Comments (5)
Hi! thanks for your interest. The structures are different depends on the datasets.
from scenerf.
Hi! thanks for your interest. The structures are different depends on the datasets.
Thank you for your reply!This is the dataset structure I set up, I only used the KITTI dataset.
But when I train, it remains in this state and does not respond. What is the problem?
from scenerf.
You need to put the content inside data_odometry_color, data_odometry_velodyne to the dataset
folder that contains poses. For example, you can take a look at this code .
Similar for images etc.
from scenerf.
You need to put the content inside data_odometry_color, data_odometry_velodyne to the
dataset
folder that contains poses. For example, you can take a look at this code . Similar for images etc.
I have moved the data set according to the tips you gave, but when I train, I still have this problem and no response. What is the problem? Is there still a problem with my data?
from scenerf.
You should also check if the variable seq_img_paths
is not empty.
Also, your dataloader might stuck. Can you try to set num_workers to 0?
from scenerf.
Related Issues (20)
- Something wrong when I want to compute the depth metrics on all frames in each sequence HOT 7
- Some question about compute_transformation and dataset HOT 10
- Bugs in generate_novel_depths.py HOT 3
- About cam_pts_to_angle HOT 4
- How do I set the data if I want to move the image I acquired with this code? HOT 6
- Are there any changes to the code and configuration for indoor scene reconstruction? HOT 6
- Are this method scene-specific? HOT 2
- train semantickitti problem HOT 2
- Some questions about performance against baseline Adabins HOT 2
- Question about FPS in inference HOT 4
- Asking for preprocess tsdf of 13.84 IoU ckpt HOT 5
- No Module named scenerf" HOT 8
- The details of converting image coordinates to spherical coordinates are somewhat confusing HOT 1
- [Question] 3D reconstruction from image slides HOT 2
- Error in Chekcpoints Saving HOT 1
- Question about Function "depth2disp" HOT 2
- Error with training on single gpu. HOT 5
- depth estimation on other images HOT 3
- Can the scene be reconstructed in 3D? HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from scenerf.