Tensorflow GPU OOM错误

Question

当在一组TFRecords上运行CNN时，我得到一个OOM错误，其中Tensorflow似乎尝试创建一个非常大的张量。我的模型是MNIST模型，稍微适用于尺寸为200x200的RGB图像。我使用Inception模型中的Build_image_data.py脚本创建TFrecords，然后使用Inception模型中的dataset.py and image_processing.py脚本丢失它们。

我在Nvidia 960m上运行2GB GPU内存和16GB系统内存。

我得到的错误是：

==== RESTART: C:\Users\User\stack\Projects\Neural Network\Nippler\cnn.py ==== 
INFO:tensorflow:Using default config. 
INFO:tensorflow:Using config: {'_keep_checkpoint_max': 5, '_task_id': 0, '_session_config': None, '_master': '', '_tf_random_seed': None, '_environment': 'local', '_num_ps_replicas': 0, '_save_checkpoints_steps': None, '_keep_checkpoint_every_n_hours': 10000, '_save_checkpoints_secs': 600, '_evaluation_master': '', '_task_type': None, '_num_worker_replicas': 0, '_save_summary_steps': 100, '_model_dir': '/tmp/feature_model', '_is_chief': True, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x0000013B77A3F9B0>, '_tf_config': gpu_options { 
    per_process_gpu_memory_fraction: 1 
} 
} 
INFO:tensorflow:Create CheckpointSaverHook. 
Traceback (most recent call last): 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1139, in _do_call 
    return fn(*args) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1121, in _run_fn 
    status, run_metadata) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\contextlib.py", line 66, in __exit__ 
    next(self.gen) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\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.ResourceExhaustedError: OOM when allocating tensor with shape[160000,1024] 
    [[Node: dense/kernel/Assign = Assign[T=DT_FLOAT, _class=["loc:@dense/kernel"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/gpu:0"](dense/kernel, dense/kernel/Initializer/random_uniform)]] 

During handling of the above exception, another exception occurred: 

Traceback (most recent call last): 
    File "C:\Users\User\stack\Projects\Neural Network\Nippler\cnn.py", line 82, in <module> 
    tf.app.run() 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\platform\app.py", line 48, in run 
    _sys.exit(main(_sys.argv[:1] + flags_passthrough)) 
    File "C:\Users\User\stack\Projects\Neural Network\Nippler\cnn.py", line 71, in main 
    feature_classifier.fit(input_fn=lambda:image_processing.inputs(training_data, batch_size), steps=200000, monitors=[logging_hook]) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\util\deprecation.py", line 289, in new_func 
    return func(*args, **kwargs) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py", line 455, in fit 
    loss = self._train_model(input_fn=input_fn, hooks=hooks) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py", line 1003, in _train_model 
    config=self._session_config 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\training\monitored_session.py", line 352, in MonitoredTrainingSession 
    stop_grace_period_secs=stop_grace_period_secs) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\training\monitored_session.py", line 648, in __init__ 
    stop_grace_period_secs=stop_grace_period_secs) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\training\monitored_session.py", line 477, in __init__ 
    self._sess = _RecoverableSession(self._coordinated_creator) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\training\monitored_session.py", line 822, in __init__ 
    _WrappedSession.__init__(self, self._create_session()) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\training\monitored_session.py", line 827, in _create_session 
    return self._sess_creator.create_session() 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\training\monitored_session.py", line 538, in create_session 
    self.tf_sess = self._session_creator.create_session() 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\training\monitored_session.py", line 412, in create_session 
    init_fn=self._scaffold.init_fn) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\training\session_manager.py", line 279, in prepare_session 
    sess.run(init_op, feed_dict=init_feed_dict) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py", line 789, in run 
    run_metadata_ptr) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py", line 997, in _run 
    feed_dict_string, options, run_metadata) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1132, in _do_run 
    target_list, options, run_metadata) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1152, in _do_call 
    raise type(e)(node_def, op, message) 
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[160000,1024] 
    [[Node: dense/kernel/Assign = Assign[T=DT_FLOAT, _class=["loc:@dense/kernel"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/gpu:0"](dense/kernel, dense/kernel/Initializer/random_uniform)]] 

