aaronwool / rcvpose Goto Github PK
View Code? Open in Web Editor NEW(ECCV 22 Oral)Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting
License: GNU General Public License v3.0
(ECCV 22 Oral)Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting
License: GNU General Public License v3.0
Line 518 in e25ff74
Thanks for the great work!
I want to download the dispersed keypoints resource, but the link is no longer available. It would be appreciated that you could update the link.
Hi,
while testing the RCVPose I get sem_out variable always all zeros at line 556 of AccumulatorSpace.py. To solve, is it possible that we have to multiply the variable by 1000 like here: sem_out = np.where(sem_out*1000>0.8,1,0) ?
Thanks
Hi,
I want to experiment with LINEMOD_OCCLUSION dataset.
Do you have any plan to reveal the codes and pretrained-weights for LINEMOD_OCCLUSION?
Thanks.
There seem to exist discrepancies in LINEMOD_ORIG and LINEMOD w.r.t. masks - some of them simply are not available in LINEMOD, the algorithm then crashes.
The download of the dataset, the folder structure creation and pruning should be performed within another script. The manual labor becomes confusing and is very error prone.
Hi,
thanks for the great work. I am testing RCVPose but got the following error:
center_mm_s = Accumulator_3D(xyz, xyz_load_transformed, radial_list, pixel_coor)
TypeError: Accumulator_3D() takes 2 positional arguments but 4 were given
The function is defined for two inputs as arguments. Can you help here?
Best
Hello,
Can someone provide a download link to the LINEMOD_ORIG dataset? The links in the readme are outdated and the sharepoint doesn't exist anymore. If anyone has the LINEMOD and the LINEMOD_ORIG dataset, I will be very glad. The LINEMOD can be downloaded by the BOP website that is linked, but there is no LINEMOD_ORIG as I can see.
Thank you very much!
Hi, thanks for sharing so nice work.
Could you mind sharing the code to reproduce experiment results in YCB dataset about training and testing part ?
(venv310) blab@blab-server:~/pporzz/rcvpose$ python main.py --root_dataset="/home/bimlab/pporzz/rcvpose/Datasets/6dPoseData/" --mode=test --demo_mode True
ape
Traceback (most recent call last):
File "/home/bimlab/pporzz/rcvpose/main.py", line 70, in
trainer = Trainer(data, opts, vis)
File "/home/bimlab/pporzz/rcvpose/train.py", line 25, in init
self.Test()
File "/home/bimlab/pporzz/rcvpose/train.py", line 194, in Test
estimate_6d_pose_lm(self.opts)
File "/home/bimlab/pporzz/rcvpose/AccumulatorSpace.py", line 518, in estimate_6d_pose_lm
model_path = opts.model_dir + class_name+"_pt"+str(keypoint_count)+".pth.tar"
UnboundLocalError: local variable 'keypoint_count' referenced before assignment
I don't have any ideas on this issue. Can someone help me? Or give a hint?
Could you please update the download-Link for the Linemod-dataset.
The current one is not working and the BOP-Dataset has another format.
Hey, I am trying to run the code with your pretrained weights. (without training it by myself)
How to run the code just for testing/visualization?
Following your guide:
when running python3 main.py --root_dataset="datasets/" --mode=test --demo_mode=True
I am getting the next error:
FileNotFoundError: [Errno 2] No such file or directory: 'datasets/LINEMOD/ape/Split/train.txt'
or 'datasets/LINEMOD/ape/Split/val.txt'
that because there is not Split directory (the ape/Split/
doesn't exist) but instead the files inside the ape/
folder
Can you please try to edit the guide for us to run your code from scratch?
Thanks for your great work!
Zengo‘s products , must be fine !
Line 499 in e25ff74
Hello. I'm looking to use my custom dataset with rcvpose.
What values are present in outside9.npy, which is needed for training?
For example I am using the demo I get the next error when I try your visualization option.
IndexError: index 816 is out of bounds for axis 1 with size 640```
The requirements_simplified.txt file is invalid.
You might need to consider employing "==" or ">=" for installing the required packages.
Further the pip command is not correct.
It should be
pip install -r requirements_simplified.txt
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.