I'm in high school and I'm trying to do a project involving neural networks. I am using Ubuntu and trying to do reinforcement learning with tensorflow, but I consistently get lots of underrun warnings when I train a neural network. They take the form of ALSA lib pcm.c:7963:(snd_pcm_recover) underrun occurred. This message is printed to the screen more and more frequently as training progresses. Eventually, I get a ResourceExhaustedError and the program terminates. Here is the full error message:
W tensorflow/core/framework/op_kernel.cc:975] Resource exhausted: OOM when allocating tensor with shape[320000,512]
Traceback (most recent call last):
File "./train.py", line 121, in <module>
loss, _ = model.train(minibatch, gamma, sess) # Train the model based on the batch, the discount factor, and the tensorflow session.
File "/home/perrin/neural/dqn.py", line 174, in train
return sess.run([self.loss, self.optimize], feed_dict=self.feed_dict) # Runs the training. This is where the underrun errors happen
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 766, in run
run_metadata_ptr)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 964, in _run
feed_dict_string, options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1014, in _do_run
target_list, options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1034, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[320000,512]
[[Node: gradients/fully_connected/MatMul_grad/MatMul_1 = MatMul[T=DT_FLOAT, transpose_a=true, transpose_b=false, _device="/job:localhost/replica:0/task:0/cpu:0"](dropout/mul, gradients/fully_connected/BiasAdd_grad/tuple/control_dependency)]]
Caused by op u'gradients/fully_connected/MatMul_grad/MatMul_1', defined at:
File "./train.py", line 72, in <module>
model = AC_Net([None, 201, 201, 3], 5, trainer) # This creates the neural network using the imported AC_Net class.
File "/home/perrin/neural/dqn.py", line 128, in __init__
self.optimize = trainer.minimize(self.loss) # This tells the trainer to adjust the weights in such a way as to minimize the loss. This is what actually
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/optimizer.py", line 269, in minimize
grad_loss=grad_loss)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/optimizer.py", line 335, in compute_gradients
colocate_gradients_with_ops=colocate_gradients_with_ops)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gradients_impl.py", line 482, in gradients
in_grads = grad_fn(op, *out_grads)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_grad.py", line 731, in _MatMulGrad
math_ops.matmul(op.inputs[0], grad, transpose_a=True))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py", line 1729, in matmul
a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 1442, in _mat_mul
transpose_b=transpose_b, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2240, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1128, in __init__
self._traceback = _extract_stack()
...which was originally created as op u'fully_connected/MatMul', defined at:
File "./train.py", line 72, in <module>
model = AC_Net([None, 201, 201, 3], 5, trainer) # This creates the neural network using the imported AC_Net class.
File "/home/perrin/neural/dqn.py", line 63, in __init__
net = slim.fully_connected(net, 512, activation_fn=tf.nn.elu, scope='fully_connected') # Feeds the input through a fully connected layer
File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 177, in func_with_args
return func(*args, **current_args)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1350, in fully_connected
outputs = standard_ops.matmul(inputs, weights)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py", line 1729, in matmul
a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 1442, in _mat_mul
transpose_b=transpose_b, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2240, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1128, in __init__
self._traceback = _extract_stack()
ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[320000,512]
[[Node: gradients/fully_connected/MatMul_grad/MatMul_1 = MatMul[T=DT_FLOAT, transpose_a=true, transpose_b=false, _device="/job:localhost/replica:0/task:0/cpu:0"](dropout/mul, gradients/fully_connected/BiasAdd_grad/tuple/control_dependency)]]
I researched these problems but didn't get a clear idea of how I could fix them. I am pretty new to programming so I don't know much about how buffers and data reading/writing works. I am very perplexed by these errors. Does anyone know what parts of my code might be causing this and how to fix it? Thanks for taking the time to consider this question!
