Qi (Claire) Chen
Qi (Claire) Chen
in your code, you use https://github.com/poodarchu/Det3D/blob/1a674e9c80eb8b6213b2b24d0de15c64fb395b04/det3d/datasets/lyft/lyft_common.py#L58 IN the latest version, "rotate method is deprected. Use `rotate_around_origin` and `rotate_around_box_center` instead"
https://github.com/songdejia/Siamese-RPN-pytorch/blob/master/code_v1.0/train_siamrpn.py#L233 should be x3=x3/ratio
I have this concern because Tensorflow Lite does not support RNN and bilinear sampling for now. From this repo, I could see conv, pooling, some normalizations and fc work.
Hi I tried to test ROIAlign on images with `rois = roi_align(detections, boxes, box_index)` detections' shape is `torch.Size([1, 3, 271, 271])` and boxes looks like `tensor([[ 151.6779, 18.8237, 270.0000, 84.2876],...