Closed nttstar closed 2 years ago
For CONV layers, we calculate FLOPs as the following:
FLOPs_conv = (2 * C_in * K * K - bias) * (C_out // groups) * H_out * W_out
So the FLOPs of CONV layers in our 85K-param model is about 0.767 GFLOPs under a 640x480 input.
More details will be released on https://github.com/ShiqiYu/libfacedetection.train once we clear our code.
@fengyuentau Thanks! So for pytorch style computation, it should be around 0.38G FLOPs.
Hi, how about the FLOPs of your new v3 CNN model(under 640x480 input)?