Merge branch 'update-model-zoo' into 'master'

Update model zoo links and readme

See merge request open-mmlab/mmdet.3d!102

.dev_scripts/gather_models.py

+import argparse
+import glob
+import json
+import os.path as osp
+import shutil
+import subprocess
+
+import mmcv
+import torch
+
+# build schedule look-up table to automatically find the final model
+SCHEDULES_LUT = {
+    '_1x_': 12,
+    '_2x_': 24,
+    '_20e_': 20,
+    '_3x_': 36,
+    '_4x_': 48,
+    '_24e_': 24,
+    '_6x_': 73
+}
+
+# TODO: add support for lyft dataset
+RESULTS_LUT = {
+    'coco': ['bbox_mAP', 'segm_mAP'],
+    'nus': ['pts_bbox_NuScenes/NDS', 'NDS'],
+    'kitti-3d-3class': [
+        'KITTI/Overall_3D_moderate',
+        'Overall_3D_moderate',
+    ],
+    'kitti-3d-car': ['KITTI/Car_3D_moderate_strict', 'Car_3D_moderate_strict'],
+    'lyft': ['score'],
+    'scannet': ['mAR_0.50'],
+    'sunrgbd': ['mAR_0.50']
+}
+
+
+def get_model_dataset(log_json_path):
+    for key in RESULTS_LUT:
+        if log_json_path.find(key) != -1:
+            return key
+
+
+def process_checkpoint(in_file, out_file):
+    checkpoint = torch.load(in_file, map_location='cpu')
+    # remove optimizer for smaller file size
+    if 'optimizer' in checkpoint:
+        del checkpoint['optimizer']
+    # if it is necessary to remove some sensitive data in checkpoint['meta'],
+    # add the code here.
+    torch.save(checkpoint, out_file)
+    sha = subprocess.check_output(['sha256sum', out_file]).decode()
+    final_file = out_file.rstrip('.pth') + '-{}.pth'.format(sha[:8])
+    subprocess.Popen(['mv', out_file, final_file])
+    return final_file
+
+
+def get_final_epoch(config):
+    if config.find('grid_rcnn') != -1 and config.find('2x') != -1:
+        # grid_rcnn 2x trains 25 epochs
+        return 25
+
+    for schedule_name, epoch_num in SCHEDULES_LUT.items():
+        if config.find(schedule_name) != -1:
+            return epoch_num
+
+
+def get_best_results(log_json_path):
+    dataset = get_model_dataset(log_json_path)
+    max_dict = dict()
+    max_memory = 0
+    with open(log_json_path, 'r') as f:
+        for line in f.readlines():
+            log_line = json.loads(line)
+            if 'mode' not in log_line.keys():
+                continue
+
+            # record memory and find best results & epochs
+            if log_line['mode'] == 'train' \
+                    and max_memory <= log_line['memory']:
+                max_memory = log_line['memory']
+
+            elif log_line['mode'] == 'val':
+                result_dict = {
+                    key: log_line[key]
+                    for key in RESULTS_LUT[dataset] if key in log_line
+                }
+                if len(max_dict) == 0:
+                    max_dict = result_dict
+                    max_dict['epoch'] = log_line['epoch']
+                elif all(
+                    [max_dict[key] <= result_dict[key]
+                     for key in result_dict]):
+                    max_dict.update(result_dict)
+                    max_dict['epoch'] = log_line['epoch']
+
+        max_dict['memory'] = max_memory
+        return max_dict
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description='Gather benchmarked models')
+    parser.add_argument(
+        'root',
+        type=str,
+        help='root path of benchmarked models to be gathered')
+    parser.add_argument(
+        'out', type=str, help='output path of gathered models to be stored')
+
+    args = parser.parse_args()
+    return args
+
+
+def main():
+    args = parse_args()
+    models_root = args.root
+    models_out = args.out
+    mmcv.mkdir_or_exist(models_out)
+
+    # find all models in the root directory to be gathered
+    raw_configs = list(mmcv.scandir('./configs', '.py', recursive=True))
+
+    # filter configs that is not trained in the experiments dir
+    used_configs = []
+    for raw_config in raw_configs:
+        if osp.exists(osp.join(models_root, raw_config)):
+            used_configs.append(raw_config)
+    print(f'Find {len(used_configs)} models to be gathered')
+
+    # find final_ckpt and log file for trained each config
+    # and parse the best performance
+    model_infos = []
+    for used_config in used_configs:
+        exp_dir = osp.join(models_root, used_config)
+
+        # get logs
+        log_json_path = glob.glob(osp.join(exp_dir, '*.log.json'))[0]
+        log_txt_path = glob.glob(osp.join(exp_dir, '*.log'))[0]
+        model_performance = get_best_results(log_json_path)
+        final_epoch = model_performance['epoch']
+        final_model = 'epoch_{}.pth'.format(final_epoch)
+        model_path = osp.join(exp_dir, final_model)
+
+        # skip if the model is still training
+        if not osp.exists(model_path):
+            print(f'Expected {model_path} does not exist!')
+            continue
+
+        if model_performance is None:
+            print(f'Obtained no performance for model {used_config}')
+            continue
+
+        model_time = osp.split(log_txt_path)[-1].split('.')[0]
+        model_infos.append(
+            dict(
+                config=used_config,
+                results=model_performance,
+                epochs=final_epoch,
+                model_time=model_time,
+                log_json_path=osp.split(log_json_path)[-1]))
+
+    # publish model for each checkpoint
+    publish_model_infos = []
+    for model in model_infos:
+        model_publish_dir = osp.join(models_out, model['config'].rstrip('.py'))
+        mmcv.mkdir_or_exist(model_publish_dir)
+
+        model_name = model_publish_dir + '_' + model['model_time']
+        publish_model_path = osp.join(model_publish_dir, model_name)
+        trained_model_path = osp.join(models_root, model['config'],
+                                      'epoch_{}.pth'.format(model['epochs']))
+
+        # convert model
+        final_model_path = process_checkpoint(trained_model_path,
+                                              publish_model_path)
+
+        # copy log
+        shutil.copy(
+            osp.join(models_root, model['config'], model['log_json_path']),
+            osp.join(model_publish_dir, f'{model_name}.log.json'))
+        shutil.copy(
+            osp.join(models_root, model['config'],
+                     model['log_json_path'].rstrip('.json')),
+            osp.join(model_publish_dir, f'{model_name}.log'))
+
+        # copy config to guarantee reproducibility
+        config_path = model['config']
+        config_path = osp.join(
+            'configs',
+            config_path) if 'configs' not in config_path else config_path
+        target_cconfig_path = osp.split(config_path)[-1]
+        shutil.copy(config_path,
+                    osp.join(model_publish_dir, target_cconfig_path))
+
+        model['model_path'] = final_model_path
+        publish_model_infos.append(model)
+
+    models = dict(models=publish_model_infos)
+    print(f'Totally gathered {len(publish_model_infos)} models')
+    mmcv.dump(models, osp.join(models_out, 'model_info.json'))
+
+
+if __name__ == '__main__':
+    main()

