def restore(self, ckpt_file='/tmp/rlflow/model.ckpt'):
"""
Restore state from a file
"""
self.saver.restore(self.sess, ckpt_file)
# if '-' in ckpt_file[ckpt_file.rfind('.ckpt'):]:
# last_step = int(ckpt_file[ckpt_file.find('-')+1:])
# self.step = last_step
print("Session restored from file: %s" % ckpt_file)
# def build_summary_ops(self, verbose=3):
# """
# Build summary ops for activations, gradients, reward, q values,
# values estimates, etc
# Create summaries with `verbose` level
# """
# if verbose >= 3:
# # Summarize activations
# activations = tf.get_collection(tf.GraphKeys.ACTIVATIONS)
# tflearn.summarize_activations(activations, RLAlgorithm.SUMMARY_COLLECTION_NAME)
# if verbose >= 2:
# # Summarize variable weights
# tflearn.summarize_variables(tf.trainable_variables(), RLAlgorithm.SUMMARY_COLLECTION_NAME)
# if verbose >= 1:
# # summarize reward
# episode_reward = tf.Variable(0., trainable=False)
# self.episode_reward_summary = scalar_summary("Reward", episode_reward, collections=RLAlgorithm.SUMMARY_COLLECTION_NAME)
# self.episode_reward_placeholder = tf.placeholder("float")
# self.episode_reward_op = episode_reward.assign(self.episode_reward_placeholder)
# tf.add_to_collection(RLAlgorithm.SUMMARY_COLLECTION_NAME, self.episode_reward_summary)
#
# # Summarize gradients
# # tflearn.summarize_gradients(self.grads_and_vars, summ_collection)
#
# if len(tf.get_collection(RLAlgorithm.SUMMARY_COLLECTION_NAME)) != 0:
# self.summary_op = merge_all_summaries(key=RLAlgorithm.SUMMARY_COLLECTION_NAME)
评论列表
文章目录