Suggestion for better test_indices

[ychong]

Hi I would like to propose a better implementation for 'test_indices':

We can remove the unneeded np.array casting:

Cleaner/New:
test_indices = list(set(range(len(texts))) - set(train_indices))

Old:
test_indices = np.array(list(set(range(len(texts))) - set(train_indices)))

[nfmcclure]

Thanks! I'll look into this. Do you know where specifically you want this changed?

[ychong]

Hi Nick thanks for replying. Yes I didn't make it clear earlier. It's just clearer syntax. You can change it under Chapter 07 Neural Network - improving_linear_regression.py, and other similar implementation as well.

[12744746]

Hi Everyone
could you please let me know for the classification part is the following data set suitable to build classification model for point Cloud.
https://shapenet.cs.stanford.edu/media/modelnet40_ply_hdf5_2048.zip,

thanks