Adding pose estimation models, adding new models to previous tasks

Author: thomasehuang

README.md

@@ -6,7 +6,7 @@
 
 In this repository, we provide popular models for each task in the [BDD100K dataset](https://www.bdd100k.com/). For each task in the dataset, we make publicly available the model weights, evaluation results, predictions, visualizations, as well as scripts to performance evaluation and visualization. The goal is to provide a set of competitive baselines to facilitate research and provide a common benchmark for comparison.
 
-The number of pre-trained models in this zoo is :one::one::five:. **You can include your models in this repo as well!** See [contribution](./doc/CONTRIBUTING.md) instructions.
+The number of pre-trained models in this zoo is :one::seven::nine:. **You can include your models in this repo as well!** See [contribution](./doc/CONTRIBUTING.md) instructions.
 
 This repository currently supports the tasks listed below. For more information about each task, click on the task name. We plan to support all tasks in the BDD100K dataset eventually; see the [roadmap](#roadmap) for our plan and progress.
 
@@ -17,14 +17,15 @@ This repository currently supports the tasks listed below. For more information
 - [**Drivable Area**](./drivable)
 - [**Multiple Object Tracking (MOT)**](./mot)
 - [**Multiple Object Tracking and Segmentation (MOTS)**](./mots)
+- [**Pose Estimation**](./pose)
 
 If you have any questions, please go to the BDD100K [discussions](https://github.com/bdd100k/bdd100k/discussions).
 
 ## Roadmap
 
+- [x] Pose estimation
 - [ ] Lane marking
 - [ ] Panoptic segmentation
-- [ ] Pose estimation
 
 ## Dataset
 

det/README.md

@@ -0,0 +1,15 @@
+"""HRNet18, 1x schedule."""
+
+_base_ = "./faster_rcnn_hrnetv2p_w32_1x_det_bdd100k.py"
+model = dict(
+    pretrained="open-mmlab://msra/hrnetv2_w18",
+    backbone=dict(
+        extra=dict(
+            stage2=dict(num_channels=(18, 36)),
+            stage3=dict(num_channels=(18, 36, 72)),
+            stage4=dict(num_channels=(18, 36, 72, 144)),
+        ),
+    ),
+    neck=dict(type="HRFPN", in_channels=[18, 36, 72, 144], out_channels=256),
+)
+load_from = "https://dl.cv.ethz.ch/bdd100k/det/models/faster_rcnn_hrnetv2p_w18_1x_det_bdd100k.pth"

det/configs/det/faster_rcnn_hrnetv2p_w18_1x_det_bdd100k.py

@@ -0,0 +1,15 @@
+"""HRNet18, 3x schedule, MS training."""
+
+_base_ = "./faster_rcnn_hrnetv2p_w32_3x_det_bdd100k.py"
+model = dict(
+    pretrained="open-mmlab://msra/hrnetv2_w18",
+    backbone=dict(
+        extra=dict(
+            stage2=dict(num_channels=(18, 36)),
+            stage3=dict(num_channels=(18, 36, 72)),
+            stage4=dict(num_channels=(18, 36, 72, 144)),
+        ),
+    ),
+    neck=dict(type="HRFPN", in_channels=[18, 36, 72, 144], out_channels=256),
+)
+load_from = "https://dl.cv.ethz.ch/bdd100k/det/models/faster_rcnn_hrnetv2p_w18_3x_det_bdd100k.pth"

