search

zju3dv / disprcnn

Code release for Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation (CVPR 2020, TPAMI 2021)
Apache License 2.0
213 stars 36 forks source link

I solved what i asked before. #4

Closed RohDonghyeon closed 4 years ago

RohDonghyeon commented 4 years ago

I solved what i asked before. Thanks for a lot of help. In the same way, i want to visually check the ground truth value of data > kitti > obejct > training > pob > mask_2. Screenshot from 2020-04-27 18-21-30 I think it's because the dimensions are different, but i wonder if there is another way to visualize it as a 3D image?

Originally posted by @RohDonghyeon in https://github.com/zju3dv/disprcnn/issues/2#issuecomment-619852723

ootts commented 4 years ago

Each mask pseudo-GT has three dimensions, the first dimension is the number of objects which you can find in label_2, and the last two dimensions is the image size. (10, 375,1242) means there are 10 objects. You can perform 'plt.imshow(mask.sum(0))' to visualize the full-image mask, or 'plt.imshow(mask[i])' to visualize the mask of the i-th object.

ootts commented 4 years ago

If there are no more questions, I will close this issue.