README.md

@@ -49,17 +49,17 @@ Results and models are available in the [model zoo](docs/model_zoo.md).
 
 |                    | ResNet   | ResNeXt  | SENet    |PointNet++ | HRNet | RegNetX | Res2Net |
 |--------------------|:--------:|:--------:|:--------:|:---------:|:-----:|:--------:|:-----:|
-| SECOND             | ☐        | ☐        | ☐        | ✗         | ✓     | ✓        | ☐     |
-| PointPillars       | ☐        | ☐        | ☐        | ✗         | ✓     | ✓        | ☐     |
-| FreeAnchor         | ☐        | ☐        | ☐        | ✗         | ✓     | ✓        | ☐     |
+| SECOND             | ☐        | ☐        | ☐        | ✗         | ☐     | ✓        | ☐     |
+| PointPillars       | ☐        | ☐        | ☐        | ✗         | ☐     | ✓        | ☐     |
+| FreeAnchor         | ☐        | ☐        | ☐        | ✗         | ☐     | ✓        | ☐     |
 | VoteNet            | ✗        | ✗        | ✗        | ✓         | ✗     | ✗        | ✗     |
-| Part-A2            | ☐        | ☐        | ☐        | ✗         | ✓     | ✓        | ☐     |
-| MVXNet             | ☐        | ☐        | ☐        | ✗         | ✓     | ✓        | ☐     |
+| Part-A2            | ☐        | ☐        | ☐        | ✗         | ☐     | ✓        | ☐     |
+| MVXNet             | ☐        | ☐        | ☐        | ✗         | ☐     | ✓        | ☐     |
 
