search

miyosuda / async_deep_reinforce

Asynchronous Methods for Deep Reinforcement Learning
Apache License 2.0
592 stars 192 forks source link

About variable error. #33

Closed Michi-123 closed 5 years ago

Michi-123 commented 7 years ago

Hello. When I ran "a3c.py" or "a3c_display.py" , I got error log bellow.

I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcublas.so.8.0 locally I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcudnn.so.5 locally I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcufft.so.8.0 locally I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcuda.so.1 locally I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcurand.so.8.0 locally Traceback (most recent call last): File "a3c.py", line 50, in global_network = GameACLSTMNetwork(ACTION_SIZE, -1, device) File "/home/uchi/async_deep_reinforce/game_ac_network.py", line 218, in init self.W_lstm = tf.get_variable("BasicLSTMCell/Linear/Matrix") File "/home/uchi/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 988, in get_variable custom_getter=custom_getter) File "/home/uchi/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 890, in get_variable custom_getter=custom_getter) File "/home/uchi/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 348, in get_variable validate_shape=validate_shape) File "/home/uchi/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 333, in _true_getter caching_device=caching_device, validate_shape=validate_shape) File "/home/uchi/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 657, in _get_singlevariable "VarScope?" % name) ValueError: Variable net-1/BasicLSTMCell/Linear/Matrix does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

How do I resolve this problem?

miyosuda commented 7 years ago

I've upgraded my code from TensorFlow r0.12 to r1.0 just now. (These error occurred TF r1.0 environment while my code used to use r0.12 env.) Could you try again?

Michi-123 commented 7 years ago

Thank you for replying. At the first, I couldn't get source with the command 'git clone git@github.com:miyosuda/async_deep_reinforce.git' but I could get with the green Download button on the web site. (the new one is 'async_deep_reinforce-master' , isn't it )

And now, your program is really working!

kmcnayr commented 7 years ago

Reference to Issue: #32 This needs to be updated again per the latest release notes: https://github.com/tensorflow/tensorflow/blob/master/RELEASE.md

I successfully ran a3c.py by substituting "kernel" for "weights" and "bias" for "biases"