Charles Weill

AdaNet works on GPU just like any other TensorFlow Estimator. Any guide on the web to do GPU training should get you started. You can also try GPU on Colab...

@svjack: We may open source some of our complexity measures including Standard Deviation. Currently the one we have in adanet_objective.ipynb is `sqrt(d)` where `d` is the number of hidden layers....

@jheffez Our team has mostly looked into applying adanet to supervised learning tasks, and some semi-supervised learning work. If you think there is a good way to use adanet for...

@SmallyolkLiu: Did you find the answer to your original question?

If you want to use the latest checkpoint, just recreate the same `adanet.Estimator` with the same `model_dir`. When you call `Estimator#predict` it will load the variables from the latest checkpoint....

Could it be that `tf.estimator.EvalSpec` did not support `None` steps in TF 1.8?

@yuezhilanyi: Could you please copy the full log from start to end? It's not clear what is raising this `TypeError`. In the meantime you can use Colab to run the...

Can you try upgrading to TF 1.9+? We recently bumped our minimum version to 1.9.

Unfortunately, I won't be able to look into TF 1.8 support for a while. If you figure out the source of the issue, feel free to submit a PR.

@AnnMariaW: I'd recommend first trying out [our tutorial notebooks](https://github.com/tensorflow/adanet/tree/master/adanet/examples/tutorials) to get a feel for how AdaNet works. Once you have some suggestions for how we can improve, please let us...