Skip to content

Instantly share code, notes, and snippets.

@lefnire
Created October 7, 2017 02:57
Show Gist options
  • Save lefnire/eb89a196f366ae40627d454319beb4a9 to your computer and use it in GitHub Desktop.
Save lefnire/eb89a196f366ae40627d454319beb4a9 to your computer and use it in GitHub Desktop.
2017-10-06 19:57:20.025172: 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.
2017-10-06 19:57:20.025184: 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.
2017-10-06 19:57:20.025186: 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.
2017-10-06 19:57:20.025188: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-10-06 19:57:20.025189: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
2017-10-06 19:57:20.027887: E tensorflow/stream_executor/cuda/cuda_driver.cc:406] failed call to cuInit: CUDA_ERROR_NO_DEVICE
2017-10-06 19:57:20.027917: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:158] retrieving CUDA diagnostic information for host: lefnire-ubuntu
2017-10-06 19:57:20.027922: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:165] hostname: lefnire-ubuntu
2017-10-06 19:57:20.027953: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:189] libcuda reported version is: 375.66.0
2017-10-06 19:57:20.027975: 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 6.3.0 20170406 (Ubuntu 6.3.0-12ubuntu2)
"""
2017-10-06 19:57:20.027988: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:193] kernel reported version is: 375.66.0
2017-10-06 19:57:20.027991: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:300] kernel version seems to match DSO: 375.66.0
[2017-10-06 19:57:20,087] Configuration values not accessed: tf_saver
mode: ALL row_count: 399140 split: 319312
Exception in thread Thread-7:
Traceback (most recent call last):
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1327, in _do_call
return fn(*args)
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1306, in _run_fn
status, run_metadata)
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/contextlib.py", line 88, in __exit__
next(self.gen)
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'training/lstm1/Placeholder' with dtype float and shape [?,2,256]
[[Node: training/lstm1/Placeholder = Placeholder[dtype=DT_FLOAT, shape=[?,2,256], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/threading.py", line 916, in _bootstrap_inner
self.run()
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/threading.py", line 864, in run
self._target(*self._args, **self._kwargs)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/execution/threaded_runner.py", line 83, in _run_single
agent.observe(reward=reward, terminal=terminal)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/agents/batch_agent.py", line 89, in observe
self.model.update(self.batch)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/models/q_model.py", line 166, in update
return super(QModel, self).update(*args, **kwargs)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/models/model.py", line 273, in update
feed_dict = self.update_feed_dict(batch=batch)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/models/dqn_nstep_model.py", line 66, in update_feed_dict
target_q_vals = self.session.run(self.target_values, feed_dict=feed_dict)
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 895, in run
run_metadata_ptr)
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1124, in _run
feed_dict_tensor, options, run_metadata)
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1321, in _do_run
options, run_metadata)
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1340, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'training/lstm1/Placeholder' with dtype float and shape [?,2,256]
[[Node: training/lstm1/Placeholder = Placeholder[dtype=DT_FLOAT, shape=[?,2,256], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Caused by op 'training/lstm1/Placeholder', defined at:
File "/home/lefnire/Apps/pycharm-2017.2/helpers/pydev/pydevd.py", line 1596, in <module>
globals = debugger.run(setup['file'], None, None, is_module)
File "/home/lefnire/Apps/pycharm-2017.2/helpers/pydev/pydevd.py", line 1023, in run
pydev_imports.execfile(file, globals, locals) # execute the script
File "/home/lefnire/Apps/pycharm-2017.2/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/home/lefnire/Sites/btc/threaded_ale.py", line 53, in <module>
main()
File "/home/lefnire/Sites/btc/threaded_ale.py", line 38, in main
main_agent = agent = AgentsDictionary[experiments.AGENT_TYPE](config=conf)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/agents/batch_agent.py", line 55, in __init__
super(BatchAgent, self).__init__(config, model)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/agents/agent.py", line 162, in __init__
self.model = self.__class__.model(config)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/models/dqn_model.py", line 48, in __init__
super(DQNModel, self).__init__(config)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/models/q_model.py", line 48, in __init__
super(QModel, self).__init__(config)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/models/model.py", line 112, in __init__
self.create_tf_operations(config)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/models/dqn_nstep_model.py", line 45, in create_tf_operations
super(DQNNstepModel, self).create_tf_operations(config)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/models/q_model.py", line 66, in create_tf_operations
self.training_network = NeuralNetwork(network_builder=network_builder, inputs=self.state, summary_level=config.tf_summary_level, is_training=self.is_training)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/core/networks/network.py", line 37, in __init__
network = network_builder(inputs, summary_level=summary_level, is_training=is_training)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/core/networks/layers.py", line 435, in network_builder
kwargs=dict(x=x, scope=scope, summary_level=summary_level, is_training=is_training)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/util.py", line 173, in get_object
return obj(**full_kwargs)
File "/home/lefnire/Sites/btc/tmp/tensorforce/tensorforce/core/networks/layers.py", line 372, in lstm
internal_input = tf.placeholder(dtype=tf.float32, shape=(None, 2, size))
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 1548, in placeholder
return gen_array_ops._placeholder(dtype=dtype, shape=shape, name=name)
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 2094, in _placeholder
name=name)
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
op_def=op_def)
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2630, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/lefnire/anaconda3/envs/btc3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1204, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'training/lstm1/Placeholder' with dtype float and shape [?,2,256]
[[Node: training/lstm1/Placeholder = Placeholder[dtype=DT_FLOAT, shape=[?,2,256], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment