Open guker opened 1 year ago
I haven't looked at this repository in a while so I don't remember all the details. But the main reason is the input image is 256x256 pixels while the predicted heatmaps is 64x64. So when you downsample the image, the intrinsic matrix of the camera must also be modified. n = -2
here actually means 1/4
rescale. The intrinsic matrix can be modified by just multiplying the projection matrix from the left. For more details, look here: link
I got it, thanks
https://github.com/TemugeB/CDRnet/blob/c130864902083ae2d992d53b56ba15907b23d993/train_and_test.py#L109 why use resized_mat@pms_v1?