Process many images in parallel
authorMartin Pitt <martin@piware.de>
Sat, 29 Aug 2020 19:29:39 +0000 (21:29 +0200)
committerMartin Pitt <martin@piware.de>
Sun, 30 Aug 2020 09:40:28 +0000 (11:40 +0200)
commit1de3cdb5ecba32a8a3b0a02bbf71e883383a689d
treef1d44473298d6433b76150bfe67a1ef36fab9723
parent8dcd00e9f8bbfc569c9b29ac06d748320d8bf737
Process many images in parallel

Provide one object per NN layer and implement their functionality
separately, like in
https://www.kdnuggets.com/2019/08/numpy-neural-networks-computational-graphs.html

Each layer does not take only one image vector, but a whole 10,000 of
them, which massively speeds up the computation -- much less time spent
in Python iterations.
README.md
nnet.py [new file with mode: 0644]
train.py