CHaiDNN
CHaiDNN copied to clipboard
CHaiDNN normalization input
I have a network trained with pixel/255.0 as normalized input
however, i cannot get the correct results. i wonder do chaidnn accept input of pixels/255.0 as input layer? any examples?
i notice that the xiInputRead will call only loadMeanSubtractedDatafromBuffptr and there are no other loadNormalizedInputDatafromBuffptr(inp_mode == 1) or loadPixelMeanSubtractedDatafromBuffptr (inp_mode == 2)
So does it mean it do not support normalized input with pixel/255.0?
I suggest you to create your own input layer if the ones provided don't fit your needs, it's simple.
so are you suggesting to modify the xiInputRead function? can you elaborate how simple is to add a new xiInputRead function? thanks
still stuck in modifying xiInputRead function. i wish to know what is the data type expected for such function?
anyone can help?
Hi, since the pixel/255 will result in input value (-1,1], what is the expected representation of such value? in mean-subtracted case, it is rather understandable. the example use truncated input (as in Trim2FP_Offline). However in the case of pixel/255, the Trim2FixedPoint will makes every input to 0