kishanios123
commented
2 years ago You need to have Nvidia Cuda compatible GPU to run this project.
BTW faced this issue with GPU also due to nvcc issue ... and solved it by installing cudatoolkit-dev==10.0 package with conda.
/mnt/anaconda/bin/python3.7 /mnt/StyleCLIP-main/global_directions/GetCode.py 2021-09-28 02:44:08.434424: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcudart.so.10.0'; dlerror: libcudart.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda/lib64 2021-09-28 02:44:08.434559: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcublas.so.10.0'; dlerror: libcublas.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda/lib64 2021-09-28 02:44:08.434671: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcufft.so.10.0'; dlerror: libcufft.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda/lib64 2021-09-28 02:44:08.434781: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcurand.so.10.0'; dlerror: libcurand.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda/lib64 2021-09-28 02:44:08.434887: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcusolver.so.10.0'; dlerror: libcusolver.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda/lib64 2021-09-28 02:44:08.434993: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcusparse.so.10.0'; dlerror: libcusparse.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda/lib64 2021-09-28 02:44:08.435101: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcudnn.so.7'; dlerror: libcudnn.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda/lib64 2021-09-28 02:44:08.435114: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1641] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. Skipping registering GPU devices... Setting up TensorFlow plugin "fused_bias_act.cu": Failed! 2021-09-28 02:44:08.919891: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcudart.so.10.0'; dlerror: libcudart.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda/lib64 2021-09-28 02:44:08.919973: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcublas.so.10.0'; dlerror: libcublas.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda/lib64 2021-09-28 02:44:08.920035: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcufft.so.10.0'; dlerror: libcufft.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda/lib64 2021-09-28 02:44:08.920095: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcurand.so.10.0'; dlerror: libcurand.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda/lib64 2021-09-28 02:44:08.920156: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcusolver.so.10.0'; dlerror: libcusolver.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda/lib64 2021-09-28 02:44:08.920215: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcusparse.so.10.0'; dlerror: libcusparse.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda/lib64 2021-09-28 02:44:08.920274: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcudnn.so.7'; dlerror: libcudnn.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda/lib64 2021-09-28 02:44:08.920282: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1641] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. Skipping registering GPU devices... Traceback (most recent call last): File "/mnt/StyleCLIP-main/global_directions/GetCode.py", line 210, in
GetCode(Gs,random_state,num_img,num_once,dataset_name)
File "/mnt/StyleCLIP-main/global_directions/GetCode.py", line 82, in GetCode
dlatent_avg=Gs.get_var('dlatent_avg')
File "/mnt/StyleCLIP-main/global_directions/dnnlib/tflib/network.py", line 396, in get_var
return self.find_var(var_or_local_name).eval()
File "/mnt/StyleCLIP-main/global_directions/dnnlib/tflib/network.py", line 391, in find_var
return self._get_vars()[var_or_local_name] if isinstance(var_or_local_name, str) else var_or_local_name
File "/mnt/StyleCLIP-main/global_directions/dnnlib/tflib/network.py", line 297, in _get_vars
self._vars = OrderedDict(self._get_own_vars())
File "/mnt/StyleCLIP-main/global_directions/dnnlib/tflib/network.py", line 286, in _get_own_vars
self._init_graph()
File "/mnt/StyleCLIP-main/global_directions/dnnlib/tflib/network.py", line 151, in _init_graph
out_expr = self._build_func(*self._input_templates, *build_kwargs)
File "", line 187, in G_main
File "/mnt/StyleCLIP-main/global_directions/dnnlib/tflib/network.py", line 232, in input_shape
return self.input_shapes[0]
File "/mnt/StyleCLIP-main/global_directions/dnnlib/tflib/network.py", line 219, in input_shapes
self._input_shapes = [t.shape.as_list() for t in self.input_templates]
File "/mnt/StyleCLIP-main/global_directions/dnnlib/tflib/network.py", line 267, in input_templates
self._init_graph()
File "/mnt/StyleCLIP-main/global_directions/dnnlib/tflib/network.py", line 151, in _init_graph
out_expr = self._build_func( self._input_templates, **build_kwargs)
File "", line 491, in G_synthesis_stylegan2
File "", line 455, in layer
File "", line 99, in modulated_conv2d_layer
File "", line 68, in apply_bias_act
File "/mnt/StyleCLIP-main/global_directions/dnnlib/tflib/ops/fused_bias_act.py", line 72, in fused_bias_act
return impl_dict[impl](x=x, b=b, axis=axis, act=act, alpha=alpha, gain=gain, clamp=clamp)
File "/mnt/StyleCLIP-main/global_directions/dnnlib/tflib/ops/fused_bias_act.py", line 132, in _fused_bias_act_cuda
cuda_op = _get_plugin().fused_bias_act
File "/mnt/StyleCLIP-main/global_directions/dnnlib/tflib/ops/fused_bias_act.py", line 18, in _get_plugin
return custom_ops.get_plugin(os.path.splitext(file)[0] + '.cu')
File "/mnt/StyleCLIP-main/global_directions/dnnlib/tflib/custom_ops.py", line 139, in get_plugin
compile_opts += f' --gpu-architecture={_get_cuda_gpu_arch_string()}'
File "/mnt/StyleCLIP-main/global_directions/dnnlib/tflib/custom_ops.py", line 60, in _get_cuda_gpu_arch_string
raise RuntimeError('No GPU devices found')
RuntimeError: No GPU devices found