Gradient Implementation

ehw-fit / tf-approximate

Approximate layers - TensorFlow extension

MIT License

26 stars 10 forks source link

Gradient Implementation #6

Closed AaronJing closed 4 years ago

AaronJing commented 4 years ago

Great Work! Just some questions. For the gradient part, I did not see the actual implementation for gradient operation, but only register using official implementation. If I missed it, please correct me. In this case, are you using approximation only in forwarding stage? Thanks.

pilipovicr commented 4 years ago

Related to the topic: Can you train the models with approximate layers (FakeApproxConv2D)?

AaronJing commented 4 years ago

Only support inference