UpDate README.md

autonomous_driving/Online-HD-Map-Construction-CVPR2023/tools/visualization/visualize.py → autonomous_driving/Online-HD-Map-Construction/tools/visualization/visualize.py

-import argparse
-import mmcv
-from mmcv import Config
-import os
-from renderer import Renderer
-
-CAT2ID = {
-    'ped_crossing': 0,
-    'divider': 1,
-    'boundary': 2,
-}
-
-ID2CAT = {v: k for k, v in CAT2ID.items()}
-
-ROI_SIZE = (60, 30)
-
-def parse_args():
-    parser = argparse.ArgumentParser(
-        description='Visualize groundtruth and results')
-    
-    parser.add_argument('log_id', type=str,
-        help='log_id of data to visualize')
-    parser.add_argument('ann_file', 
-        help='gt file to visualize')
-    parser.add_argument('--result', 
-        type=str,
-        help='prediction result to visualize')
-    parser.add_argument('--thr', 
-        type=float,
-        default=0,
-        help='score threshold to filter predictions')
-    parser.add_argument(
-        '--out-dir', 
-        default='demo',
-        help='directory where visualize results will be saved')
-    args = parser.parse_args()
-
-    return args
-
-def import_plugin(cfg):
-    '''
-        import modules, registry will be update
-    '''
-
-    import sys
-    sys.path.append(os.path.abspath('.'))    
-    if hasattr(cfg, 'plugin'):
-        if cfg.plugin:
-            import importlib
-            if hasattr(cfg, 'plugin_dir'):
-                def import_path(plugin_dir):
-                    _module_dir = os.path.dirname(plugin_dir)
-                    _module_dir = _module_dir.split('/')
-                    _module_path = _module_dir[0]
-
-                    for m in _module_dir[1:]:
-                        _module_path = _module_path + '.' + m
-                    print(f'importing {_module_path}/')
-                    plg_lib = importlib.import_module(_module_path)
-
-                plugin_dirs = cfg.plugin_dir
-                if not isinstance(plugin_dirs,list):
-                    plugin_dirs = [plugin_dirs,]
-                for plugin_dir in plugin_dirs:
-                    import_path(plugin_dir)
-                
-            else:
-                # import dir is the dirpath for the config file
-                _module_dir = os.path.dirname(args.config)
-                _module_dir = _module_dir.split('/')
-                _module_path = _module_dir[0]
-                for m in _module_dir[1:]:
-                    _module_path = _module_path + '.' + m
-                print(f'importing {_module_path}/')
-                plg_lib = importlib.import_module(_module_path)
-
-def main(args):
-    log_id = args.log_id
-    ann = mmcv.load(args.ann_file)
-    root_path = os.path.dirname(args.ann_file)
-    out_dir = os.path.join(args.out_dir, str(log_id))
-    
-    log_ann = ann[log_id]
-    renderer = Renderer(roi_size=ROI_SIZE)
-
-    if args.result:
-        result = mmcv.load(args.result)['results']
-
-    for frame in mmcv.track_iter_progress(log_ann):
-        timestamp = frame['timestamp']
-        sensor = frame['sensor']
-        annotation = frame['annotation']
-        imgs = [mmcv.imread(os.path.join(root_path, 'argoverse2', i['image_path'])) for i in sensor.values()]
-        extrinsics = [i['extrinsic'] for i in sensor.values()]
-        intrinsics = [i['intrinsic'] for i in sensor.values()]
-
-        frame_dir = os.path.join(out_dir, timestamp, 'gt')
-        os.makedirs(frame_dir, exist_ok=True)
-        
-        renderer.render_bev_from_vectors(annotation, out_dir=frame_dir)
-        renderer.render_camera_views_from_vectors(annotation, imgs, extrinsics, 
-            intrinsics, 4, frame_dir)
-
-        if args.result:
-            pred = result[timestamp]
-            vectors = {cat: [] for cat in CAT2ID.keys()}
-            for i in range(len(pred['labels'])):
-                score = pred['scores'][i]
-                label = pred['labels'][i]
-                v = pred['vectors'][i]
-
-                if score > args.thr:
-                    vectors[ID2CAT[label]].append(v)
-            
-            frame_dir = os.path.join(out_dir, timestamp, 'pred')
-            os.makedirs(frame_dir, exist_ok=True)
-            renderer.render_bev_from_vectors(vectors, out_dir=frame_dir)
-            renderer.render_camera_views_from_vectors(vectors, imgs, 
-                    extrinsics, intrinsics, 4, frame_dir)
-
-
-if __name__ == '__main__':
-    args = parse_args()
+import argparse
+import mmcv
+from mmcv import Config
+import os
+from renderer import Renderer