Caused by op 'dense/kernel/Assign', defined at: 
    File "<string>", line 1, in <module> 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\idlelib\run.py", line 130, in main 
    ret = method(*args, **kwargs) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\idlelib\run.py", line 357, in runcode 
    exec(code, self.locals) 
    File "C:\Users\User\stack\Projects\Neural Network\Nippler\cnn.py", line 82, in <module> 
    tf.app.run() 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\platform\app.py", line 48, in run 
    _sys.exit(main(_sys.argv[:1] + flags_passthrough)) 
    File "C:\Users\User\stack\Projects\Neural Network\Nippler\cnn.py", line 71, in main 
    feature_classifier.fit(input_fn=lambda:image_processing.inputs(training_data, batch_size), steps=200000, monitors=[logging_hook]) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\util\deprecation.py", line 289, in new_func 
    return func(*args, **kwargs) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py", line 455, in fit 
    loss = self._train_model(input_fn=input_fn, hooks=hooks) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py", line 955, in _train_model 
    model_fn_ops = self._get_train_ops(features, labels) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py", line 1162, in _get_train_ops 
    return self._call_model_fn(features, labels, model_fn_lib.ModeKeys.TRAIN) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py", line 1133, in _call_model_fn 
    model_fn_results = self._model_fn(features, labels, **kwargs) 
    File "C:\Users\User\stack\Projects\Neural Network\Nippler\cnn.py", line 30, in cnn_model_fn 
    dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\layers\core.py", line 215, in dense 
    return layer.apply(inputs) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\layers\base.py", line 492, in apply 
    return self.__call__(inputs, *args, **kwargs) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\layers\base.py", line 434, in __call__ 
    self.build(input_shapes[0]) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\layers\core.py", line 118, in build 
    trainable=True) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\layers\base.py", line 374, in add_variable 
    trainable=trainable and self.trainable) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 1065, in get_variable 
    use_resource=use_resource, custom_getter=custom_getter) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 962, in get_variable 
    use_resource=use_resource, custom_getter=custom_getter) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 367, in get_variable 
    validate_shape=validate_shape, use_resource=use_resource) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 352, in _true_getter 
    use_resource=use_resource) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 725, in _get_single_variable 
    validate_shape=validate_shape) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\variables.py", line 200, in __init__ 
    expected_shape=expected_shape) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\variables.py", line 309, in _init_from_args 
    validate_shape=validate_shape).op 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\state_ops.py", line 271, in assign 
    validate_shape=validate_shape) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\gen_state_ops.py", line 45, in assign 
    use_locking=use_locking, name=name) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 767, in apply_op 
    op_def=op_def) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 2506, in create_op 
    original_op=self._default_original_op, op_def=op_def) 
    File "C:\Users\User\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 1269, in __init__ 
    self._traceback = _extract_stack() 

ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[160000,1024] 
    [[Node: dense/kernel/Assign = Assign[T=DT_FLOAT, _class=["loc:@dense/kernel"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/gpu:0"](dense/kernel, dense/kernel/Initializer/random_uniform)]] 

这似乎尝试和分配形状[160000,1024]张量。我的记录中只有1400张200x200 RGB图像。为什么即使batch_size为10，它的内存耗尽？

这是我的完整的例子：

from __future__ import absolute_import 
from __future__ import division 
from __future__ import print_function 

import numpy as np 
import tensorflow as tf 

from tensorflow.contrib import learn 
from tensorflow.contrib.learn.python.learn.estimators import model_fn as model_fn_lib 

import image_processing 
import dataset 

tf.logging.set_verbosity(tf.logging.INFO) 

height = 200 
width = 200 
channels = 3 

batch_size = 10 

def cnn_model_fn(features, labels, mode): 
    input_layer = tf.reshape(features, [-1, width, height, channels]) 

    conv1 = tf.layers.conv2d(inputs=input_layer, filters=32, kernel_size=[5, 5], padding="same", activation=tf.nn.relu) 
    pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2) 
    conv2 = tf.layers.conv2d(inputs=pool1, filters=64, kernel_size=[5, 5], padding="same", activation=tf.nn.relu) 
    pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2) 
    pool2_flat = tf.reshape(pool2, [-1, (int(width/4)) * (int(width/4)) * 64]) 
    dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu) 
    dropout = tf.layers.dropout(inputs=dense, rate=0.4, training=mode == learn.ModeKeys.TRAIN) 
    logits = tf.layers.dense(inputs=dropout, units=2) 

    loss = None 
    train_op = None 

    if mode != learn.ModeKeys.INFER: 
     onehot_labels = tf.one_hot(indices=tf.cast(labels, tf.int32), depth=2) 
     loss = tf.losses.softmax_cross_entropy(onehot_labels=onehot_labels, logits=logits) 

    if mode == learn.ModeKeys.TRAIN: 
     train_op = tf.contrib.layers.optimize_loss(loss=loss, global_step=tf.contrib.framework.get_global_step(), learning_rate=0.001, optimizer="SGD") 

    predictions = { 
      "classes": tf.argmax(input=logits, axis=1), 
      "probabilities": tf.nn.softmax(logits, name="softmax_tensor") 
    } 

    return model_fn_lib.ModelFnOps(mode=mode, predictions=predictions, loss=loss, train_op=train_op) 

def main(unused_argv): 
    training_data = dataset.Dataset("train-00000-of-00001", "train") 
    validation_data = dataset.Dataset("validation-00000-of-00001", "validation") 

    config = tf.ConfigProto() 
    config.gpu_options.allow_growth = True 

    sess = tf.InteractiveSession(config=config) 


    feature_classifier = learn.Estimator(model_fn=cnn_model_fn, model_dir="/tmp/feature_model") 
    tensors_to_log = {"probabilities": "softmax_tensor"} 
    logging_hook = tf.train.LoggingTensorHook(tensors=tensors_to_log, every_n_iter=50) 

    feature_classifier.fit(input_fn=lambda:image_processing.inputs(training_data, batch_size), steps=200000, monitors=[logging_hook]) 
    metrics = { "accuracy": learn.MetricSpec(metric_fn=tf.metrics.accuracy, prediction_key="classes"), 
    } 

if __name__ == "__main__": 
    tf.app.run() 

是我喂的数据的方式错了吗？

Answer 1

根据我的理解，大张量来自cnn_model_fn中的第一个完全连接层dense。经过两次合并后，原始尺寸从200x200减少到50x50，具有64个过滤器映射，因此dense的输入形状为[无，64,50,50]，并且必须具有形状[64 * 50 * 50,1024 ]，这正是错误消息报告的内容。这是参数的大小，与batch_size无关。尝试减少参数的数量或使用更多内存更好的GPU。