Comments (2)
Thanks! After I have added the '--logDispStep 1' option I got the disparity predictions.
I would suggest to add this option to the readme page.
from real-time-self-adaptive-deep-stereo.
I am using /home/dp92/Desktop/deep-stereo/data/kitti/image_00/data/0000000000.png as fake GT, is it OK? or how should it run it without GT?
Yes, it is ok. The GT is only used for evaluation purpose, not for the actual algorithm. Just be sure that the GT you are loading is a 1 channel image (either 8 or 16 bit) and with the same resolution as the left and right frames.
Anyway the process is not completed successfully, What could be the problem?
With newer versions of tensorflow, the try-except block I was using is not properly catching all the exceptions, and when all the image are elaborated the background thread raise an exception.
Looking at your log it might have completed the execution just fine, check if in '~/Desktop/deep-stereo/outputs' there is a file called 'series.csv', it should display one row with some info for each image elaborated.
Moreover, if you run the same script with the additional command line option '--logDispStep 1' it should save in the output folder the disparity predicted by the network.
Apologize for the poor exception handling, I'll improve the code soon.
from real-time-self-adaptive-deep-stereo.
Related Issues (20)
- about the implementation details in MadNet HOT 2
- I want to get right disparity. HOT 3
- Problem when train from scratch HOT 5
- [Feature requested] Could you please provide PyTorch version? HOT 1
- Confusion about loss calculation with loss_factory api HOT 4
- Feature request: Tensorflow lite model HOT 1
- collab example HOT 3
- MADNet's EPE on sceneflow? HOT 1
- How can I get proxy disparity? HOT 1
- failed to load pretrained weights HOT 1
- About correlation layer. HOT 1
- Shape must be rank $ but is rank 3 for 'model/MirrorPad' HOT 3
- Ground-truth of raw data in KITTI dataset HOT 2
- MADNet Tensorflow 2 Implementation HOT 2
- A warning about 'get_proxy_loss' in Stereo_Continual_Adaptation.py HOT 1
- A confusion about the metrics in Tab. 2 of your paper HOT 1
- The problem in data loading HOT 1
- TPAMI code 'NoneType' object cannot be interpreted as an integer
- The size of the picture to inference
- Question about setup and performance on kitti raw dataset
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 real-time-self-adaptive-deep-stereo.