Here is my code for defining the neural network (based on this tutorial):
#! /usr/bin/python
import numpy as np
import tensorflow as tf
slim = tf.contrib.slim
# The neural network
class AC_Net:
# This defines the actual neural network.
# output_size: the number of outputs of the policy
# trainer: the tensorflow training optimizer used by the network
def __init__(self, input_shape, output_size, trainer):
with tf.name_scope('input'):
self.input = tf.placeholder(shape=list(input_shape), dtype=tf.float32, name='input')
net = tf.image.per_image_standardization(self.input[0])
net = tf.expand_dims(net, [0])
with tf.name_scope('convolution'):
net = slim.conv2d(net, 32, [8, 8], activation_fn=tf.nn.elu, scope='conv')
net = slim.max_pool2d(net, [2, 2], scope='pool')
net = slim.flatten(net)
net = tf.nn.dropout(net, .5)
net = slim.fully_connected(net, 512, activation_fn=tf.nn.elu, scope='fully_connected')
net = tf.nn.dropout(net, .5)
with tf.name_scope('LSTM'):
cell = tf.nn.rnn_cell.BasicLSTMCell(256, state_is_tuple=True, activation=tf.nn.elu)
with tf.name_scope('state_in'):
state_in = cell.zero_state(tf.shape(net)[0], tf.float32)
net = tf.expand_dims(net, [0])
step_size = tf.shape(self.input)[:1]
output, state = tf.nn.dynamic_rnn(cell, net, initial_state=state_in, sequence_length=step_size, time_major=False, scope='LSTM')
out = tf.reshape(output, [-1, 256])
out = tf.nn.dropout(out, .5)
self.policy = slim.fully_connected(out, output_size, activation_fn=tf.nn.softmax, scope='policy')
self.value = slim.fully_connected(out, 1, activation_fn=None, scope='value')
# Defines the loss functions
with tf.name_scope('loss_function'):
self.target_values = tf.placeholder(dtype=tf.float32, name='target_values') # The target value is the discounted reward.
self.actions = tf.placeholder(dtype=tf.int32, name='actions') # This is the network's policy.
# The advantage is the difference between what the network thought the value of an action was, and what it actually was.
# It is computed as R - V(s), where R is the discounted reward and V(s) is the value of being in state s.
self.advantages = tf.placeholder(dtype=tf.float32, name='advantages')
with tf.name_scope('entropy'):
entropy = -tf.reduce_sum(tf.log(self.policy + 1e-10) * self.policy)
with tf.name_scope('responsible_actions'):
actions_onehot = tf.one_hot(self.actions, output_size, dtype=tf.float32)
responsible_actions = tf.reduce_sum(self.policy * actions_onehot, [1]) # This returns only the actions that were selected.
with tf.name_scope('loss'):
with tf.name_scope('value_loss'):
self.value_loss = tf.reduce_sum(tf.square(self.target_values - tf.reshape(self.value, [-1])))
with tf.name_scope('policy_loss'):
self.policy_loss = -tf.reduce_sum(tf.log(responsible_actions + 1e-10) * self.advantages)
with tf.name_scope('total_loss'):
self.loss = self.value_loss + self.policy_loss - entropy * .01
tf.summary.scalar('loss', self.loss)
with tf.name_scope('gradient_clipping'):
tvars = tf.trainable_variables()
grads = tf.gradients(self.loss, tvars)
grads, _ = tf.clip_by_global_norm(grads, 20.)
self.optimize = trainer.apply_gradients(zip(grads, tvars))
def predict(self, inputs, sess):
return sess.run([self.policy, self.value], feed_dict={self.input:inputs})
def train(self, train_batch, gamma, sess):
inputs = train_batch[:, 0]
actions = train_batch[:, 1]
rewards = train_batch[:, 2]
values = train_batch[:, 4]
discounted_rewards = rewards[::-1]
for i, j in enumerate(discounted_rewards):
if i > 0:
discounted_rewards[i] += discounted_rewards[i - 1] * gamma
discounted_rewards = np.array(discounted_rewards, np.float32)[::-1]
advantages = discounted_rewards - values
self.feed_dict = {
self.input:np.vstack(inputs),
self.target_values:discounted_rewards,
self.actions:actions,
self.advantages:advantages
}
return sess.run([self.loss, self.optimize], feed_dict=self.feed_dict)
Here is my code for training the neural network:
#! /usr/bin/python
import game_env, move_right, move_right_with_obs, random, inspect, os
import tensorflow as tf
import numpy as np
from dqn import AC_Net
def process_outputs(x):
a = [int(x > 2), int(x%2 == 0 and x > 0)*2-int(x > 0)]
return a
environment = game_env # The environment to use
env_name = str(inspect.getmodule(environment).__name__) # The name of the environment
ep_length = 2000
num_episodes = 20
total_steps = ep_length * num_episodes # The total number of steps
model_path = '/home/perrin/neural/nn/' + env_name
learning_rate = 1e-4 # The learning rate
trainer = tf.train.AdamOptimizer(learning_rate=learning_rate) # The gradient descent optimizer used
first_epsilon = 0.6 # The initial chance of random action
final_epsilon = 0.01 # The final chance of random action
gamma = 0.9
anneal_steps = 35000 # The number of steps it takes to go from initial to random
count = 0 # Keeps track of the number of steps we've run
experience_buffer = [] # Stores the agent's experiences in a list
buffer_size = 10000 # How large the experience buffer can be
train_step = 256 # How often to train the model
batches_per_train = 10
save_step = 500 # How often to save the trained model
batch_size = 256 # How many experiences to train on at once
env_size = 500 # How many pixels tall and wide the environment should be.
