Your input ran out of data； interrupting training. Make sure that your dataset or generator can ….

人工智能91
history = model.fit_generator(
      train_generator,
      steps_per_epoch=100,
      epochs=100,
      validation_data=validation_generator,
      validation_steps=50)

Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least steps_per_epoch * epochs batches (in this case, 10000 batches). You may need to use the repeat() function when building your dataset.

翻译：您的输入数据不足；中断训练。确保您的数据集或生成器至少可以生成" steps_per_epoch * epochs "批。 （在本例中为10000批）。在构建数据集时，可能需要使用repeat（）函数。**

我们训练图像有2000张，验证图像1000张，和1000张测试图像。

steps_per_epoch=100，batch_size=32，如此数据应该是3200张，很明显输入训练数据不够。
validation_steps=50，batch_size=32，如此数据应该是1600张，很明显验证数据不够。

因此，改为steps_per_epoch=2000/32≈63，validation_steps=1000/32≈32。

history = model.fit_generator(
      train_generator,
      steps_per_epoch=63,
      epochs=100,
      validation_data=validation_generator,
      validation_steps=32)

可以运行！但是可能还是有些纰漏。

参考链接：

Original: https://blog.csdn.net/baidu_30506559/article/details/121149928
Author: 布拉格沃兹基硕德
Title: Your input ran out of data； interrupting training. Make sure that your dataset or generator can ....