In file binary segmentation (camvid).ipynb, block 5, there is:

# Lets look at data we have
dataset = Dataset(x_train_dir, y_train_dir, classes=['car', 'pedestrian'])
image, mask = dataset[5] # get some sample
visualize(
    image=image, 
    cars_mask=mask[..., 0].squeeze(),
    sky_mask=mask[..., 1].squeeze(),
    background_mask=mask[..., 2].squeeze(),
)

here, sky_mask

• 1. add docs to describe the model, explain the arguments (as well as how to configure in recipe) and best pratices. A good reference: https://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science/coxph.html
• 2. use the same parameter name in MTNetForecaster and AutoTS recipes.
• 3. in MTNetGridRandomRecipe, past_seq_len actually is conditioned on time_step and long_num,
  https://gi

Describe the bug

Guide under Tensorflow.js heading needs an update, 'names' flag changed to 'name_policy ' according to latest commit?

Under supported layers heading, ConvTrsnpose2d==ConvTranspose2d?