 Other features
 - [x] [Dynamic Voxelization](configs/carafe/README.md)
 
-**Notice**: All the models or modules supported in [MMDetection's model zoo](https://github.com/open-mmlab/mmdetection/blob/master/docs/model_zoo.md) can be trained or used in this codebase.
+All the about **300 models, 40+ papers**, and modules supported in [MMDetection's model zoo](https://github.com/open-mmlab/mmdetection/blob/master/docs/model_zoo.md) can be trained or used in this codebase.
 
 ## Installation
 

configs/dynamic_voxelization/README.md

@@ -21,6 +21,6 @@ We implement Dynamic Voxelization proposed in  and provide its results and model
 
 |  Model   |Class| Lr schd | Mem (GB) | Inf time (fps) | mAP | Download |
 | :---------: | :-----: |:-----: | :------: | :------------: | :----: | :------: |
-|[SECOND](./dv_second_secfpn_6x8_80e_kitti-3d-car.py)|Car    |cyclic 80e|5.5||78.83||
-|[SECOND](./dv_second_secfpn_2x8_cosine_80e_kitti-3d-3class.py)| 3 Class|cosine 80e|5.5||65.10||
-|[PointPillars](./dv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py)| Car|cyclic 80e|4.7||77.76||
+|[SECOND](./dv_second_secfpn_6x8_80e_kitti-3d-car.py)|Car    |cyclic 80e|5.5||78.83|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/)|
+|[SECOND](./dv_second_secfpn_2x8_cosine_80e_kitti-3d-3class.py)| 3 Class|cosine 80e|5.5||65.10|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/)|
+|[PointPillars](./dv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py)| Car|cyclic 80e|4.7||77.76|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/)|

configs/free_anchor/README.md

@@ -80,9 +80,13 @@ train_cfg = dict(
 
 |  Backbone   |FreeAnchor|Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
 | :---------: |:-----: |:-----: | :------: | :------------: | :----: |:----: | :------: |
-|[FPN](../pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py)|✗|2x|17.1||40.0|53.3||
-|[FPN](./hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py)|✓|2x|||43.7|55.1||
-|[RegNetX-400MF-FPN](../regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d.py)|✗|2x|17.3||44.8|56.4||
-|[RegNetX-400MF-FPN](./hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py)|✓|2x||||||
-|[RegNetX-1.6GF-FPN](./hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py)|✓|2x||||||
-|[RegNetX-3.2GF-FPN](./hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py)|✓|2x||||||
+|[FPN](../pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py)|✗|2x|17.1||40.0|53.3|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20200620_230405-2fa62f3d.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20200620_230405.log.json)|
+|[FPN](./hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py)|✓|2x|16.2||43.7|55.3|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/free_anchor/hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d_20200628_210537-09d359fc.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/free_anchor/hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d_20200628_210537.log.json)|
+|[RegNetX-400MF-FPN](../regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d.py)|✗|2x|17.3||44.8|56.4|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d_20200620_230239-c694dce7.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d_20200620_230239.log.json)|
+|[RegNetX-400MF-FPN](./hv_pointpillars_regnet-400mf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py)|✓|2x|17.7||47.9|58.6|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/free_anchor/hv_pointpillars_regnet-400mf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d/hv_pointpillars_regnet-400mf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d_20200629_050311-a334765d.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/free_anchor/hv_pointpillars_regnet-400mf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d/hv_pointpillars_regnet-400mf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d_20200629_050311.log.json)|
+|[RegNetX-1.6GF-FPN](./hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py)|✓|2x|24.3||51.2|60.8|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/free_anchor/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d_20200629_105446-6ffa59cb.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/free_anchor/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d_20200629_105446.log.json)|
+|[RegNetX-1.6GF-FPN](./hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d.py)*|✓|3x|24.3|53.0|62.2|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/free_anchor/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d_20200701_201531-036f7de3.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/free_anchor/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d_20200701_201531.log.json)|
+|[RegNetX-3.2GF-FPN](./hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py)|✓|2x|29.5||52.2|62.0|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/free_anchor/hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d/hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d_20200629_055854-658125b0.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/free_anchor/hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d/hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d_20200629_055854.log.json)|
+|[RegNetX-3.2GF-FPN](./hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d.py)*|✓|3x|29.5||55.09|63.5|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/free_anchor/hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d/hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d_20200629_181452-297fdc66.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/free_anchor/hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d/hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d_20200629_181452.log.json)|
+
+**Note**: Models noted by `*` means it is trained using stronger augmentation with vertical flip under bird-eye-view, global translation, and larger range of global rotation.

