Wang Junfu

icon company Beihang University, IRIP Lab

Results 5 comments of Wang Junfu

add binary fully connected operator

Hi, there @AdamHillier @Tombana @arashb @lgeiger > This wouldn't be particularly fast (though it would hopefully be faster than float dense layers), because our optimised binary convolution kernels operate on...

Bool input tensor

Thanks for your reply. It helps me a lot. Besides, how can I use int8 input in LCE benchmark? When I directly modify the dtype of input tensor, it raises...

Bool input tensor

I get it. Thank you!

Bool input tensor

Hi @Tombana , sorry for reopening this issue. After learning more about larq compute engine, I have two new questions. As discussed above, ```python X_in = Input(shape=(1, 1, 1024), batch_size=1024,...

Bool input tensor

@Tombana , thanks for your suggestion! I have successfully removed the `float32` input tensor by extending the `strip_lcedequantize_ops` function.