WIN10:CUDA error: no kernel image is available for execution on the device

[heiheiheibj]

stylegan2_pytorch --data images default: 0%| | 0/150000 [00:00<?, ?it/s] Traceback (most recent call last): File "d:\programdata\anaconda3\lib\runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "d:\programdata\anaconda3\lib\runpy.py", line 85, in run_code exec(code, run_globals) File "C:\Users\hater\AppData\Roaming\Python\Python37\Scripts\stylegan2_pytorch.exe_main.py", line 7, in File "C:\Users\hater\AppData\Roaming\Python\Python37\site-packages\stylegan2_pytorch\cli.py", line 176, in main fire.Fire(train_from_folder) File "C:\Users\hater\AppData\Roaming\Python\Python37\site-packages\fire\core.py", line 138, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) File "C:\Users\hater\AppData\Roaming\Python\Python37\site-packages\fire\core.py", line 468, in _Fire target=component.name) File "C:\Users\hater\AppData\Roaming\Python\Python37\site-packages\fire\core.py", line 672, in _CallAndUpdateTrace component = fn(*varargs, **kwargs) File "C:\Users\hater\AppData\Roaming\Python\Python37\site-packages\stylegan2_pytorch\cli.py", line 167, in train_from_folder run_training(0, 1, model_args, data, load_from, new, num_train_steps, name, seed) File "C:\Users\hater\AppData\Roaming\Python\Python37\site-packages\stylegan2_pytorch\cli.py", line 59, in run_training retry_call(model.train, tries=3, exceptions=NanException) File "C:\Users\hater\AppData\Roaming\Python\Python37\site-packages\retry\api.py", line 101, in retry_call return __retry_internal(partial(f, *args, **kwargs), exceptions, tries, delay, max_delay, backoff, jitter, logger) File "C:\Users\hater\AppData\Roaming\Python\Python37\site-packages\retry\api.py", line 33, in __retry_internal return f() File "C:\Users\hater\AppData\Roaming\Python\Python37\site-packages\stylegan2_pytorch\stylegan2_pytorch.py", line 928, in train w_space = latent_to_w(S, style) File "C:\Users\hater\AppData\Roaming\Python\Python37\site-packages\stylegan2_pytorch\stylegan2_pytorch.py", line 217, in latent_to_w return [(style_vectorizer(z), num_layers) for z, num_layers in latent_descr] File "C:\Users\hater\AppData\Roaming\Python\Python37\site-packages\stylegan2_pytorch\stylegan2_pytorch.py", line 217, in return [(style_vectorizer(z), num_layers) for z, num_layers in latent_descr] File "d:\programdata\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 550, in call result = self.forward(*input, **kwargs) File "C:\Users\hater\AppData\Roaming\Python\Python37\site-packages\stylegan2_pytorch\stylegan2_pytorch.py", line 364, in forward x = F.normalize(x, dim=1) File "d:\programdata\anaconda3\lib\site-packages\torch\nn\functional.py", line 3590, in normalize denom = input.norm(p, dim, keepdim=True).clamp_min(eps).expand_as(input) File "d:\programdata\anaconda3\lib\site-packages\torch\tensor.py", line 342, in norm return torch.norm(self, p, dim, keepdim, dtype=dtype) File "d:\programdata\anaconda3\lib\site-packages\torch\functional.py", line 882, in norm return _VF.norm(input, p, _dim, keepdim=keepdim) RuntimeError: CUDA error: no kernel image is available for execution on the device

Display card : NV 780 pytorch == 1.7 cudatoolkit=10.2 thanks ....