configs/free_anchor/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d.py

+_base_ = './hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py'
+
+model = dict(
+    pretrained=dict(pts='open-mmlab://regnetx_1.6gf'),
+    pts_backbone=dict(
+        _delete_=True,
+        type='NoStemRegNet',
+        arch='regnetx_1.6gf',
+        out_indices=(1, 2, 3),
+        frozen_stages=-1,
+        strides=(1, 2, 2, 2),
+        base_channels=64,
+        stem_channels=64,
+        norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
+        norm_eval=False,
+        style='pytorch'),
+    pts_neck=dict(in_channels=[168, 408, 912]))
+
+# If point cloud range is changed, the models should also change their point
+# cloud range accordingly
+point_cloud_range = [-50, -50, -5, 50, 50, 3]
+# For nuScenes we usually do 10-class detection
+class_names = [
+    'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
+    'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
+]
+# file_client_args = dict(backend='disk')
+# Uncomment the following if use ceph or other file clients.
+# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
+# for more details.
+file_client_args = dict(
+    backend='petrel',
+    path_mapping=dict({
+        './data/nuscenes/': 's3://nuscenes/nuscenes/',
+        'data/nuscenes/': 's3://nuscenes/nuscenes/'
+    }))
+train_pipeline = [
+    dict(
+        type='LoadPointsFromFile',
+        load_dim=5,
+        use_dim=5,
+        file_client_args=file_client_args),
+    dict(
+        type='LoadPointsFromMultiSweeps',
+        sweeps_num=10,
+        file_client_args=file_client_args),
+    dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
+    dict(
+        type='GlobalRotScaleTrans',
+        rot_range=[-0.7854, 0.7854],
+        scale_ratio_range=[0.95, 1.05],
+        translation_std=[0.2, 0.2, 0.2]),
+    dict(
+        type='RandomFlip3D',
+        flip_ratio_bev_horizontal=0.5,
+        flip_ratio_bev_vertical=0.5),
+    dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
+    dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
+    dict(type='ObjectNameFilter', classes=class_names),
+    dict(type='PointShuffle'),
+    dict(type='DefaultFormatBundle3D', class_names=class_names),
+    dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
+]
+data = dict(train=dict(pipeline=train_pipeline))
+
+lr_config = dict(step=[28, 34])
+evaluation = dict(interval=36)
+total_epochs = 36

configs/free_anchor/hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py

+_base_ = './hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py'
+
+model = dict(
+    pretrained=dict(pts='open-mmlab://regnetx_3.2gf'),
+    pts_backbone=dict(
+        _delete_=True,
+        type='NoStemRegNet',
+        arch='regnetx_3.2gf',
+        out_indices=(1, 2, 3),
+        frozen_stages=-1,
+        strides=(1, 2, 2, 2),
+        base_channels=64,
+        stem_channels=64,
+        norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
+        norm_eval=False,
+        style='pytorch'),
+    pts_neck=dict(in_channels=[192, 432, 1008]))

