Work Update, May 22nd: TF Improvements

[tylermzeller]

TensorFlow

• Training w/ variable learning rates
• Send bias as well as weights
• Generalize client TF for any numbers of parameters (weights and biases) [get_collections in python] Fully Configurable TensorFlow Models #29
  • 1 layer NN Android TensorFlow (with wifi & refractoring changes) #32
  • 2 layer NN, ReLu activations
• Adam optimizer
  • @3ygun in Android TensorFlow (with wifi & refractoring changes) #32 had a model running with the Adam optimizer. But wasn't seeing improved results as implementation bug? E.G. weight accuracy wasn't going >13% (See NOT A BUG : Problem with the server config file #33 for the issue) @3ygun didn't have a proper server config and that resulted in the <20% accuracy 🤕
• Reinit user on parameter update, regardless of state

Refractoring

• See the david-tensorflow branch for Refractor BackgroundDataSend #27 & the tensorflow branch changes. Will merge into tensorflow when it works. Current problems: (All fixed in Android TensorFlow (with wifi & refractoring changes) #32)
  • Believe my server configuration is incorrect
  • Is the trainer correctly cycled between?