Trained Model Test Fail

[dmoyandreu]

Good Afternoon,

My name is David, actually I'm using your project for my degree final task (TFG).
Apreciate how much your work has helped me to reach the goal I'm trying to get.

This is my setup:

1. OS Windows 10 Home
2. Tensorflow version 1.15
3. Python version: 3.7.6

After loading the trained model (zip decompressed in main folder as said in ArashHosseini@808f843):

4.1 TRACEBACK

File "src/predict_3dpose.py", line 546, in
tf.app.run()
File "C:\Users\David\venv\lib\site-packages\tensorflow_core\python\platform\app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "C:\Users\David\venv\lib\site-packages\absl\app.py", line 299, in run
_run_main(main, args)
File "C:\Users\David\venv\lib\site-packages\absl\app.py", line 250, in _run_main
sys.exit(main(argv))
File "src/predict_3dpose.py", line 541, in main
sample()
File "src/predict_3dpose.py", line 433, in sample
model = create_model(sess, actions, batch_size)
File "src/predict_3dpose.py", line 146, in create_model
raise( ValueError, "Checkpoint {0} does not seem to exist".format( ckpt.model_checkpoint_path ) )
AttributeError: 'NoneType' object has no attribute 'model_checkpoint_path'

4.2 C:\Users\David\TFG\3d-pose-baseline\src\data_utils.py:462: FutureWarning: arrays to stack must be passed as a "sequence" type such as list or tuple. Support for non-sequence iterables such as generators is deprecated as of NumPy 1.16 and will raise an error in the future.
complete_train = copy.deepcopy( np.vstack( train_set.values() ))

Guess this one (4.2) can be ignored?

4.3 2020-04-20 20:53:03.763958: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cudart64_100.dll'; dlerror: cudart64_100.dll not found
2020-04-20 20:53:03.769277: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cublas64_100.dll'; dlerror: cublas64_100.dll not found
2020-04-20 20:53:03.774464: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cufft64_100.dll'; dlerror: cufft64_100.dll not found
2020-04-20 20:53:03.779579: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'curand64_100.dll'; dlerror: curand64_100.dll not found
2020-04-20 20:53:03.784830: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cusolver64_100.dll'; dlerror: cusolver64_100.dll not found
2020-04-20 20:53:03.789774: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cusparse64_100.dll'; dlerror: cusparse64_100.dll not found
2020-04-20 20:53:03.795735: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cudnn64_7.dll'; dlerror: cudnn64_7.dll not found
2020-04-20 20:53:03.800441: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1641] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.

Should I use GPU mandatory?

4.4 So much warnings on tensorflow syntax's: "deprecated". I'm above version 1. I have tried on the last version and got the same results.

Also tried to run the "Quick Demo" in your Readme, but same errors jumped.
Would be so grateful if you could explain me why I'm gettint these issues.

Thanks for your attention,

David.

[scucszw]

Same as you
Have you solved it?Please help me...