+
+CAT2ID = {
+    'ped_crossing': 0,
+    'divider': 1,
+    'boundary': 2,
+}
+
+ID2CAT = {v: k for k, v in CAT2ID.items()}
+
+ROI_SIZE = (60, 30)
+
+def parse_args():
+    parser = argparse.ArgumentParser(
+        description='Visualize groundtruth and results')
+    
+    parser.add_argument('log_id', type=str,
+        help='log_id of data to visualize')
+    parser.add_argument('ann_file', 
+        help='gt file to visualize')
+    parser.add_argument('--result', 
+        type=str,
+        help='prediction result to visualize')
+    parser.add_argument('--thr', 
+        type=float,
+        default=0,
+        help='score threshold to filter predictions')
+    parser.add_argument(
+        '--out-dir', 
+        default='demo',
+        help='directory where visualize results will be saved')
+    args = parser.parse_args()
+
+    return args
+
+def import_plugin(cfg):
+    '''
+        import modules, registry will be update
+    '''
+
+    import sys
+    sys.path.append(os.path.abspath('.'))    
+    if hasattr(cfg, 'plugin'):
+        if cfg.plugin:
+            import importlib
+            if hasattr(cfg, 'plugin_dir'):
+                def import_path(plugin_dir):
+                    _module_dir = os.path.dirname(plugin_dir)
+                    _module_dir = _module_dir.split('/')
+                    _module_path = _module_dir[0]
+
+                    for m in _module_dir[1:]:
+                        _module_path = _module_path + '.' + m
+                    print(f'importing {_module_path}/')
+                    plg_lib = importlib.import_module(_module_path)
+
+                plugin_dirs = cfg.plugin_dir
+                if not isinstance(plugin_dirs,list):
+                    plugin_dirs = [plugin_dirs,]
+                for plugin_dir in plugin_dirs:
+                    import_path(plugin_dir)
+                
+            else:
+                # import dir is the dirpath for the config file
+                _module_dir = os.path.dirname(args.config)
+                _module_dir = _module_dir.split('/')
+                _module_path = _module_dir[0]
+                for m in _module_dir[1:]:
+                    _module_path = _module_path + '.' + m
+                print(f'importing {_module_path}/')
+                plg_lib = importlib.import_module(_module_path)
+
+def main(args):
+    log_id = args.log_id
+    ann = mmcv.load(args.ann_file)
+    root_path = os.path.dirname(args.ann_file)
+    out_dir = os.path.join(args.out_dir, str(log_id))
+    
+    log_ann = ann[log_id]
+    renderer = Renderer(roi_size=ROI_SIZE)
+
+    if args.result:
+        result = mmcv.load(args.result)['results']
+
+    for frame in mmcv.track_iter_progress(log_ann):
+        timestamp = frame['timestamp']
+        sensor = frame['sensor']
+        annotation = frame['annotation']
+        imgs = [mmcv.imread(os.path.join(root_path, 'argoverse2', i['image_path'])) for i in sensor.values()]
+        extrinsics = [i['extrinsic'] for i in sensor.values()]
+        intrinsics = [i['intrinsic'] for i in sensor.values()]
+
+        frame_dir = os.path.join(out_dir, timestamp, 'gt')
+        os.makedirs(frame_dir, exist_ok=True)
+        
+        renderer.render_bev_from_vectors(annotation, out_dir=frame_dir)
+        renderer.render_camera_views_from_vectors(annotation, imgs, extrinsics, 
+            intrinsics, 4, frame_dir)
+
+        if args.result:
+            pred = result[timestamp]
+            vectors = {cat: [] for cat in CAT2ID.keys()}
+            for i in range(len(pred['labels'])):
+                score = pred['scores'][i]
+                label = pred['labels'][i]
+                v = pred['vectors'][i]
+
+                if score > args.thr:
+                    vectors[ID2CAT[label]].append(v)
+            
+            frame_dir = os.path.join(out_dir, timestamp, 'pred')
+            os.makedirs(frame_dir, exist_ok=True)
+            renderer.render_bev_from_vectors(vectors, out_dir=frame_dir)
+            renderer.render_camera_views_from_vectors(vectors, imgs, 
+                    extrinsics, intrinsics, 4, frame_dir)
+
+
+if __name__ == '__main__':
+    args = parse_args()
     main(args)
\ No newline at end of file

autonomous_driving/README.md

+<div id="top" align="center">
+
+# InternImage for CVPR 2023 Workshop on End-to-End Autonomous Driving
+ </div>
+
+
+
+## 1. InternImage-based Baseline for CVPR23 Occupancy Prediction Challenge
+We achieve a nimprovement of 1.44 in MIOU baseline by leveraging the InterImage-based model.
