AutoAlignV2
AutoAlignV2 copied to clipboard
question about “crop_img_patch_with_box” function
Hello, Do you add “crop_img_patch_with_box” in /AutoAlignV2/tools/data_converter/create_gt_database.py? Or is this function from mmdet3d? Thank you.
i have the same question.it will show TypeError: list indices must be integers or slices, not tuple
,right? there are actually a wrong, but do not know the solution. may i get your ways? thanks
File "tools/create_data.py", line 237, in
i meet the question like this. it shows that the org_img_list input only contains one image while we choose 6 images of different views to crop it. so my question is, why only crop one image patches?
Hi, we only choose one view to crop, the first view that has the object, following the order (FRONT, LEFT_FRONT, RIGHT_FRONT, LEFT_BACK, RIGHT_BACK, BACK, maybe). The reason that I crop one image patch is we simply want to reduce the size of GT database.
thanks a lot for your prompt answer~ so in [crop_img_patch_with_box”] function, i may just filter other views like this?
if(num_img ==0) img_patch = org_img_list[0][y1:y1 + h, x1:x1 + w] img_patches.append(img_patch)
where num_img varies from 0 to 5, which means 6 different views gt bboxes.
buaazeus opened this issue on Oct 26, 2022 · 3 co
Hi, we only choose one view to crop, the first view that has the object, following the order (FRONT, LEFT_FRONT, RIGHT_FRONT, LEFT_BACK, RIGHT_BACK, BACK, maybe). The reason that I crop one image patch is we simply want to reduce the size of GT database.
You may have a try. The code should not have this problem since I have used it to generate the database before... it's quite strange... Perhaps I changed it for waymo afterwards.