A more consistent and multi-functional global level of verbosity control,
suggest an enhancement that will see print(...) in project be converted to using the python logging. module

import logging
#Then instead of print() use either
logging.info(......)
#or
logging.debug(.....)
#or
logging.warning(....)
#or
#logging.error()

In that way verbosity can be globally

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

The 2x down-sampling is one of the important operations in reference models. But, a convolution or a pooling with stride=2, padding='SAME' may result in different outputs over different deep learning libraries (e.g., TensorFlow, CNTK, Theano, Caffe, Torch, ...) due to their different padding behaviors.

For example (TensorNets syntax; but can be regarded as pseudo codes for other libraries),

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?

pip insatll tensorflow==2.0.0 or pip install tensorflow==2.0.0-beta1，tensorflow2.0.0or tensorflow2.0.0-beta1,but when I run train.py, the error of "ValueError: This converter can only convert a single ConcreteFunction. Converting multiple functions is under development" appears,why?How to do?