MonoDTR
MonoDTR copied to clipboard
MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer (CVPR 2022)
where is this imdb.pkl file?
Hi! Thank for you great work!  I saw that in monodtr_core you have do this. I think it must be img_feat = img_feat.permute(0,2,3,1).view(N,H*W,C)
./launchers/det_precompute.sh config/config.py train Precomputation for the training/validation split start reading training data training split finished precomputing06s, eta:0.70s, **total_objs:[11670, 2156, 706], usable_objs:[11670, 2105, 700]]** start reading validation data **validation split finished...
Hi @KuanchihHuang, Thanks for your great work, I am doing research on your model. I have problem when I use my custom data. I use VisualDet3D code to reshape my...
Thanks for sharing the codes of such a good method. I am wondering could you please send the anchor_mean_Car.npy generate from KITTI to me. my email is [email protected]. Best,
Hello and thanks for your great work! I want to visualize the attention diagram in the dtr, and I would like to ask if the value of attention is the...
Hi, Thanks for your great work and this awesome released code. But I encountered some problems to reproduce the performance on KITTI test set. I used the provided code to...
Hi Thanks for this work. The README says only single GPU is supported. But your code has DDP code. Is it fully supported yet? Any updates on this end? Thanks
Hi, could you provide the same installation setup for CUDA 11.0 ? The makefile for deformable convolution doesn't seem to run for CUDA 11.0
Hi, Do you have any advice with regards to training MonoDTR algorithm to another dataset? Basically I have a dataset in KITTI format: images, annotation, pointcloud, calibration between the camera...