我正在使用 Tensorflow 在 CPU 上进行 CIFAR-10 培训。在前几轮比赛中，输球似乎还不错。但是在步骤 10210 之后，损失会发生变化并最终变为 NaN。
我的网络模型来自他们网站的 CIFAR-10 CNN 模型。这是我的设置，
image_size = 32
num_channels = 3
num_classes = 10
num_batches_to_run = 50000
batch_size = 128
eval_batch_size = 64
initial_learning_rate = 0.1
learning_rate_decay_factor = 0.1
num_epochs_per_decay = 350.0
moving_average_decay = 0.9999
结果如下所示。
2017-05-12 21:53:05.125242: step 10210, loss = 4.99 (124.9 examples/sec; 1.025 sec/batch)
2017-05-12 21:53:13.960001: step 10220, loss = 7.55 (139.5 examples/sec; 0.918 sec/batch)
2017-05-12 21:53:23.491228: step 10230, loss = 6.63 (149.5 examples/sec; 0.856 sec/batch)
2017-05-12 21:53:33.355805: …