clean-pvnet
clean-pvnet copied to clipboard
zju3dv
Code for "PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation" CVPR 2019 oral
Could you please share the instruction for getting inference on a single test image for a model that is trained with custom dataset following your instruction?
Could you please help how to fix this? ``` eta: 0:00:12 epoch: 0 step: 280 vote_loss: 0.1839 seg_loss: 0.0552 loss: 0.2391 data: 0.0541 batch: 0.3603 lr: 0.001000 max_mem: 18299 eta:...
ℹ️ Ensure Compatibility with Newer PyTorch and CUDA Versions for RANSAC Voting Layer 🚀 Summary: This commit updates the RANSAC voting module to ensure compatibility with the latest PyTorch and...
I am struggling to find any sort of documentation that shows how you have converted the original LINEMOD which looks like below: ``` (clean-pvnet) mona@ada:/data2/data/BOP/lm/train_pbr/000000$ ls total 8.0M drwxrwxrwx 52...
I have created a custom synthetic dataset using BlenderProc of my own custom 3D model that follows Linemod format. ``` (blenderproc) mona@ada:~/BlenderProc/examples/datasets/bop_challenge/output_data/bop_data/lm/train_pbr/000000$ ls total 2.4M drwxrwxr-x 3 mona mona 4.0K...
network = make_network(cfg).cuda() load_network(network, cfg.model_dir, epoch=cfg.test.epoch) network.eval() # export onnx dummy = torch.zeros(1, 3, 1024, 2048).cuda() torch.onnx.export(network, dummy, "cat.onnx", input_names=["image"], output_names=["output"], opset_version=11) RuntimeError: Exporting the operator uniform to ONNX opset...
I'm training on my own dataset. I found `ransac_voting_layer_v3` generate wrong 2d keypoints even using the ground truth `vertex` in the `__getitem__` function of `lib/datasets/custom/pvnet.py`. However, using the `ransac_voting_layer` can...
I wanted to know if anyone tried to use pvnet for realtime pose estimation? I want to do that. If you recommend me a documents or resources to read and...
