qianguih / voxelnet

This is an unofficial inplementation of VoxelNet in TensorFlow.
646 stars 241 forks source link

Is the label_2 folder under validation an empty folder? #22

Open wutaoo opened 6 years ago

wutaoo commented 6 years ago

if not, where can i get

zemahran commented 6 years ago

No, it contains 7480 training labels provided with the KITTI dataset. You can get them from here.

tiandaji commented 5 years ago

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:

  1. Velodyne point clouds (29 GB): input data to VoxelNet
  2. Training labels of object data set (5 MB): input label to VoxelNet
  3. Camera calibration matrices of object data set (16 MB): for visualization of predictions
  4. 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