我尝试使用：train = optimizer.minimize(loss)，但标准优化器不支持tf.float64。因此我想将我的loss从tf.float64转换为tf.float32。

Traceback (most recent call last):  File "q4.py", line 85, in <module>    train = optimizer.minimize(loss)  File "/Library/Python/2.7/site-packages/tensorflow/python/training/optimizer.py", line 190, in minimize    colocate_gradients_with_ops=colocate_gradients_with_ops)  File "/Library/Python/2.7/site-packages/tensorflow/python/training/optimizer.py", line 229, in compute_gradients    self._assert_valid_dtypes([loss])  File "/Library/Python/2.7/site-packages/tensorflow/python/training/optimizer.py", line 354, in _assert_valid_dtypes    dtype, t.name, [v for v in valid_dtypes]))ValueError: Invalid type tf.float64 for Add_1:0, expected: [tf.float32].

回答：

简短的回答是，您可以使用tf.cast()操作将张量从tf.float64转换为tf.float32：

loss = tf.cast(loss, tf.float32)

更详细的回答是，这并不能解决您在使用优化器时遇到的问题。（对tf.float64的支持不足是一个已知问题。）优化器要求您尝试优化的所有tf.Variable对象也必须是tf.float32类型。