maudzung / SFA3D

Super Fast and Accurate 3D Object Detection based on 3D LiDAR Point Clouds (The PyTorch implementation)
https://github.com/maudzung/Super-Fast-Accurate-3D-Object-Detection
MIT License
1k stars 271 forks source link

Data Augmentation Issue in Random Scaling #90

Open DominikFle opened 10 months ago

DominikFle commented 10 months ago

Here: https://github.com/maudzung/SFA3D/blob/0e2f0b63dc4090bd6c08e15505f11d764390087c/sfa/data_process/transformation.py#L367 the scaling factor is not correctly sampled from the scaling range. Instead of: factor = np.random.uniform(self.scaling_range[0], self.scaling_range[0]) It should be factor = np.random.uniform(self.scaling_range[0], self.scaling_range[1])