[Problem] training step

[Jaehyun0818]

Hi,

I followed the instruction to run the training:python train.py using the default settings max_epoch=500 At the beginning of the training step, there is error popping up:

2019-02-02 15:50:29.682610: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX 2019-02-02 15:50:29.907778: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1105] Found device 0 with properties: name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.645 pciBusID: 0000:03:00.0 totalMemory: 10.91GiB freeMemory: 10.37GiB 2019-02-02 15:50:29.907851: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1195] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:03:00.0, compute capability: 6.1) --- Get model and loss Process Process-1: Traceback (most recent call last): File "/usr/lib/python2.7/multiprocessing/process.py", line 258, in _bootstrap self.run() File "/usr/lib/python2.7/multiprocessing/process.py", line 114, in run self._target(*self._args, self._kwargs) File "train.py", line 164, in fill_queues stack_train.put(p.get()) File "/usr/lib/python2.7/multiprocessing/pool.py", line 567, in get raise self._value ValueError: probabilities do not sum to 1 --- Get training operator 2019-02-02 15:50:37.119749: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1195] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:03:00.0, compute capability: 6.1) ('in epoch', 0) ('max_epoch', 500) ** EPOCH 000 **** 2019-02-02 15:50:41.417430 Progress: [----------] 0.0%

Also, the progress percentage doesn't increase during a day and it keeps 0.0%.

Would anyone please advise on what the error above means and what should I do? Thanks. Jaehyun

[lemontree6]

Hi, Jaehyun. Did you solve the problem?

[akhilsantha7]

Hey, did u figure it out? Even I'm facing the same problem.

[Jaehyun0818]

Yes. In my case, I figured it out by changing the python version to python 3.5