-
Notifications
You must be signed in to change notification settings - Fork 10
Open
Labels
Description
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-tensorflowbranch for Refractor BackgroundDataSend #27 & thetensorflowbranch changes. Will merge intotensorflowwhen 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?
Reactions are currently unavailable