\lib\utils\renderer.py", line 19, in import pyrender File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\pyrender_init_.py", line 3, in from .light import Light, PointLight, DirectionalLight, SpotLight File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\pyrender\light.py", line 11, in from .texture import Texture File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\pyrender\texture.py", line 8, in from OpenGL.GL import * File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\OpenGL\GL_init_.py", line 3, in from OpenGL import error as _error File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\OpenGL\error.py", line 12, in from OpenGL import platform, configflags File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\OpenGL\platform_init.py", line 35, in load() File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\OpenGL\platform_init.py", line 32, in _load plugin.install(globals()) File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\OpenGL\platform\baseplatform.py", line 92, in install namespace[ name ] = getattr(self,name,None) File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\OpenGL\platform\baseplatform.py", line 14, in get value = self.fget( obj ) File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\OpenGL\platform\egl.py", line 93, in GetCurrentContext return self.EGL.eglGetCurrentContext File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\OpenGL\platform\baseplatform.py", line 14, in get value = self.fget( obj ) File "E:\Users\Firing\miniconda3\envs\venv_vibe\lib\site-packages\OpenGL\platform\egl.py", line 73, in EGL raise ImportError("Unable to load EGL library", *err.args) ImportError: ('Unable to load EGL library', 22, 'The specified module could not be found', None, 126, None, 'EGL', None)

[carlosedubarreto]

I never tested the youtube function. But lets narrow down the problem.

The other way, using a mp4, does it works with you?

[firingthoughts]

Hello, no, it doesn't. That's the first issue in my post

[carlosedubarreto]

Please, can you run the installation again and put here all that is shown?

I'm about to go sleep but I'll look at it in the morning

[firingthoughts]

Like install vibe again? It was installed correctly i think

[carlosedubarreto]

yes, to just tun the installation bat again, in the created enviroment.

This is important to see where is the error. what part of the installation failed.

Because if you are having this issue using Vibe, is because something didnt go right on the installation.

[Anitazyx]

You need to modify the statements in the lib/models/vibe.py file torch.load(pretrained) torch.load(pretrained,map_location='cpu')

[firingthoughts]

You need to modify the statements in the lib/models/vibe.py file torch.load(pretrained) torch.load(pretrained,map_location='cpu')

I updated GPU drivers and it worked for a brief second, it seems to be a problem with the torch.load file indeed. What do I change those statements to? To "(pretrained,map_location='cpu')"?