letdivedeep
letdivedeep
@JiawangBian thanks for your inputs. it Worked !!
@JiawangBian I used the kitti pretrained model to infer on some images using the inference.sh script The depth map were stored in the .npy dir structure. we read the file...
@JiawangBian Thanks for your quick reply I checked the [test.py](https://github.com/JiawangBian/sc_depth_pl/blob/master/test.py) and found that an function compute_errors is called to calculate the errors ``` for i, (tgt_img, gt_depth) in enumerate(tqdm(test_loader)): pred_depth...
@JiawangBian I tried with above approch as illustrated in the following code base : ``` def find_distances(gt_depth_map,pt_depth_map, pred_bboxes, img, method="closest"): depth_list = [] h, w, _ = img.shape for box...
Hi @YuanLiuuuuuu Thanks for the reply. Can use the pretrained vit encoder as backbone and use the yolox head or any single stage detector head. If so what should be...
@YuanLiuuuuuu Thanks for the inputs, i am trying to follow the PR, but this is for Mask-RCNN . what needs to be changed to make vit backbone work with yolox....
Kudos @hollance. Thanks for your reply. I tried the above approach, it worked.
@YuanLiuuuuuu Thanks for your response. I ran the above command by which I was able to resolve the issue. But this was all working with a torch version of ```...
@YuanLiuuuuuu 1.x can work with pytorch 1.10
> Did you solve this problem? No @YuanLiuuuuuu, I was not able to solve the above problem, so just wanted to check if 1.x works with pytorch 1.10 ... As...