jarlva

[request] intel ice lake AVX512 support?

1

Hey, Intel's recent ice-lake cpu have some nifty AI-based tricks, like AVX512. Also, Ice-lake comes with the Iris plus GPU. It has some major speed improvements matching some of Nvidia's...

[question] Utility to convert json export into code?

1

Hi, is there a way to convert an existing panel/dashboard into python code (or similar)? The intent is to jump-start dashboard-as-code for existing dashboards. Thus saving conversion time.

Dopamine duplicate Gym functionality

9

I spent a lot of time trying to understand the colab cartpole Gym example so to apply to a custom discrete Gym environment, which is similar to the cartpole gym...

Is there a way, or AutoML tool like Adanet/mcfly, that we can use to optimize model/parameters? [https://github.com/tensorflow/adanet](url)

TRPO "underflow encountered in multiply"

2

While running a TRPO train, after some time (random - anywhere from 15sec to 1min) it kicks with the following: `Traceback (most recent call last): File "callback.py", line 196, in...

[question] adanet with Reinforcement Learning?

1

RL is very time and resource intensive, often taking hours and days to complete. Any reduction/optimization is a huge benefit. Has anyone tried to apply adanet with RL?

TF 2.0?

2

Hi, any plans to update to Tensorflow 2 (and preferably tf.keras while at it)?

Adanet?

2

Hi All, It seems that more and more, Tensorflow-derived projects could benefit from each other. For example, using the tensorflow/AdaNet AutoML to find the best TF model, In addition, ability...

Hey group, As you know pip and conda don't work with pyjp in Windows. Do you have any plans to support Windows?

[question] Feature importance?

2

Hi, Let's say we have a bunch of features (> 100) and the model is trained and working (but took forever to train). Is there a way to tell which...