Comments (2)
No, it contains 7480 training labels provided with the KITTI dataset. You can get them from here.
from voxelnet.
I've read the readme several times, and I have the same doubt as @wutaoo
The instruction says, we should download these following zip files:
- Velodyne point clouds (29 GB): input data to VoxelNet
- Training labels of object data set (5 MB): input label to VoxelNet
- Camera calibration matrices of object data set (16 MB): for visualization of predictions
- Left color images of object data set (12 GB): for visualization of predictions
For the 2nd one, however, there is only one training folder, not the same as the others with both training and testing folders, which leads to the data lacking problem:
└── DATA_DIR
├── training <-- training data
| ├── image_2
| ├── label_2
| └── velodyne
└── validation <--- evaluation data
| ├── image_2
| ├── label_2 (have a little problem, do not have these data)
| └── velodyne
So I am wondering how we update the testing data file path for label_2 in the launch_test.sh to replace "#GT_DIR=/media/hdc/KITTI/for_voxelnet/cropped_dataset/validation/label_2".
From your previous post on May 27 @zemahran , I assume that you meant to copy the training label_2 as the validating data. Maybe I misunderstood or missed something important in the instructions, thanks a lot if you guys can give me some indications @zemahran @qianguih
from voxelnet.
Related Issues (20)
- 帮忙看一下问题可以吗
- should we use rotate iou?
- Here is a non-commercial Wechat group for discussing the lidar-based perception technologies. Welcome to join us. HOT 9
- prediction skipped due to error HOT 2
- ModuleNotFoundError: No module named 'utils.box_overlaps' HOT 3
- Issue with 'training' paramter for batchnormalization of 3d convolution
- problem about multi gpus HOT 1
- Invalid argument Error :coordinate has shape(batch_size,K,4) while voxelwise has shape(batch_size,K,128)How can we apply scatter_nd? In FeatureNet, self.outputs = tf.scatter_nd(self.coordinate, voxelwise, [self.batch_size, 10, cfg.INPUT_HEIGHT, cfg.INPUT_WIDTH, 128])
- For pedestrian/cyclist training HOT 8
- Anaconda environment
- The program is stuck during running and cannot continue to run
- Training the voxel net for different objects at a time? HOT 6
- KITTI/data/validation/label_2/ folder is empty, how to train the voxelnet model? HOT 2
- unable to run test.py HOT 1
- Error while trying to call train.py HOT 1
- About the point cloud range
- Facing below issue while executing train.py. HOT 1
- running setup.py find error HOT 1
- whenever I starting the training.py it's showing error!
- Error while compiling "setup HOT 1
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 voxelnet.