configs/free_anchor/hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d.py

+_base_ = './hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py'
+
+model = dict(
+    pretrained=dict(pts='open-mmlab://regnetx_3.2gf'),
+    pts_backbone=dict(
+        _delete_=True,
+        type='NoStemRegNet',
+        arch='regnetx_3.2gf',
+        out_indices=(1, 2, 3),
+        frozen_stages=-1,
+        strides=(1, 2, 2, 2),
+        base_channels=64,
+        stem_channels=64,
+        norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
+        norm_eval=False,
+        style='pytorch'),
+    pts_neck=dict(in_channels=[192, 432, 1008]))
+
+# If point cloud range is changed, the models should also change their point
+# cloud range accordingly
+point_cloud_range = [-50, -50, -5, 50, 50, 3]
+# For nuScenes we usually do 10-class detection
+class_names = [
+    'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
+    'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
+]
+# file_client_args = dict(backend='disk')
+# Uncomment the following if use ceph or other file clients.
+# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
+# for more details.
+file_client_args = dict(
+    backend='petrel',
+    path_mapping=dict({
+        './data/nuscenes/': 's3://nuscenes/nuscenes/',
+        'data/nuscenes/': 's3://nuscenes/nuscenes/'
+    }))
+train_pipeline = [
+    dict(
+        type='LoadPointsFromFile',
+        load_dim=5,
+        use_dim=5,
+        file_client_args=file_client_args),
+    dict(
+        type='LoadPointsFromMultiSweeps',
+        sweeps_num=10,
+        file_client_args=file_client_args),
+    dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
+    dict(
+        type='GlobalRotScaleTrans',
+        rot_range=[-0.7854, 0.7854],
+        scale_ratio_range=[0.9, 1.1],
+        translation_std=[0.2, 0.2, 0.2]),
+    dict(
+        type='RandomFlip3D',
+        flip_ratio_bev_horizontal=0.5,
+        flip_ratio_bev_vertical=0.5),
+    dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
+    dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
+    dict(type='ObjectNameFilter', classes=class_names),
+    dict(type='PointShuffle'),
+    dict(type='DefaultFormatBundle3D', class_names=class_names),
+    dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
+]
+
+data = dict(train=dict(pipeline=train_pipeline))
+lr_config = dict(step=[28, 34])
+evaluation = dict(interval=36)
+total_epochs = 36

configs/free_anchor/hv_pointpillars_regnet-400mf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py

+_base_ = './hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py'
+
+model = dict(
+    pretrained=dict(pts='open-mmlab://regnetx_400mf'),
+    pts_backbone=dict(
+        _delete_=True,
+        type='NoStemRegNet',
+        arch='regnetx_400mf',
+        out_indices=(1, 2, 3),
+        frozen_stages=-1,
+        strides=(1, 2, 2, 2),
+        base_channels=64,
+        stem_channels=64,
+        norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
+        norm_eval=False,
+        style='pytorch'),
+    pts_neck=dict(in_channels=[64, 160, 384]))

configs/mvxnet/README.md

@@ -21,4 +21,4 @@ We implement MVX-Net and provide its results and models on KITTI dataset.
 
 |  Backbone   |Class| Lr schd | Mem (GB) | Inf time (fps) | mAP | Download |
 | :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
-|    [SECFPN](./dv_mvx-fpn_second_secfpn_adamw_2x8_80e_kitti-3d-3class.py)|3 Class|cosine 80e|6.7||63.0||
+|    [SECFPN](./dv_mvx-fpn_second_secfpn_adamw_2x8_80e_kitti-3d-3class.py)|3 Class|cosine 80e|6.7||63.0|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/mvxnet/dv_mvx-fpn_second_secfpn_adamw_2x8_80e_kitti-3d-3class/dv_mvx-fpn_second_secfpn_adamw_2x8_80e_kitti-3d-3class_20200621_003904-10140f2d.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/mvxnet/dv_mvx-fpn_second_secfpn_adamw_2x8_80e_kitti-3d-3class/dv_mvx-fpn_second_secfpn_adamw_2x8_80e_kitti-3d-3class_20200621_003904.log.json)|

configs/parta2/README.md

@@ -20,5 +20,5 @@ We implement Part-A^2 and provide its results and checkpoints on KITTI dataset.
 
