- 两个loss函数
- tf.nn.sparse_softmax_cross_entropy_with_logits ()
logits.shape:[batch_size, num_classes]
labels.shape:[batch_size] - tf.nn.softmax_cross_entropy_with_logits_v2()
logits.shape:[batch_size, num_classes]
labels.shape:[batch_size, num_classes]
- 人家写的tensorflow一些常见问题 网址
- multi_gpu出现的问题:
“Variable conv1/weights/ExponentialMovingAverage/ does not exist”
with tf.variable_scope(tf.get_variable_scope()):
for i in xrange(FLAGS.num_gpus):
with tf.device('/gpu:%d' % i):