TensorFlow訓練MNIST報錯ResourceExhaustedError
阿新 • • 發佈:2018-12-26
mmm feed see resource print test shell pro shape
title: TensorFlow訓練MNIST報錯ResourceExhaustedError
date: 2018-04-01 12:35:44
categories:
- deep learning
tags:
- MNIST
- TensorFlow
在最後測試的一步報錯:
ResourceExhaustedError (see above for traceback): OOM when allocating tensor
搜索了一下才知道是GPU顯存不足(emmmm....)造成的,可以把最後測試的那行代碼改為將測試集分成幾個小部分分別測試最後再求精度的平均值:
accuracy_sum = tf.reduce_sum(tf.cast(correct_prediction, tf.float32)) good = 0 total = 0 for i in range(10): testSet = mnist.test.next_batch(50) good += accuracy_sum.eval(feed_dict={ x: testSet[0], y_: testSet[1], keep_prob: 1.0}) total += testSet[0].shape[0] print ("test accuracy %g"%(good/total))
TensorFlow訓練MNIST報錯ResourceExhaustedError