Comments (4)
Do I need to make changes here??
Yes. If you resize the images, the intrinsics should be adjusted accordingly.
from self-supervised-depth-completion.
I can run in 2 or 4 GTX 1080Ti. I think you should use GPU memory more than 16G.
from self-supervised-depth-completion.
RuntimeError: CUDA out of memory
As @AbnerCSZ mentioned, it is due to limited GPU memory. You could try with a simpler model or a smaller image size.
from self-supervised-depth-completion.
@fangchangma, referring to this part of the code in kitti_loader.py:
note: we will take the center crop of the images during augmentation
# that changes the optical centers, but not focal lengths
K[0,2] = K[0,2] - 13 # from width = 1242 to 1216, with a 13-pixel cut on both sides
K[1,2] = K[1,2] - 11.5 # from width = 375 to 352, with a 11.5-pixel cut on both sides
Do I need to make changes here??
Or shall I directly resize the rgb and depth image??
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.