CODa to KITTI converter improved

cuda_11.3_env

@@ -0,0 +1,10 @@
+CUDAVER=cuda-11.3
+CUDA_ABS_PATH=/usr/local/$CUDAVER
+export PATH=$CUDA_ABS_PATH/bin:$PATH
+export LD_LIBRARY_PATH=$CUDA_ABS_PATH/lib:$LD_LIBRARY_PATH
+export LD_LIBRARY_PATH=$CUDA_ABS_PATH/lib64:$LD_LIBRARY_PATH
+export CUDADIR=$CUDA_ABS_PATH
+export CUDA_PATH=$CUDA_ABS_PATH
+export CUDA_ROOT=$CUDA_ABS_PATH
+export CUDA_HOME=$CUDA_ABS_PATH
+export CUDA_HOST_COMPILER=/usr/bin/gcc

docs/GETTING_STARTED.md

@@ -9,20 +9,28 @@ We describe how to prepare the other datasets in the [preparing external dataset
 
 ### Campus Object Dataset (CODa)
 
-Please download the official CODa using the [dataset development kit](https://github.com/ut-amrl/coda-devkit) 
-and link it in the data directory in this repo as follows. You may need to symlink the `3d_raw` directory
-to the `3d_comp` directory if you downloaded CODa by split rather than by sequence.
-
+Please download the official CODa using the [dataset development kit](https://github.com/ut-amrl/coda-devkit) with the command:
+```bashrc
+python scripts/download_split.py -d data/coda -t split --split full
 ```
+Link it in the data directory `coda_original_format` in this repo as follows. You may need to symlink the `3d_raw` directory to the `3d_comp` directory.
+
+Next, download the `2d_bbox` folder from the [url](https://web.corral.tacc.utexas.edu/texasrobotics/web_CODa/CODa_models/). Unzip and arrange as follows:
+
+```bash
 coda-models
 ├── data
-│   ├── coda_original_format
+│   └── coda_original_format
+│       ├── 2d_bbox
 │       ├── 2d_rect
-|       ├── 3d_raw
+│       ├── 3d_bbox
+│       ├── 3d_comp    
+│       ├── 3d_raw         # soft-link to 3d_comp
+│       ├── 3d_semantic
 │       ├── calibrations
 │       ├── metadata
 │       ├── poses
-|       ├── timestamps
+│       └── timestamps
 ├── pcdet
 ├── tools
 ```
@@ -32,33 +40,64 @@ coda-models
 python tools/create_data.py coda
 ```
 
+You should now see the following file structure:
+
+```bash
+coda-models
+├── data
+│   ├── coda_original_format
+│   │   ├── 2d_bbox
+│   │   ├── 2d_rect
+│   │   ├── 3d_bbox
+│   │   ├── 3d_comp    
+│   │   ├── 3d_raw         # soft-link to 3d_comp
+│   │   ├── 3d_semantic
+│   │   ├── calibrations
+│   │   ├── metadata
+│   │   ├── poses
+│   │   └── timestamps
+│   │
+│   └── coda128_allclass_full
+│       ├── ImageSets
+│       ├── testing
+│       └── training
+├── pcdet
+├── tools
+```
+
+
 * Generate the data infos by running the following command:
 ```python
 python -m pcdet.datasets.coda.coda_dataset create_coda_infos tools/cfgs/dataset_configs/da_coda_oracle_dataset_full.yaml
 ```
 
-You should now see the following file structure.
+You should now see the following file structure:
 
-```
+```bash
 coda-models
 ├── data
 │   ├── coda_original_format
-│       ├── 2d_rect
-|       ├── 3d_raw
-│       ├── calibrations
-│       ├── metadata
-│       ├── poses
-|       ├── timestamps
-│   ├── coda128_allclass_full
+│   │   ├── 2d_bbox
+│   │   ├── 2d_rect
+│   │   ├── 3d_bbox
+│   │   ├── 3d_comp    
+│   │   ├── 3d_raw         # soft-link to 3d_comp
+│   │   ├── 3d_semantic
+│   │   ├── calibrations
+│   │   ├── metadata
+│   │   ├── poses
+│   │   └── timestamps
+│   │
+│   └── coda128_allclass_full
 │       ├── gt_database
-|       ├── ImageSets
+│       ├── ImageSets
 │       ├── testing
 │       ├── training
 │       ├── coda_dbinfos_train.pkl
-|       ├── coda_infos_test.pkl
-|       ├── coda_infos_train.pkl
-|       ├── coda_infos_trainval.pkl
-|       ├── coda_infos_val.pkl
+│       ├── coda_infos_test.pkl
+│       ├── coda_infos_train.pkl
+│       ├── coda_infos_trainval.pkl
+│       └── coda_infos_val.pkl
 ├── pcdet
 ├── tools
 ```

docs/INSTALL.md

@@ -45,7 +45,19 @@ pip install spconv-cu113
 pip install -r requirements.txt
 ```
 
-c. Install this repository
+c. Link to cuda_11.3 on your machine and use correct GCC/G++
+
+```bashrc
+source cuda_11.3_env 
+
+sudo apt-get install gcc-9 g++-9 -y
+sudo ln -sfn /usr/bin/gcc-9 /usr/bin/gcc
+sudo ln -sfn /usr/bin/gcc-9 /usr/bin/cc
+sudo ln -sfn /usr/bin/g++-9 /usr/bin/g++
+sudo ln -sfn /usr/bin/g++-9 /usr/bin/c++
+```
+
+d. Install this repository
 
