训练时生成对抗网络的错误

时间:2020-08-19 08:03:26

标签: python tensorflow generative-adversarial-network

我对stylegan有疑问。 我创建了一个引用此站点的自定义tfrecord。 https://evigio.com/post/how-to-use-custom-datasets-with-stylegan-tensorFlow-implementation 然后我运行train.py并收到以下错误: 你有什么提示吗?


~/stylegan$ python train.py 
Creating the run dir: results/00005-sgan-custom_datasets-4gpu
Copying files to the run dir
dnnlib: Running training.training_loop.training_loop() on localhost...
Streaming data using training.dataset.TFRecordDataset...
Traceback (most recent call last):
  File "train.py", line 191, in <module>
    main()
  File "train.py", line 186, in main
    dnnlib.submit_run(**kwargs)
  File "/home/shannonlab/stylegan/dnnlib/submission/submit.py", line 290, in submit_run
    run_wrapper(submit_config)
  File "/home/shannonlab/stylegan/dnnlib/submission/submit.py", line 242, in run_wrapper
    util.call_func_by_name(func_name=submit_config.run_func_name, submit_config=submit_config, **submit_config.run_func_kwargs)
  File "/home/shannonlab/stylegan/dnnlib/util.py", line 257, in call_func_by_name
    return func_obj(*args, **kwargs)
  File "/home/shannonlab/stylegan/training/training_loop.py", line 146, in training_loop
    training_set = dataset.load_dataset(data_dir=config.data_dir, verbose=True, **dataset_args)
  File "/home/shannonlab/stylegan/training/dataset.py", line 234, in load_dataset
    dataset = dnnlib.util.get_obj_by_name(class_name)(**adjusted_kwargs)
  File "/home/shannonlab/stylegan/training/dataset.py", line 70, in __init__
    assert os.path.isdir(self.tfrecord_dir)
AssertionError

环境 CUDA 9.0 Python 3.6.10 Ubuntu 16.04

0 个答案:

没有答案