Adding types on the public API surface would allow us to do some runtime type checking later on and would allow user's IDE to have more info for static analysis.

The functions/signatures to type are the ones listed here https://github.com/keras-team/autokeras/blob/master/autokeras/__init__.py

For the context, see #856 where I add some type information on a ImageClassifier.

This issue can

What would you like to be added: As title

Why is this needed: All pruning schedule except AGPPruner only support level, L1, L2. While there are FPGM, APoZ, MeanActivation and Taylor, it would be much better if we can choose any pruner with any pruning schedule.

**Without this feature, how does current nni

We would like to forward a particular 'key' column which is part of the features to appear alongside the predictions - this is to be able to identify to which set of features a particular prediction belongs to. Here is an example of predictions output using the tensorflow.contrib.estimator.multi_class_head:

{"classes": ["0", "1", "2", "3", "4", "5", "6", "7", "8", "9"],
 "scores": [0.068196

Hi Jiahui,

Thanks for the great work. I'm trying to reproduce AutoSlim for CIFAR-10 (Table 2).
Could you please provide a detailed hyperparameter you used for it?

I'm able to train the baseline MobileNetV2 1.0x to 7.9 Top-1 error using the following hyperparameters:

• 0.1 initial learning rate
• linear learning rate decay
• 128 batch size
• 300 epochs of training
• 5e-4 weight decay

In the code, it seems that you use the model stored in ema to do the validation and get the final result.Here i have two questions:
1.Why do you use the ema model to do the validation, but do not use the model_wrapper which is directely preuned?
2.Is it supposed that ema model will get better result than model_wrapper?And why?
Thanks very much for your reply!