det/configs/det/faster_rcnn_hrnetv2p_w18_3x_det_bdd100k.py

@@ -0,0 +1,49 @@
+"""HRNet32, 1x schedule."""
+
+_base_ = "./faster_rcnn_r50_fpn_1x_det_bdd100k.py"
+model = dict(
+    pretrained="open-mmlab://msra/hrnetv2_w32",
+    backbone=dict(
+        _delete_=True,
+        type="HRNet",
+        extra=dict(
+            stage1=dict(
+                num_modules=1,
+                num_branches=1,
+                block="BOTTLENECK",
+                num_blocks=(4,),
+                num_channels=(64,),
+            ),
+            stage2=dict(
+                num_modules=1,
+                num_branches=2,
+                block="BASIC",
+                num_blocks=(4, 4),
+                num_channels=(32, 64),
+            ),
+            stage3=dict(
+                num_modules=4,
+                num_branches=3,
+                block="BASIC",
+                num_blocks=(4, 4, 4),
+                num_channels=(32, 64, 128),
+            ),
+            stage4=dict(
+                num_modules=3,
+                num_branches=4,
+                block="BASIC",
+                num_blocks=(4, 4, 4, 4),
+                num_channels=(32, 64, 128, 256),
+            ),
+        ),
+    ),
+    neck=dict(
+        _delete_=True,
+        type="HRFPN",
+        in_channels=[32, 64, 128, 256],
+        out_channels=256,
+    ),
+)
+data = dict(samples_per_gpu=2, workers_per_gpu=2)
+optimizer = dict(type="SGD", lr=0.02, momentum=0.9, weight_decay=0.0001)
+load_from = "https://dl.cv.ethz.ch/bdd100k/det/models/faster_rcnn_hrnetv2p_w32_1x_det_bdd100k.pth"

det/configs/det/faster_rcnn_hrnetv2p_w32_1x_det_bdd100k.py

@@ -0,0 +1,49 @@
+"""HRNet32, 3x schedule, MS training."""
+
+_base_ = "./faster_rcnn_r50_fpn_3x_det_bdd100k.py"
+model = dict(
+    pretrained="open-mmlab://msra/hrnetv2_w32",
+    backbone=dict(
+        _delete_=True,
+        type="HRNet",
+        extra=dict(
+            stage1=dict(
+                num_modules=1,
+                num_branches=1,
+                block="BOTTLENECK",
+                num_blocks=(4,),
+                num_channels=(64,),
+            ),
+            stage2=dict(
+                num_modules=1,
+                num_branches=2,
+                block="BASIC",
+                num_blocks=(4, 4),
+                num_channels=(32, 64),
+            ),
+            stage3=dict(
+                num_modules=4,
+                num_branches=3,
+                block="BASIC",
+                num_blocks=(4, 4, 4),
+                num_channels=(32, 64, 128),
+            ),
+            stage4=dict(
+                num_modules=3,
+                num_branches=4,
+                block="BASIC",
+                num_blocks=(4, 4, 4, 4),
+                num_channels=(32, 64, 128, 256),
+            ),
+        ),
+    ),
+    neck=dict(
+        _delete_=True,
+        type="HRFPN",
+        in_channels=[32, 64, 128, 256],
+        out_channels=256,
+    ),
+)
+data = dict(samples_per_gpu=2, workers_per_gpu=2)
+optimizer = dict(type="SGD", lr=0.02, momentum=0.9, weight_decay=0.0001)
+load_from = "https://dl.cv.ethz.ch/bdd100k/det/models/faster_rcnn_hrnetv2p_w32_3x_det_bdd100k.pth"

det/configs/det/faster_rcnn_hrnetv2p_w32_3x_det_bdd100k.py

@@ -0,0 +1,10 @@
+"""Libra R-CNN with ResNet101-FPN, 3x schedule, MS training."""
+
+_base_ = "./libra_faster_rcnn_r50_fpn_3x_det_bdd100k.py"
+model = dict(
+    backbone=dict(
+        depth=101,
+        init_cfg=dict(type="Pretrained", checkpoint="torchvision://resnet101"),
+    )
+)
+load_from = "https://dl.cv.ethz.ch/bdd100k/det/models/libra_faster_rcnn_r101_fpn_3x_det_bdd100k.pth"