 |  Backbone   |Class| Lr schd | Mem (GB) | Inf time (fps) | mAP | Download |
 | :---------: | :-----: |:-----: | :------: | :------------: | :----: |:----: | :------: |
-|    [SECFPN](./hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class.py) |3 Class|cyclic 80e|4.1||67.9||
-|    [SECFPN](./hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car.py) |Car |cyclic 80e|4.0||79.16||
+|    [SECFPN](./hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class.py) |3 Class|cyclic 80e|4.1||67.9|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class_20200620_230724-a2672098.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class_20200620_230724.log.json)|
+|    [SECFPN](./hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car.py) |Car |cyclic 80e|4.0||79.16|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car_20200620_230755-f2a38b9a.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car_20200620_230755.log.json)|

configs/pointpillars/README.md

@@ -21,12 +21,12 @@ We implement PointPillars and provide the results and checkpoints on KITTI and n
 
 |  Backbone|Class   | Lr schd | Mem (GB) | Inf time (fps) | AP  |Download |
 | :---------: | :-----: |:-----: | :------: | :------------: | :----: | :------: |
-|    [SECFPN](./hv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py)|Car|cyclic 160e|5.4||77.1||
-|    [SECFPN](./hv_pointpillars_secfpn_6x8_160e_kitti-3d-3class.py)|3 Class|cyclic 160e|5.5||59.5|
+|    [SECFPN](./hv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py)|Car|cyclic 160e|5.4||77.1|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_secfpn_6x8_160e_kitti-3d-car/hv_pointpillars_secfpn_6x8_160e_kitti-3d-car_20200620_230614-77663cd6.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_secfpn_6x8_160e_kitti-3d-car/hv_pointpillars_secfpn_6x8_160e_kitti-3d-car_20200620_230614.log.json)|
+|    [SECFPN](./hv_pointpillars_secfpn_6x8_160e_kitti-3d-3class.py)|3 Class|cyclic 160e|5.5||59.5|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_secfpn_6x8_160e_kitti-3d-3class/hv_pointpillars_secfpn_6x8_160e_kitti-3d-3class_20200620_230421-aa0f3adb.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_secfpn_6x8_160e_kitti-3d-3class/hv_pointpillars_secfpn_6x8_160e_kitti-3d-3class_20200620_230421.log.json)|
 
 ### nuScenes
 
 |  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
 | :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
-|[SECFPN](./hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d.py)|2x|16.4||35.17|49.7||
-|[FPN](./hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py)|2x|16.4||40.0|53.3||
+|[SECFPN](./hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d.py)|2x|16.4||35.17|49.7|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d_20200620_230725-0817d270.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d_20200620_230725.log.json)|
+|[FPN](./hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py)|2x|16.4||40.0|53.3|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20200620_230405-2fa62f3d.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20200620_230405.log.json)|

configs/regnet/README.md

@@ -51,7 +51,8 @@ For other pre-trained models or self-implemented regnet models, the users are re
 
 |  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
 | :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
-|[SECFPN](../pointpillars/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d.py)|2x|16.4||35.17|49.7||
-|[RegNetX-400MF-SECFPN](./hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d.py)|  2x    |16.4||41.2|55.2||
-|[FPN](../pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py)|2x|17.1||40.0|53.3||
-|[RegNetX-400MF-FPN](./hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d.py)|2x|17.3||44.8|56.4||
+|[SECFPN](../pointpillars/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d.py)|2x|16.4||35.17|49.7|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d_20200620_230725-0817d270.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d_20200620_230725.log.json)|
+|[RegNetX-400MF-SECFPN](./hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d.py)|  2x    |16.4||41.2|55.2|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d_20200620_230334-53044f32.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d_20200620_230334.log.json)|
+|[FPN](../pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py)|2x|17.1||40.0|53.3|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20200620_230405-2fa62f3d.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20200620_230405.log.json)|
+|[RegNetX-400MF-FPN](./hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d.py)|2x|17.3||44.8|56.4|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d_20200620_230239-c694dce7.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d_20200620_230239.log.json)|
+|[RegNetX-1.6gF-FPN](./hv_pointpillars_regnet-1.6gf_fpn_sbn-all_4x8_2x_nus-3d.py)|2x|24.0||48.2|59.3|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_4x8_2x_nus-3d_20200629_050311-dcd4e090.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_4x8_2x_nus-3d_20200629_050311.log.json)|

