Tensorflow MNIST: terminating a call after invoking an instance of 'std :: bad_alloc'

Question

I am trying to implement a minimized neural network on Tensorflow using their default MNIST dataset.

from __future__ import print_function import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets('MNIST_data', one_hot=True) def compute_accuracy(v_xs, v_ys): global prediction y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1}) correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1}) return result def weight_variable(shape): initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial) def bias_variable(shape): initial = tf.constant(0.1, shape=shape) return tf.Variable(initial) def conv2d(x, W): # stride [1, x_movement, y_movement, 1] # Must have strides[0] = strides[3] = 1 return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') def max_pool_2x2(x): # stride [1, x_movement, y_movement, 1] return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME') # define placeholder for inputs to network xs = tf.placeholder(tf.float32, [None, 784]) # 28x28 ys = tf.placeholder(tf.float32, [None, 10]) keep_prob = tf.placeholder(tf.float32) x_image = tf.reshape(xs, [-1, 28, 28, 1]) # print(x_image.shape) # [n_samples, 28,28,1] ## conv1 layer ## W_conv1 = weight_variable([5,5, 1,32]) # patch 5x5, in size 1, out size 32 b_conv1 = bias_variable([32]) h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 28x28x32 h_pool1 = max_pool_2x2(h_conv1) # output size 14x14x32 ## conv2 layer ## W_conv2 = weight_variable([5,5, 32, 64]) # patch 5x5, in size 32, out size 64 b_conv2 = bias_variable([64]) h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 14x14x64 h_pool2 = max_pool_2x2(h_conv2) # output size 7x7x64 ## fc1 layer ## W_fc1 = weight_variable([7*7*64, 1024]) b_fc1 = bias_variable([1024]) # [n_samples, 7, 7, 64] ->> [n_samples, 7*7*64] h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64]) h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) ## fc2 layer ## W_fc2 = weight_variable([1024, 10]) b_fc2 = bias_variable([10]) prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) # the error between prediction and real data cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction), reduction_indices=[1])) # loss train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) sess = tf.Session() sess.run(tf.global_variables_initializer()) for i in range(100): batch_xs, batch_ys = mnist.train.next_batch(10) sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5}) if i % 10 == 0: print(compute_accuracy( mnist.test.images, mnist.test.labels)) 

When python is executed with this message, the: terminate call after an instance of 'std :: bad_alloc' what () is called: std :: bad_alloc

I was able to indicate that this happens when I call the compute_accuracy function or generally when I load all the mnist.test iamges and tags. Any suggestions on what can be done, given that I want to use this data. I could work with images in general, in another case.

Answer 1

I think you do not have enough memory. It works fine on my machine (6GB graphics card). Try reducing the batch size or using a smaller fully connected layer.

Answer 2

I had the same problem. I resolved it by reducing the number of test images in order to calculate the accuracy, for example. I replaced

 print(compute_accuracy(mnist.test.images, mnist.test.labels)) 

Something like

 batch_test = mnist.test.next_batch(5000) print(compute_accuracy(batch_test[0], batch_test[1]) 

Hope this helps.