Lance Norskog
Lance Norskog
This has support for Basic Auth. It required changes in the wordpress part and in the SolrPhpClient. I'm not a PHP coder (your favorite thing to hear :) and I...
I use a few libraries that have custom Keras layers, and generate complex graphs inside these layers. Some are algorithmic and generate, say, 20 nodes N times. Some way to...
The output section of every Keras graph is complex, and has a long chain of TF nodes that uses up a lot of screen space. Request some way to Prune...
This page, section iii, has an excellent interactive lab of how neural network weight initializations work. I previously understood the "generally accepted wisdom", but this shows why. http://www.deeplearning.ai/ai-notes/initialization/ It might...
This does not look to be the final version of your code. The features file is created, but is not used by deepnet.py, for example. Also, I've got deepnet.py generally...
Please describe the amount of work required to expand this tool to supporting Azure or Google Cloud "file blob" S3-alike services. I work at a (very large) company that is...
A request
I would like to request a philosophy statement, or statement of purpose, for the Keras framework. It would address things like - A backend must support all features in a...
@beresandras Running the Denoising Diffusion Implicit Model in Tensorflow and Keras 2.9.0 gives this error stack: --------------------------------------------------------------------------- UnimplementedError Traceback (most recent call last) [](https://localhost:8080/#) in () 33 callbacks=[ 34 keras.callbacks.LambdaCallback(on_epoch_end=model.plot_images),...
Setting the keep probability is only possible during eager evaluation. How can it be made to work during the training phase?
Also, think about adding a Colab notebook. I've done all of my work there. It is (mostly) usable, and enforces a reproducible style of development.