search

pudae / tensorflow-pspnet

47 stars 19 forks source link

No such file or directory: './train/skynet_v1_50_graph.pb' #4

Open Heidisnaps opened 7 years ago

Heidisnaps commented 7 years ago

Hello. @pudae

I downloaded the file(pspnet_v1_50_miou_0_349.zip) you provided. and then, I run test_model.py. but like this error:

$ python test_model.py
2017-08-11 01:28:50.432318: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-08-11 01:28:50.432383: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-08-11 01:28:50.432435: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-08-11 01:28:50.961497: E tensorflow/stream_executor/cuda/cuda_driver.cc:405] failed call to cuInit: CUDA_ERROR_NO_DEVICE
2017-08-11 01:28:50.961770: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:158] retrieving CUDA diagnostic information for host: ip-172-31-31-194
2017-08-11 01:28:50.961883: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:165] hostname: ip-172-31-31-194
2017-08-11 01:28:50.962149: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:189] libcuda reported version is: 375.66.0
2017-08-11 01:28:50.962330: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:369] driver version file contents: """NVRM version: NVIDIA UNIX x86_64 Kernel Module  375.66  Mon May  1 15:29:16 PDT 2017
GCC version:  gcc version 5.4.0 20160609 (Ubuntu 5.4.0-6ubuntu1~16.04.4)
"""
2017-08-11 01:28:50.962590: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:193] kernel reported version is: 375.66.0
2017-08-11 01:28:50.962697: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:300] kernel version seems to match DSO: 375.66.0
Traceback (most recent call last):
  File "test_model.py", line 60, in <module>
    tf.app.run()
  File "/home/ubuntu/anaconda3/envs/heidi_env2/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "test_model.py", line 30, in main
    with open('./train/skynet_v1_50_graph.pb', 'rb') as file:
FileNotFoundError: [Errno 2] No such file or directory: './train/skynet_v1_50_graph.pb'

thanks!