 ```
 python setup.py develop

environment.yml

@@ -196,7 +196,6 @@ dependencies:
       - stack-data==0.6.2
       - tensorboardx==2.6.2.2
       - threadpoolctl==3.2.0
-      - tifffile==2023.8.30
       - tqdm==4.66.1
       - traitlets==5.9.0
       - tzdata==2023.3

tools/create_data.py

@@ -1,4 +1,6 @@
 # Copyright (c) OpenMMLab. All rights reserved.
+import os, sys
+sys.path.append(os.getcwd())
 import argparse
 from os import path as osp
 
@@ -35,8 +37,8 @@ def coda_data_prep(root_path,
             split=split,
             channels=channels
         )
+        print("CODa Split= {} Length = {}".format(split, len(converter)))
         converter.convert()
-        print("length dataset ", len(converter))
 
 parser = argparse.ArgumentParser(description='Data converter arg parser')
 parser.add_argument('dataset', metavar='coda', help='name of the dataset')

tools/data_converter/coda_converter.py

@@ -210,6 +210,15 @@ def __init__(self,
             'cam1': 1,
             'os1': 2
         }
+        # CODA Camera to KITTI Camera
+        # 0 is 2
+        # 1 is 3
+        # 2 is assumed 4
+        self.coda_to_kitti_id = {
+            0: 2,
+            1: 3,
+            2: 4
+        }
 
         # Used to downsample lidar vertical channels
         self.channels = channels
@@ -232,7 +241,7 @@ def process_metadata(self):
             label_list = meta_json["ObjectTracking"][self.split]
             self.bbox_label_files.extend(label_list)
 
-            lidar_list = [label_path.replace('3d_label', '3d_raw').replace('.json', '.bin') 
+            lidar_list = [label_path.replace('3d_label', '3d_comp').replace('.json', '.bin')
                 for label_path in label_list]
             self.lidar_files.extend(lidar_list)
 
@@ -285,10 +294,10 @@ def get_filename_info(filename):
     @staticmethod
     def set_filename_by_prefix(modality, sensor_name, trajectory, frame):
         if "2d_rect"==modality:
-            filetype = "jpg" # change to jpg later
+            filetype = "png" # change to jpg later
         elif "2d_bbox"==modality:
             filetype = "txt"
-        elif "3d_raw"==modality:
+        elif "3d_comp"==modality or "3d_raw"==modality:
             filetype = "bin"
         elif "3d_bbox"==modality:
             filetype = "json"
@@ -381,7 +390,7 @@ def save_image(self, traj, src_img_path, cam_id, frame_idx, file_idx):
             frame_idx (int): Current frame index.
         """
         assert isfile(src_img_path), "Image file does not exist: %s" % src_img_path
-        kitti_img_path = f'{self.image_save_dir}{str(cam_id)}/' + \
+        kitti_img_path = f'{self.image_save_dir}{str(self.coda_to_kitti_id[cam_id])}/' + \
                 f'{str(traj).zfill(2)}{str(frame_idx).zfill(5)}.jpg'
         shutil.copyfile(src_img_path, kitti_img_path)
 
@@ -424,10 +433,18 @@ def save_calib(self, traj, frame_idx, file_idx):
         for cam_id in self.cam_ids:
             calib_context += 'P' + str(cam_id) + ': ' + \
                 ' '.join(camera_calibs[cam_id]) + '\n'
+        # Also map cam_id to KITTI camera ids
+        for cam_id in self.cam_ids:
+            calib_context += 'P' + str(self.coda_to_kitti_id[cam_id]) + ': ' + \
+                ' '.join(camera_calibs[cam_id]) + '\n'
         calib_context += 'R0_rect' + ': ' + ' '.join(R0_rect) + '\n'
         for cam_id in self.cam_ids:
-            calib_context += 'Tr_velo_to_cam_' + str(cam_id) + ': ' + \
-                ' '.join(Tr_os1_to_cams[cam_id]) + '\n'
+            if cam_id == 0:
+                calib_context += 'Tr_velo_to_cam' + ': ' + \
+                                 ' '.join(Tr_os1_to_cams[cam_id]) + '\n'
+            else:
+                calib_context += 'Tr_velo_to_cam_' + str(cam_id) + ': ' + \
+                    ' '.join(Tr_os1_to_cams[cam_id]) + '\n'
 
         with open(
                 f'{self.calib_save_dir}/' +
@@ -442,7 +459,7 @@ def save_lidar(self, traj, frame_idx, file_idx, channels=128):
             traj (int): Current trajectory index.
             frame_idx (int): Current frame index.
         """
-        bin_file = self.set_filename_by_prefix("3d_raw", "os1", traj, frame_idx)
+        bin_file = self.set_filename_by_prefix("3d_comp", "os1", traj, frame_idx)
         bin_path = join(self.load_dir, "3d_raw", "os1", traj, bin_file)
         assert isfile(bin_path), "Bin file for traj %s frame %s does not exist: %s" % (traj, frame_idx, bin_path)
         point_cloud = np.fromfile(bin_path, dtype=np.float32).reshape(-1, 4)
@@ -554,7 +571,7 @@ def save_label(self, traj, cam_id, frame_idx, file_idx):
             line_all = line[:-1] + '\n'
 
             fp_label = open(
-                f'{self.label_save_dir}{cam_id}/' +
+                f'{self.label_save_dir}{self.coda_to_kitti_id[cam_id]}/' +
                 f'{str(traj).zfill(2)}{str(frame_idx).zfill(5)}.txt', 'a')
             fp_label.write(line)
             fp_label.close()