使用 cnn 的 ResourceExhaustedError

Question

在尝试运行我的 3D 卷积神经网络时，我收到以下错误。可能是什么原因？

ResourceExhaustedError（回溯见上文）：分配时出现 OOM 形状张量[54080,1024] [[节点：Variable_10/Adam/Assign = 赋值[T=DT_FLOAT, _class=["loc:@Variable_10"], use_locking=true, 验证形状=真， _device="/job:localhost/replica:0/task:0/gpu:0"](Variable_10/Adam, zeros_4)]]

这是我使用的代码：

import tensorflow as tf
import numpy as np

IMG_SIZE_PX = 50
SLICE_COUNT = 20

n_classes = 2
batch_size = 10

x = tf.placeholder('float')
y = tf.placeholder('float')

keep_rate = 0.8
def conv3d(x, W):
    return tf.nn.conv3d(x, W, strides=[1,1,1,1,1], padding='SAME')

def maxpool3d(x):
    return tf.nn.max_pool3d(x, ksize=[1,2,2,2,1], strides=[1,2,2,2,1], padding='SAME')

def convolutional_neural_network(x):

    weights = {'W_conv1':tf.Variable(tf.random_normal([3,3,3,1,32])),

               'W_conv2':tf.Variable(tf.random_normal([3,3,3,32,64])),

               'W_fc':tf.Variable(tf.random_normal([54080,1024])),
               'out':tf.Variable(tf.random_normal([1024, n_classes]))}

    biases = {'b_conv1':tf.Variable(tf.random_normal([32])),
               'b_conv2':tf.Variable(tf.random_normal([64])),
               'b_fc':tf.Variable(tf.random_normal([1024])),
               'out':tf.Variable(tf.random_normal([n_classes]))}


    x = tf.reshape(x, shape=[-1, IMG_SIZE_PX, IMG_SIZE_PX, SLICE_COUNT, 1])

    conv1 = tf.nn.relu(conv3d(x, weights['W_conv1']) + biases['b_conv1'])
    conv1 = maxpool3d(conv1)


    conv2 = tf.nn.relu(conv3d(conv1, weights['W_conv2']) + biases['b_conv2'])
    conv2 = maxpool3d(conv2)

    fc = tf.reshape(conv2,[-1, 54080])
    fc = tf.nn.relu(tf.matmul(fc, weights['W_fc'])+biases['b_fc'])
    fc = tf.nn.dropout(fc, keep_rate)

    output = tf.matmul(fc, weights['out'])+biases['out']

    return output

much_data = np.load('muchdata-50-50-20.npy')
# If you are working with the basic sample data, use maybe 2 instead of 100 here... you don't have enough data to really do this
train_data = much_data[:-100]
validation_data = much_data[-100:]


def train_neural_network(x):
    prediction = convolutional_neural_network(x)
    cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits=prediction,labels=y) )
    optimizer = tf.train.AdamOptimizer(learning_rate=1e-3).minimize(cost)

    hm_epochs = 10
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())

        successful_runs = 0
        total_runs = 0

        for epoch in range(hm_epochs):
            epoch_loss = 0
            for data in train_data:
                total_runs += 1
                try:
                    X = data[0]
                    Y = data[1]
                    _, c = sess.run([optimizer, cost], feed_dict={x: X, y: Y})
                    epoch_loss += c
                    successful_runs += 1
                except Exception as e:
                    # I am passing for the sake of notebook space, but we are getting 1 shaping issue from one 
                    # input tensor. Not sure why, will have to look into it. Guessing it's
                    # one of the depths that doesn't come to 20.
                    pass
                    #print(str(e))

            print('Epoch', epoch+1, 'completed out of',hm_epochs,'loss:',epoch_loss)

            correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
            accuracy = tf.reduce_mean(tf.cast(correct, 'float'))

            print('Accuracy:',accuracy.eval({x:[i[0] for i in validation_data], y:[i[1] for i in validation_data]}))

        print('Done. Finishing accuracy:')
        print('Accuracy:',accuracy.eval({x:[i[0] for i in validation_data], y:[i[1] for i in validation_data]}))

        print('fitment percent:',successful_runs/total_runs)

train_neural_network(x)

我正在使用 tensorflow-gpu 版本运行它。我正在使用 GTX970M 并已安装 CUDA 并正确导入了 cudnn 文件。运行最后一个命令时，出现以下错误。请帮忙！

Answer 1

由于某些原因，您的内存不足。 可能是您有一些应用程序正在使用您的 GPU（例如，另一个 tensorflow 会话仍然处于活动状态）。检查是否不是这种情况。 （你可以使用nvidia-smi 来监控）。

如果不是这样，那主要是因为您的模型大小和 GPU 内存的大小。你可以做的是尝试在 CPU 模式下启动它，用 tf.Variables 列出所有变量，计算它代表多少内存，看看它是否适合你的 GPU。

在您完成此操作之前，我无法提供更多建议。