EngrStudent

raw install has ray problem

1

### Search before asking - [X] I have searched the MuZero [issues](https://github.com/werner-duvaud/muzero-general/issues) and found no similar bug report. ### 🐛 Describe the bug I created new venv, then installed per...

the "keras_contrib.layers.normalization.instancenormalization" has been deprecated, and the content moved to tensorflow-addons. https://github.com/keras-team/keras-contrib Also, it requires pip to install instead of just conda, which makes it a little less easy to...

Suggestion: Apply to infection prediction

1

My kids currently (~ww33'21) have hand-foot-mouth and I was looking at the papers and articles on the subject to try and get vague sense of how long they will be...

root_dir in main is hard-coded for hfawaz-datas

1

############################################### main root_dir = '/b/home/uha/hfawaz-datas/temp-dl-tsc/' xps = ['use_bottleneck', 'use_residual', 'nb_filters', 'depth', 'kernel_size', 'batch_size']

It doesn't compile in the newest cython. Compile requires downgrade to cython 0.27.3. ([link](https://github.com/scikit-learn/scikit-learn/issues/10947)) It also wants for keras, which is part of the example instructions, but not part of...

contrib slim doesn't exist for 2.0, and looks to require substantial reworking. https://www.tensorflow.org/guide/migrate#a_note_on_slim_contriblayers

Does not play well with Keras

1

Disclaimer: new to the tf framework. Problem: When I try to apply it to Keras, it does not play well. I use these as prototypes. - https://keras.io/layers/writing-your-own-keras-layers/ - https://www.tensorflow.org/guide/keras/custom_layers_and_models

Process: 1. Downloaded zip, extracted into a useful directory. --> OK 2. Opened README.md, started working through "Getting Started" 3. in terminal, in directory, ran "pip3 install -r requirements. txt"...

this code in the notebook: `# loading the data into numpy arrays source_image_path = "../data/preprocessed_data/source.npy" target_image_path = "../data/preprocessed_data/target.npy" source = np.load(source_image_path) target = np.load(target_image_path)` yields this: `FileNotFoundError: [Errno 2] No...

Scoring for metrics and losses,

8

Disclaimer: I'm an engineer by training, not a statistician, so I can get this wrong. I don't know that the general thrust has technical gaps, but I could be off...