+
+model name|weight| mIoU | others | barrier | bicycle | bus | car | construction_vehicle | motorcycle | pedestrian | traffic_cone | trailer |  truck | driveable_surface | other_flat | sidewalk | terrain | manmade | vegetation | 
+----|:----------:| :--: | :--: | :--: | :--: | :--: | :--: | :--: | :--: | :--: | :--: | :--: | :--: | :--: | :--: | :----------------------: | :---: | :------: | :------: |
+bevformer_intern-s_occ|[Google Drive](https://drive.google.com/file/d/1LV9K8hrskKf51xY1wbqTKzK7WZmVXEV_/view?usp=sharing)| 25.11 | 6.93 | 35.57 | 10.40 | 35.97 | 41.23 | 13.72 | 20.30 | 21.10 | 18.34 | 19.18 | 28.64 | 49.82 | 30.74 | 31.00 | 27.44 | 19.29 | 17.29 | 
+bevformer_base_occ|[Google Drive](https://drive.google.com/file/d/1NyoiosafAmne1qiABeNOPXR-P-y0i7_I/view?usp=share_link)| 23.67 | 5.03 | 38.79 | 9.98 | 34.41 | 41.09 | 13.24 | 16.50 | 18.15 | 17.83 | 18.66 | 27.70 | 48.95 | 27.73 | 29.08 | 25.38 | 15.41 | 14.46 | 
+
+### Get Started
+please refer to [README.md](./occupancy_prediction/README.md)
+
+
+## 2. InternImage-based Baseline for Online HD Map Construction Challenge For Autonomous Driving
+By incorporating the InterImage-based model, we observe an enhancement of 6.56 in mAP baseline.
+
+model name|weight|$\mathrm{mAP}$ | $\mathrm{AP}_{pc}$ | $\mathrm{AP}_{div}$ | $\mathrm{AP}_{bound}$ | 
+----|:----------:| :--: | :--: | :--: | :--: | 
+vectormapnet_intern|[Checkpoint](https://github.com/OpenGVLab/InternImage/releases/download/track_model/vectormapnet_internimage.pth) | 49.35 | 45.05 | 56.78 | 46.22 | 
+vectormapnet_base|[Google Drive](https://drive.google.com/file/d/16D1CMinwA8PG1sd9PV9_WtHzcBohvO-D/view) | 42.79 | 37.22 | 50.47	 | 40.68 | 
+
+### Get Started
+please refer to [README.md](Online-HD-Map-Construction/README.md)
+
+
+## 3. InternImage-based Baseline for CVPR23 OpenLane-V2 Challenge
+Through the implementation of the InterImage-based model, we achieve an advancement of 0.009 in F-score baseline.
+
+
+|             | OpenLane-V2 Score | DET<sub>l</sub> | DET<sub>t</sub> | TOP<sub>ll</sub> | TOP<sub>lt</sub> | F-Score |
+|-------------|-------------------|-----------------|-----------------|------------------|------------------|---------|
+| base r50    | 0.292             | 0.183           | 0.457           | 0.022            | 0.143            | 0.215   |
+| InternImage | 0.325             | 0.194           | 0.537           | 0.02             | 0.17             | 0.224   |
+
+### Get Started
+please refer to [README.md](./openlane-v2/README.md)
+
+
+
+