pytorch-dense-correspondence
pytorch-dense-correspondence copied to clipboard
RobotLocomotion
Code for "Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation"
In order for the Change detection pipeline to work we need to build the Director repository. Unfortunately we are unable to download it from https://dl.bintray.com/patmarion/director/director-$director_version-$director_binary.tar.gz as the link is dead....
Run script in > dense_correspondence/experiments/shoes/training_shoes.ipynb meet a ZeroDivisionError Dataset is > shoe_train_4_shoes.yaml It seems that in some case, the num_matches == 0 cause the error. How to fix it? Error...
I think master is using the default K when computing correspondence. https://github.com/RobotLocomotion/pytorch-dense-correspondence/blob/master/dense_correspondence/dataset/spartan_dataset_masked.py#L655 i added `K=self.get_camera_intrinsics(scene_name).K` also https://github.com/RobotLocomotion/pytorch-dense-correspondence/blob/master/dense_correspondence/dataset/dense_correspondence_dataset_masked.py#L117
I am trying to replicate your work for my own collected dataset and I am getting confused at how to apply change detection on the 3D reconstructed model from TSDF...
Hello, I have implemented this work with Docker and without docker as well (to debug and to understand it). My question is as follows: From what I understand the quantitative...
when we run pytorch dense correspondence code, we encounter the following issue: --------------------------------------------------------------------------- ImportError Traceback (most recent call last) in () 1 import dense_correspondence_manipulation.utils.utils as utils 2 utils.add_dense_correspondence_to_python_path() ----> 3...
I downloaded the shoe data (https://github.com/RobotLocomotion/pytorch-dense-correspondence/blob/master/config/dense_correspondence/dataset/composite/shoes_all.yaml) and tried going through the tutorial training with it. I've received a "warning, empty mask b”, followed by “float division by zero” error. Also,...
I have found that the following code may be not right. https://github.com/RobotLocomotion/pytorch-dense-correspondence/blob/c3b068adca006b828248fdf16b00aa7603d462e2/dense_correspondence/correspondence_tools/correspondence_finder.py#L269 Should it be "ones = torch.ones_like (diffs_0_flattened)" ? And I also interesting in why using line 277 ~280...
Hi, I am referring to lines 499: `depth_vec = torch.index_select(img_a_depth_torch, 0, uv_a_vec_flattened)*1.0/DEPTH_IM_SCALE` and 595: `depth2_vec = torch.index_select(img_b_depth_torch, 0, uv_b_vec_flattened)*1.0/1000` in file [correspondence_finder.py](https://github.com/RobotLocomotion/pytorch-dense-correspondence/blob/76bf6499c325ad136a094fb341158a90eaa31d53/dense_correspondence/correspondence_tools/correspondence_finder.py) If you change the depth scale variable `DEPTH_IM_SCALE`,...
Metadata
Owner
Metadata
Code for "Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation"