Can't Covert Weights

[qisikai]

when use convert_weight.py , I Got follow errors:

with pytorch == 1.4 tensorflow-gpu ==1.15

How can i use the use pretrained weight.

(torch) ubuntu@Skyamd:~/jupyter_projects/StyleGan2/StyleGAN2.pytorch$ CUDA_VISIBLE_DEVICES="0" python convert_weight.py --path stylegan2-ffhq-config-f.pkl Setting up TensorFlow plugin "fused_bias_act.cu": Preprocessing... Compiling... Loading... Failed! Traceback (most recent call last): File "convert_weight.py", line 167, in <module> generator, discriminator, g_ema = pickle.load(f) File "/home/ubuntu/jupyter_projects/StyleGan2/StyleGAN2.pytorch/dnnlib/tflib/network.py", line 297, in __setstate__ self._init_graph() File "/home/ubuntu/jupyter_projects/StyleGan2/StyleGAN2.pytorch/dnnlib/tflib/network.py", line 154, in _init_graph out_expr = self._build_func(*self.input_templates, **build_kwargs) File "<string>", line 491, in G_synthesis_stylegan2 File "<string>", line 455, in layer File "<string>", line 99, in modulated_conv2d_layer File "<string>", line 68, in apply_bias_act File "/home/ubuntu/jupyter_projects/StyleGan2/StyleGAN2.pytorch/dnnlib/tflib/ops/fused_bias_act.py", line 68, in fused_bias_act return impl_dict[impl](x=x, b=b, axis=axis, act=act, alpha=alpha, gain=gain) File "/home/ubuntu/jupyter_projects/StyleGan2/StyleGAN2.pytorch/dnnlib/tflib/ops/fused_bias_act.py", line 122, in _fused_bias_act_cuda cuda_kernel = _get_plugin().fused_bias_act File "/home/ubuntu/jupyter_projects/StyleGan2/StyleGAN2.pytorch/dnnlib/tflib/ops/fused_bias_act.py", line 16, in _get_plugin return custom_ops.get_plugin(os.path.splitext(__file__)[0] + '.cu') File "/home/ubuntu/jupyter_projects/StyleGan2/StyleGAN2.pytorch/dnnlib/tflib/custom_ops.py", line 156, in get_plugin plugin = tf.load_op_library(bin_file) File "/home/ubuntu/miniconda3/envs/torch/lib/python3.6/site-packages/tensorflow_core/python/framework/load_library.py", line 61, in load_op_library lib_handle = py_tf.TF_LoadLibrary(library_filename) tensorflow.python.framework.errors_impl.NotFoundError: /home/ubuntu/jupyter_projects/StyleGan2/StyleGAN2.pytorch/dnnlib/tflib/_cudacache/fused_bias_act_120a9794993ace58a08b8706b7d58f48.so: undefined symbol: _ZN10tensorflow12OpDefBuilder4AttrENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE (torch) ubuntu@Skyamd:~/jupyter_projects/StyleGan2/StyleGAN2.pytorch$