det/configs/det/libra_faster_rcnn_r101_fpn_3x_det_bdd100k.py

@@ -0,0 +1,53 @@
+"""Libra R-CNN with ResNet50-FPN, 1x schedule."""
+
+_base_ = "./faster_rcnn_r50_fpn_1x_det_bdd100k.py"
+model = dict(
+    neck=[
+        dict(
+            type="FPN",
+            in_channels=[256, 512, 1024, 2048],
+            out_channels=256,
+            num_outs=5,
+        ),
+        dict(
+            type="BFP",
+            in_channels=256,
+            num_levels=5,
+            refine_level=2,
+            refine_type="non_local",
+        ),
+    ],
+    roi_head=dict(
+        bbox_head=dict(
+            loss_bbox=dict(
+                _delete_=True,
+                type="BalancedL1Loss",
+                alpha=0.5,
+                gamma=1.5,
+                beta=1.0,
+                loss_weight=1.0,
+            )
+        )
+    ),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(sampler=dict(neg_pos_ub=5), allowed_border=-1),
+        rcnn=dict(
+            sampler=dict(
+                _delete_=True,
+                type="CombinedSampler",
+                num=512,
+                pos_fraction=0.25,
+                add_gt_as_proposals=True,
+                pos_sampler=dict(type="InstanceBalancedPosSampler"),
+                neg_sampler=dict(
+                    type="IoUBalancedNegSampler",
+                    floor_thr=-1,
+                    floor_fraction=0,
+                    num_bins=3,
+                ),
+            )
+        ),
+    ),
+)
+load_from = "https://dl.cv.ethz.ch/bdd100k/det/models/libra_faster_rcnn_r50_fpn_1x_det_bdd100k.pth"

det/configs/det/libra_faster_rcnn_r50_fpn_1x_det_bdd100k.py

@@ -0,0 +1,53 @@
+"""Libra R-CNN with ResNet50-FPN, 3x schedule, MS training."""
+
+_base_ = "./faster_rcnn_r50_fpn_3x_det_bdd100k.py"
+model = dict(
+    neck=[
+        dict(
+            type="FPN",
+            in_channels=[256, 512, 1024, 2048],
+            out_channels=256,
+            num_outs=5,
+        ),
+        dict(
+            type="BFP",
+            in_channels=256,
+            num_levels=5,
+            refine_level=2,
+            refine_type="non_local",
+        ),
+    ],
+    roi_head=dict(
+        bbox_head=dict(
+            loss_bbox=dict(
+                _delete_=True,
+                type="BalancedL1Loss",
+                alpha=0.5,
+                gamma=1.5,
+                beta=1.0,
+                loss_weight=1.0,
+            )
+        )
+    ),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(sampler=dict(neg_pos_ub=5), allowed_border=-1),
+        rcnn=dict(
+            sampler=dict(
+                _delete_=True,
+                type="CombinedSampler",
+                num=512,
+                pos_fraction=0.25,
+                add_gt_as_proposals=True,
+                pos_sampler=dict(type="InstanceBalancedPosSampler"),
+                neg_sampler=dict(
+                    type="IoUBalancedNegSampler",
+                    floor_thr=-1,
+                    floor_fraction=0,
+                    num_bins=3,
+                ),
+            )
+        ),
+    ),
+)
+load_from = "https://dl.cv.ethz.ch/bdd100k/det/models/libra_faster_rcnn_r50_fpn_3x_det_bdd100k.pth"

det/configs/det/libra_faster_rcnn_r50_fpn_3x_det_bdd100k.py

@@ -107,9 +107,7 @@ def main() -> None:
 
     cfg = Config.fromfile(args.config)
     if cfg.load_from is None:
-        cfg_name = os.path.split(args.config)[-1].replace(
-            "_bdd100k.py", ".pth"
-        )
+        cfg_name = os.path.split(args.config)[-1].replace(".py", ".pth")
         cfg.load_from = MODEL_SERVER + cfg_name
     if args.cfg_options is not None:
         cfg.merge_from_dict(args.cfg_options)