Comments (9)
@WANGYINGYU @fangchangma Hello, I want to know how to download the kitti depth dataset. I can't download it in the ' http://www.cvlibs.net/datasets/kitti/eval_depth.php?benchmark=depth_completion'. Can you help me?
Thank you!
from self-supervised-depth-completion.
@WANGYINGYU @fangchangma Hello, I want to know how to download the kitti depth dataset. I can't download it in the ' http://www.cvlibs.net/datasets/kitti/eval_depth.php?benchmark=depth_completion'. Can you help me?
Thank you!
First, you need to download the annotated depth map dataset at this URL, and then you need to download the corresponding kitti rgb dataset. This is a tedious job, I have not completed it yet.@xskyz
from self-supervised-depth-completion.
@WANGYINGYU Thank you for your prompt reply!
from self-supervised-depth-completion.
@xskyz If you have a complete dataset or have some progress, you can share it. Thank you.
from self-supervised-depth-completion.
@WANGYINGYU OK~ I will share it if I have some progress.
from self-supervised-depth-completion.
I just uploaded scripts for downloading the corresponding RGB images for KITTI Depth. Please let me know if you have any other questions.
from self-supervised-depth-completion.
@fangchangma Thank you for your download scripts. Now I got an unknown error when I used 'tar -xvf model_best.pth.tar ' to get your pre-trained model. Can you help me?
On the other hand, can you give specific commands for training and testing?
from self-supervised-depth-completion.
@xskyz There is no need to decompress the .tar
file --- that is just the postfix for Pytorch's checkpoints, not a real compressed file. Please load the .tar
file directly using the commands in README.
from self-supervised-depth-completion.
@fangchangma Thank you, and in addition, I want to know how to use your model to inpaint a specific depth map,can you give an example command?
from self-supervised-depth-completion.
Related Issues (20)
- Error while loading "calib_cam_to_cam.txt" - can not reshape the array.
- question about depth-estimation results HOT 2
- What is the network used for single d?
- Why I can't get the result when using the trained model you provided?
- How can I get the result in your paper?
- About extracting trained model HOT 2
- Clip output in model.py
- inference HOT 2
- colorize the depth map HOT 1
- some problem about photometric_loss
- Use your pretrained model: GPU run out of memory. 8.95 gb already allocated
- Save output depth map HOT 1
- dataset extracting
- Training doesn't converge HOT 4
- silog error measurement
- Running Error in train mode sparse+photo HOT 1
- To much warning. HOT 2
- Use Stereo Pair Instead of Temporal Pair for Self-Supervised Training?
- The result cannot be reproduced
- Some questions about the details of the code
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from self-supervised-depth-completion.