load_model = True # Whether or not to load a pretrained model
train = True # Whether or not to train the model
test = False # Whether or not to test the model
tf.reset_default_graph()
sess = tf.InteractiveSession()
model = AC_Net([None, 201, 201, 3], 5, trainer)
env = environment.Env(env_size)
action = [0, 0]
state, _ = env.step(True, action)
saver = tf.train.Saver() # This saves the model
epsilon = first_epsilon
tf.global_variables_initializer().run()
if load_model:
ckpt = tf.train.get_checkpoint_state(model_path)
saver.restore(sess, ckpt.model_checkpoint_path)
print 'Model loaded'
prev_out = None
while count <= total_steps and train:
if random.random() < epsilon or count == 0:
if prev_out is not None:
out = prev_out
if random.randint(0, 100) == 100 or prev_out is None:
out = np.random.rand(5)
out = np.array([val/np.sum(out) for val in out])
_, value = model.predict(state, sess)
prev_out = out
else:
out, value = model.predict(state, sess)
out = out[0]
act = np.random.choice(out, p=out)
act = np.argmax(out == act)
act1 = process_outputs(act)
action[act1[0]] = act1[1]
_, reward = env.step(True, action)
new_state = env.get_state()
experience_buffer.append((state, act, reward, new_state, value[0, 0]))
state = new_state
if len(experience_buffer) > buffer_size:
experience_buffer.pop(0)
if count % train_step == 0 and count > 0:
print "Training model"
for i in range(batches_per_train):
# Get a random sample of experiences and train the model based on it.
x = random.randint(0, len(experience_buffer)-batch_size)
minibatch = np.array(experience_buffer[x:x+batch_size])
loss, _ = model.train(minibatch, gamma, sess)
print "Loss for batch", str(i+1) + ":", loss
if count % save_step == 0 and count > 0:
saver.save(sess, model_path+'/model-'+str(count)+'.ckpt')
print "Model saved"
if count % ep_length == 0 and count > 0:
print "Starting new episode"
env = environment.Env(env_size)
if epsilon > final_epsilon:
epsilon -= (first_epsilon - final_epsilon)/anneal_steps
count += 1
while count <= total_steps and test:
out, _ = model.predict(state, sess)
out = out[0]
act = np.random.choice(out, p=out)
act = np.argmax(out == act)
act1 = process_outputs(act)
action[act1[0]] = act1[1]
state, reward = env.step(True, action)
new_state = env.get_state()
count += 1
# Write log files to create tensorboard visualizations
merged = tf.summary.merge_all()
writer = tf.summary.FileWriter('/home/perrin/neural/summaries', sess.graph)
if train:
summary = sess.run(merged, feed_dict=model.feed_dict)
writer.add_summary(summary)
writer.flush()
You are running out of memory. It's possible that your network requires more memory than you have to run, so the first step to tracking down excessive memory usage is to figure out what is using so much memory.
Here's one approach that uses timeline and statssummarizer: https://gist.github.com/yaroslavvb/08afccbe087171881ceafc0c98abca05
This will print out several tables, one of the tables is the tensors sorted by top memory usage. You should check that you don't have something unusually large in there.
You can also see memory timeline using Chrome visualizer, as detailed here
A more advanced technique is to plot a timeline of memory allocations/deallocations, as done in this issue
Theoretically your memory usage shouldn't grow between steps if you aren't creating new stateful ops (Variables), but I found that global memory allocation can grow if sizes of your tensors change between steps.
A work-around is to periodically save your parameters to checkpoint and restart your script.