Ka Long

@ahoopes I have checked the hypernetwork in [this notebook](https://github.com/hummosa/Hypernetworks_Keras_TF2/blob/master/Hypernetworks_in_keras_and_tf2.ipynb) From my understanding hypernetwork is a network train the weights and biases in the inference network. Only network weights in the...

I can edit the content in under _post folder but not to rename them. Any idea how to make it work?

I get similar problem. When I rename the original files under _posts, I can only edit the content but not the filename. I hope this can be fixed as long...

I have completed the traning on synthmorph and checked with hypermorph. I am curious if the hypernetwork need to be combined with synthmorph for an automated hyperparameter tuning. One question...

you can get the raw ecg data via serial ports, i am working on python interfaces and you may take a look at my [repo](https://github.com/jackyko1991/HealthyPi-Python-Interface) Streaming package info can be...

You may need to adjust the `config.json` for image patch size (for head data, i recommend to be around 256*256*32 with a 11GB GPU) Also preprocessing pipeline need to be...

I wonder if you are training with Windows environment. The code is only tested on Ubuntu 18.04. The error shows that absl logging environment maybe inconsistent for Windows and Linux...

can we use callback function to update a tqdm progress bar after each iteration?

https://github.com/rapidsai/dask-cuda/blob/590d26ab4d61b785789ee6bacae29c37337e6703/dask_cuda/worker_spec.py#L95 This line seems will override user-specified per worker memory limit, should that be changed?

@quasiben I have tested to utilize all CPUs only need to use all workers no matter if it is with GPU or not. What I am trying to do here...