configs/second/README.md

@@ -18,5 +18,5 @@ We implement SECOND and provide the results and checkpoints on KITTI dataset.
 ### KITTI
 |  Backbone   |Class| Lr schd | Mem (GB) | Inf time (fps) | mAP |Download |
 | :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
-|    [SECFPN](./hv_second_secfpn_6x8_80e_kitti-3d-car.py)| Car |cyclic 80e|5.4||79.07|
-|    [SECFPN](./hv_second_secfpn_6x8_80e_kitti-3d-3class.py)| 3 Class |cyclic 80e|5.4||64.41|
+|    [SECFPN](./hv_second_secfpn_6x8_80e_kitti-3d-car.py)| Car |cyclic 80e|5.4||79.07|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/second/hv_second_secfpn_6x8_80e_kitti-3d-car/hv_second_secfpn_6x8_80e_kitti-3d-car_20200620_230238-393f000c.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/second/hv_second_secfpn_6x8_80e_kitti-3d-car/hv_second_secfpn_6x8_80e_kitti-3d-car_20200620_230238.log.json)|
+|    [SECFPN](./hv_second_secfpn_6x8_80e_kitti-3d-3class.py)| 3 Class |cyclic 80e|5.4||64.41|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/second/hv_second_secfpn_6x8_80e_kitti-3d-3class/hv_second_secfpn_6x8_80e_kitti-3d-3class_20200620_230238-9208083a.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/second/hv_second_secfpn_6x8_80e_kitti-3d-3class/hv_second_secfpn_6x8_80e_kitti-3d-3class_20200620_230238-9208083a.pth)|

configs/votenet/README.md

@@ -16,9 +16,9 @@ We implement VoteNet and provide the result and checkpoints on ScanNet and SUNRG
 ### ScanNet
 |  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | AP@0.25 |AP@0.5| Download |
 | :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
-|    [PointNet++](./votenet_8x8_scannet-3d-18class.py)     |  3x    |4.1||62.90|39.91||
+|    [PointNet++](./votenet_8x8_scannet-3d-18class.py)     |  3x    |4.1||62.90|39.91|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/votenet/votenet_16x8_sunrgbd-3d-10class/votenet_16x8_sunrgbd-3d-10class_20200620_230238-4483c0c0.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/votenet/votenet_16x8_sunrgbd-3d-10class/votenet_16x8_sunrgbd-3d-10class_20200620_230238.log.json)|
 
 ### SUNRGBD
 |  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | AP@0.25 |AP@0.5| Download |
 | :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
-|    [PointNet++](./)     |  3x    |8.1||59.07|35.77||
+|    [PointNet++](./votenet_16x8_sunrgbd-3d-10class.py)     |  3x    |8.1||59.07|35.77|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/votenet/votenet_8x8_scannet-3d-18class/votenet_8x8_scannet-3d-18class_20200620_230238-2cea9c3a.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/votenet/votenet_8x8_scannet-3d-18class/votenet_8x8_scannet-3d-18class_20200620_230238.log.json)|

mmdet3d/utils/__init__.py

 from mmcv.utils import Registry, build_from_cfg, print_log
 
-from mmdet.utils import get_model_complexity_info, get_root_logger
+from mmdet import get_root_logger
 from .collect_env import collect_env
 
 __all__ = [
-    'Registry', 'build_from_cfg', 'get_model_complexity_info',
-    'get_root_logger', 'collect_env', 'print_log'
+    'Registry', 'build_from_cfg', 'get_root_logger', 'collect_env', 'print_log'
 ]