• Tensorflow训练FashionMnist数据集报错：
  WARNING:tensorflow:Model was constructed with shape (None, 28, 28) for input KerasTensor(type_spec=TensorSpec(shape=(None, 28, 28), dtype=tf.float32, name=‘flatten_input’), name=‘flatten_input’, description=“created by layer ‘flatten_input’”), but it was called on an input with incompatible shape (None, 28).
  
• 解决方案：
  代码修改：
  
  使用reshape(1, 28, 28)

print(np.argmax(model.predict([[(test_images[0]/255).reshape(1, 28, 28)]])))

• 成功运行
  模型训练的不错，预测值与标签值相同