Comments (6)
Hi @lulianLiu,
You can follow these steps to write the dataloader for your dataset:
- Adapt this file to generate 3D ground truth at 1:8 resolution
- Modile kitti dataset loader with your camera intrinsic parameter. If you predict the 3D scene in the camera coordinate then T_velo_2_cam can be set to np.eye(4)
- You might need to modify voxel_origin and scene size. This define the area of the scene you want to predict
from monoscene.
Hi @lulianLiu, You can follow these steps to write the dataloader for your dataset:
1. Adapt [this file](https://github.com/cv-rits/MonoScene/blob/master/monoscene/data/semantic_kitti/preprocess.py) to generate 3D ground truth at 1:8 resolution 2. Modile [kitti dataset loader](https://github.com/cv-rits/MonoScene/blob/master/monoscene/data/semantic_kitti/kitti_dataset.py#L69) with your camera intrinsic parameter. If you predict the 3D scene in the camera coordinate then T_velo_2_cam can be set to np.eye(4) 3. You might need to modify [voxel_origin and scene size](https://github.com/cv-rits/MonoScene/blob/master/monoscene/data/semantic_kitti/kitti_dataset.py#L41). This define the area of the scene you want to predict
Dear author, if I train by the kitti data. I need to download follow two data?Can I download the kitti(700M) to train and modile the data to make my own data?
from monoscene.
You need the calibaration files and the RGB images which are not in the 700Mb data.
from monoscene.
But the RGB images is too big. Can you provide a small data link to me? and I also want to ask whether only use RGB images to train?
from monoscene.
Sorry, I don't have the smaller dataset. You need to calibration file for the camera intrinsics and 3D ground truth to train
from monoscene.
Hi, @anhquancao How to obtain the .pkl and .bin files from the original NYU dataset?
from monoscene.
Related Issues (20)
- I want to use the test set in the semantic-kitti dataset for inference visualization HOT 8
- How to understand _rle2voxel function HOT 6
- visualize!the image is not perfect
- I am a rookie. 想问一下如果我想用我自己拍的一张照片使用你们的模型来推理,这可行嘛? HOT 13
- Is the Unet2D encoder frozen? HOT 2
- about backbone HOT 1
- train and my dataset HOT 16
- Issue with HuggingFace space with NYU dataset HOT 4
- train other monocular image datasets HOT 1
- Inconsistent results of some baselines HOT 3
- `omegaconf.errors.ConfigAttributeError: Key 'fp_loss' is not in struct` HOT 2
- custom dataset HOT 2
- Failed to produce any outputs HOT 2
- Intuition on Frustum Proportion Loss with non-zeros classes HOT 1
- How to change backbone to others such as ResNet50 HOT 1
- Training issues HOT 21
- about the 3d_recon.gif HOT 2
- Problems about 'Inference on KITTI-360' HOT 3
- Questions regarding NYU Depth V2 class mapping HOT 3
- Problems about visualizing output on my dataset HOT 6
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 monoscene.