Merge branch 'master' into dev_v0.3.1

README.md

@@ -4,7 +4,7 @@
 
 `OpenPCDet` is a clear, simple, self-contained open source project for LiDAR-based 3D object detection. 
 
-It is also the official code release of [`[PointRCNN]`](https://arxiv.org/abs/1812.04244), [`[Part-A^2 net]`](https://arxiv.org/abs/1907.03670) and [`[PV-RCNN]`](https://arxiv.org/abs/1912.13192). 
+It is also the official code release of [`[PointRCNN]`](https://arxiv.org/abs/1812.04244), [`[Part-A^2 net]`](https://arxiv.org/abs/1907.03670), [`[PV-RCNN]`](https://arxiv.org/abs/1912.13192) and [`[Voxel R-CNN]`](https://arxiv.org/abs/2012.15712). 
 
 
 ## Overview
@@ -18,6 +18,8 @@ It is also the official code release of [`[PointRCNN]`](https://arxiv.org/abs/18
 
 
 ## Changelog
+[2021-06-08] Added support for the voxel-based 3D object detection model [`Voxel R-CNN`](#KITTI-3D-Object-Detection-Baselines)
+
 [2021-05-14] Added support for the monocular 3D object detection model [`CaDDN`](#KITTI-3D-Object-Detection-Baselines)
 
 [2020-11-27] **Bugfixed:** Please re-prepare the validation infos of Waymo dataset (version 1.2) if you would like to 

pcdet/models/__init__.py

@@ -27,7 +27,7 @@ def load_data_to_gpu(batch_dict):
         elif key in ['frame_id', 'metadata', 'calib']:
             continue
         elif key in ['images']:
-            batch_dict[key] = image_to_tensor(val).float().cuda().contiguous()
+            batch_dict[key] = kornia.image_to_tensor(val).float().cuda().contiguous()
         elif key in ['image_shape']:
             batch_dict[key] = torch.from_numpy(val).int().cuda()
         else:

tools/train.py

@@ -123,17 +123,17 @@ def main():
     start_epoch = it = 0
     last_epoch = -1
     if args.pretrained_model is not None:
-        model.load_params_from_file(filename=args.pretrained_model, to_cpu=dist, logger=logger)
+        model.load_params_from_file(filename=args.pretrained_model, to_cpu=dist_train, logger=logger)
 
     if args.ckpt is not None:
-        it, start_epoch = model.load_params_with_optimizer(args.ckpt, to_cpu=dist, optimizer=optimizer, logger=logger)
+        it, start_epoch = model.load_params_with_optimizer(args.ckpt, to_cpu=dist_train, optimizer=optimizer, logger=logger)
         last_epoch = start_epoch + 1
     else:
         ckpt_list = glob.glob(str(ckpt_dir / '*checkpoint_epoch_*.pth'))
         if len(ckpt_list) > 0:
             ckpt_list.sort(key=os.path.getmtime)
             it, start_epoch = model.load_params_with_optimizer(
-                ckpt_list[-1], to_cpu=dist, optimizer=optimizer, logger=logger
+                ckpt_list[-1], to_cpu=dist_train, optimizer=optimizer, logger=logger
             )
             last_epoch = start_epoch + 1