StyleGan2不支持Windows 10上的Microsoft Visual Studio版本

Question

今天，我尝试在我制作的自定义数据集上运行StyleGan2，该数据集由200个图像（256x256）组成。 我对命令有问题：

python run_training.py --num-gpus=1 --data-dir=./datasets --config=config-f --dataset=my-custom-dataset --mirror-augment=true --metrics=None

导致此错误的原因：

Setting up TensorFlow plugin "fused_bias_act.cu": Preprocessing... Failed!
Traceback (most recent call last):
  File "run_training.py", line 192, in <module>
    main()
  File "run_training.py", line 187, in main
    run(**vars(args))
  File "run_training.py", line 120, in run
    dnnlib.submit_run(**kwargs)
  File "C:\Users\Mista No\Desktop\stylegan2-master\dnnlib\submission\submit.py", line 343, in submit_run
    return farm.submit(submit_config, host_run_dir)
  File "C:\Users\Mista No\Desktop\stylegan2-master\dnnlib\submission\internal\local.py", line 22, in submit
    return run_wrapper(submit_config)
  File "C:\Users\Mista No\Desktop\stylegan2-master\dnnlib\submission\submit.py", line 280, in run_wrapper
    run_func_obj(**submit_config.run_func_kwargs)
  File "C:\Users\Mista No\Desktop\stylegan2-master\training\training_loop.py", line 149, in training_loop
    G = tflib.Network('G', num_channels=training_set.shape[0], resolution=training_set.shape[1], label_size=training_set.label_size, **G_args)
  File "C:\Users\Mista No\Desktop\stylegan2-master\dnnlib\tflib\network.py", line 97, in __init__
    self._init_graph()
  File "C:\Users\Mista No\Desktop\stylegan2-master\dnnlib\tflib\network.py", line 154, in _init_graph
    out_expr = self._build_func(*self.input_templates, **build_kwargs)
  File "C:\Users\Mista No\Desktop\stylegan2-master\training\networks_stylegan2.py", line 186, in G_main
    components.synthesis = tflib.Network('G_synthesis', func_name=globals()[synthesis_func], **kwargs)
  File "C:\Users\Mista No\Desktop\stylegan2-master\dnnlib\tflib\network.py", line 97, in __init__
    self._init_graph()
  File "C:\Users\Mista No\Desktop\stylegan2-master\dnnlib\tflib\network.py", line 154, in _init_graph
    out_expr = self._build_func(*self.input_templates, **build_kwargs)
  File "C:\Users\Mista No\Desktop\stylegan2-master\training\networks_stylegan2.py", line 491, in G_synthesis_stylegan2
    x = layer(x, layer_idx=0, fmaps=nf(1), kernel=3)
  File "C:\Users\Mista No\Desktop\stylegan2-master\training\networks_stylegan2.py", line 455, in layer
    x = modulated_conv2d_layer(x, dlatents_in[:, layer_idx], fmaps=fmaps, kernel=kernel, up=up, resample_kernel=resample_kernel, fused_modconv=fused_modconv)
  File "C:\Users\Mista No\Desktop\stylegan2-master\training\networks_stylegan2.py", line 99, in modulated_conv2d_layer
    s = apply_bias_act(s, bias_var=mod_bias_var) + 1 # [BI] Add bias (initially 1).
  File "C:\Users\Mista No\Desktop\stylegan2-master\training\networks_stylegan2.py", line 68, in apply_bias_act
    return fused_bias_act(x, b=tf.cast(b, x.dtype), act=act, alpha=alpha, gain=gain)
  File "C:\Users\Mista No\Desktop\stylegan2-master\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 "C:\Users\Mista No\Desktop\stylegan2-master\dnnlib\tflib\ops\fused_bias_act.py", line 122, in _fused_bias_act_cuda
    cuda_kernel = _get_plugin().fused_bias_act
  File "C:\Users\Mista No\Desktop\stylegan2-master\dnnlib\tflib\ops\fused_bias_act.py", line 16, in _get_plugin
    return custom_ops.get_plugin(os.path.splitext(__file__)[0] + '.cu')
  File "C:\Users\Mista No\Desktop\stylegan2-master\dnnlib\tflib\custom_ops.py", line 114, in get_plugin
    _run_cmd(_prepare_nvcc_cli('"%s" --preprocess -o "%s" --keep --keep-dir "%s"' % (cuda_file, tmp_file, tmp_dir)))
  File "C:\Users\Mista No\Desktop\stylegan2-master\dnnlib\tflib\custom_ops.py", line 64, in _run_cmd
    raise RuntimeError('NVCC returned an error. See below for full command line and output log:\n\n%s\n\n%s' % (cmd, output))
RuntimeError: NVCC returned an error. See below for full command line and output log:

nvcc "C:\Users\Mista No\Desktop\stylegan2-master\dnnlib\tflib\ops\fused_bias_act.cu" --preprocess -o "C:\Users\MISTAN~1\AppData\Local\Temp\tmp2cmcl945\fused_bias_act_tmp.cu" --keep --keep-dir "C:\Users\MISTAN~1\AppData\Local\Temp\tmp2cmcl945" --disable-warnings --include-path "D:\anaconda\envs\stylegan\lib\site-packages\tensorflow\include" --include-path "D:\anaconda\envs\stylegan\lib\site-packages\tensorflow\include\external\protobuf_archive\src" --include-path "D:\anaconda\envs\stylegan\lib\site-packages\tensorflow\include\external\com_google_absl" --include-path "D:\anaconda\envs\stylegan\lib\site-packages\tensorflow\include\external\eigen_archive" --compiler-bindir "D:/vs/VC/Auxiliary/Build" 2>&1

fused_bias_act.cu
D:\cuda\include\crt/host_config.h(143): fatal error C1189: #error:  -- unsupported Microsoft Visual Studio version! Only the versions between 2013 and 2017 (inclusive) are supported!

已安装Visual Studio 2017

我试着上网，但我没有找到解决问题的方法，我也不知道该去哪里

因此，如果有人能帮助我，我将非常高兴：）

非常感谢愿意帮助我的人

祝你今天愉快