Open jdmartin86 opened 6 years ago
you can try modifying function get_config(FLAGS) into following:
def get_config(FLAGS):
if FLAGS.model == 'm1':
config = M1
# elif FLAGS.model == 'm2':
# config = M2
# for k, v in FLAGS.__dict__['__flags'].items():
for k, v in FLAGS.__flags.items():
if k == 'use_gpu':
if v.value == False:
config.cnn_format = 'NHWC'
else:
config.cnn_format = 'NCHW'
if hasattr(config, k):
setattr(config, k, v.value)
return config
Thanks for the response. After making your proposed update, I receive the following memory error.
Traceback (most recent call last):
File "main.py", line 70, in <module>
tf.app.run()
File "/home/jdmartin86/anaconda2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 126, in run
_sys.exit(main(argv))
File "main.py", line 62, in main
agent = Agent(config, env, sess)
File "/home/jdmartin86/sandbox/test-qlearn/DQN-tensorflow/dqn/agent.py", line 23, in __init__
self.memory = ReplayMemory(self.config, self.model_dir)
File "/home/jdmartin86/sandbox/test-qlearn/DQN-tensorflow/dqn/replay_memory.py", line 18, in __init__
self.screens = np.empty((self.memory_size, config.screen_height, config.screen_width), dtype = np.float16)
MemoryError
Is this unrelated?
I met the same MemoryError problem as you, then I modify the memory_size in config.py to a smaller value and then it works. Hope this helps you.
for k in FLAGS.__dict__['__wrapped']:
if k == 'use_gpu':
if not FLAGS.__getattr__(k):
config.cnn_format = 'NHWC'
else:
config.cnn_format = 'NCHW'
if hasattr(config, k):
setattr(config, k, FLAGS.__getattr__(k))
With this change, I didn't get the memory error. However, there are still many bugs in the code for the new tensorflow.
After following the install instructions and running
python main.py --env_name=Breakout-v0 --is_train=True
I receive the following error