Question

所以我试图在tensorflow对象检测api中使用我自己的类来训练模型。我使用anaconda和Python 3.5，tensorflow 1.4.0。示例检测有效。我不明白哪个文件实际丢失（或哪个目录），因为错误实际上没有提供它。

python train.py --logtostderr --train_dir=/home/mace/Documents/Python/cvtennis/tensorflow/models/train/ --pipleline_config=/home/mace/Documents/Python/cvtennis/tensorflow/ssd_inception_v2_coco.config
Traceback (most recent call last):
  File "train.py", line 167, in <module>
    tf.app.run()
  File "/home/mace/anaconda3/envs/tf_35/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "train.py", line 110, in main
    overwrite=True)
  File "/home/mace/anaconda3/envs/tf_35/lib/python3.5/site-packages/tensorflow/python/lib/io/file_io.py", line 385, in copy
    compat.as_bytes(oldpath), compat.as_bytes(newpath), overwrite, status)
  File "/home/mace/anaconda3/envs/tf_35/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 473, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.NotFoundError: ; No such file or directory

Python 3 Tensorflow对象检测API没有这样的文件或目录

0 个答案: