loss functions should infer dtype from predictions

[pavithrasv]

Please make sure that this is a Bug or a Feature Request and provide all applicable information asked by the template.
If your issue is an implementation question, please ask your question on StackOverflow or on the Keras Slack channel instead of opening a GitHub issue.

System information

• Have I written custom code (as opposed to using example directory):
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04):
• TensorFlow backend (yes / no):
• TensorFlow version:
• Keras version:
• Python version:
• CUDA/cuDNN version:
• GPU model and memory:

You can obtain the TensorFlow version with:
python -c "import tensorflow as tf; print(tf.GIT_VERSION, tf.VERSION)"
You can obtain the Keras version with:
python -c 'import keras as k; print(k.version)'

Describe the current behavior
def mean_squared_error(y_true, y_pred):
if not K.is_tensor(y_pred):
y_pred = K.constant(y_pred)
y_true = K.cast(y_true, y_pred.dtype)
return K.mean(K.square(y_pred - y_true), axis=-1)

y_pred is always converted to float32 because of K.constant call.

Describe the expected behavior
pass dtype to the K.constant call

Code to reproduce the issue
Provide a reproducible test case that is the bare minimum necessary to generate the problem.

Other info / logs
Include any logs or source code that would be helpful to diagnose the problem. If including tracebacks, please include the full traceback. Large logs and files should be attached.

[sushreebarsa]

@pavithrasv Could you please refer to this link and let us know if it helps ?
In order to expedite the trouble-shooting process, please provide a code snippet to reproduce the issue reported here. Thanks!

[sushreebarsa]

Closing this issue due to lack of recent activity & assuming this issue as resolved .Please feel free to reopen if you still have concern .Thanks!