TODO List

[sarahaguasvivas]

• neural_network_generator is eating up the first ########################### characters

Done. Thanks Cooper :)

• define layer sizes (input_shape and output_shape) from parser

Done.

• end to end code generator.

Done.

• Activation function lookup

Done. TODO:

• Improve parser/ input/output shape readers

Done!

• Make activation.h and activation.c

Thanks Cooper!

• Make [N][M] and [N][M][K] squisher--> - overload fwdNN( .) or make a prepare window function
  In Progress...

• Figure out what to do when user has custom activation functions

• Weights and biases have the same name--> parser's fault

Done

• write arduino code that uses nn4mc--> Examples ...

• Finish all the installation scripts

• Test dumped code

[sarahaguasvivas]

TODO Dec 12, 2019:

parser: Fix input/output sizes (need to make more robust)
activation: Write code for when activation is mentioned as a separate layer
parser: add PyTorch parser
testing: unit test each layer type
docs: Tidy up documentation
docs: make a website (could be github.io)
layers: RNN, LSTM (Sarah TODO)

[sarahaguasvivas]

Issue closed