update algorithm description in the README.md of configs and refactor…

… the directory of FP16 config (#327) * update sot metafile and refacor fp16 directory * refactor fp16 folds and add algorithm description * fix typos Co-authored-by: JingweiZhang12 <zhangjingwei@sensetime.com>
open-mmlab · Nov 23, 2021 · 6eee561 · 6eee561
1 parent f7a0221
commit 6eee561
Show file tree

Hide file tree

Showing 19 changed files with 308 additions and 223 deletions.
diff --git a/configs/fp16/README.md b/configs/fp16/README.md
diff --git a/configs/fp16/metafile.yml b/configs/fp16/metafile.yml
diff --git a/configs/fp16/selsa_faster_rcnn_r50_dc5_fp16_1x_imagenetvid.py b/configs/fp16/selsa_faster_rcnn_r50_dc5_fp16_1x_imagenetvid.py
diff --git a/configs/mot/deepsort/README.md b/configs/mot/deepsort/README.md
@@ -1,8 +1,18 @@
-# Deep SORT
+# Simple online and realtime tracking with a deep association metric
 
-## Introduction
+## Abstract
 
-[ALGORITHM]
+Simple Online and Realtime Tracking (SORT) is a pragmatic
+approach to multiple object tracking with a focus on simple,
+effective algorithms. In this paper, we integrate appearance
+information to improve the performance of SORT. Due to this
+extension we are able to track objects through longer periods of occlusions, effectively reducing the number of identity
+switches. In spirit of the original framework we place much
+of the computational complexity into an offline pre-training
+stage where we learn a deep association metric on a largescale person re-identification dataset. During online application, we establish measurement-to-track associations using
+nearest neighbor queries in visual appearance space. Experimental evaluation shows that our extensions reduce the number of identity switches by 45%, achieving overall competitive performance at high frame rates.
+
+## Citation
 
 ```latex
 @inproceedings{bewley2016simple,
@@ -31,13 +41,11 @@ The configs in this folder are basically for inference.
 Currently we do not support training ReID models.
 We directly use the ReID model from [Tracktor](https://github.com/phil-bergmann/tracking_wo_bnw). These missed features will be supported in the future.
 
-|    Detector     |  ReID  | Train Set | Test Set | Public | Inf time (fps) | MOTA | IDF1 | FP | FN | IDSw. | Config | Download |
-| :-------------: | :----: | :-------: | :------: | :----: | :------------: | :--: | :--: |:--:|:--:| :---: | :----: | :------: |
-| R50-FasterRCNN-FPN | -  | half-train | half-val | Y     | 28.3 |   46.0 | 46.6 | 289 | 82451 | 4581 | [config](sort_faster-rcnn_fpn_4e_mot17-public-half.py) |  [detector](https://download.openmmlab.com/mmtracking/mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-half-64ee2ed4.pth) |
-| R50-FasterRCNN-FPN | -  | half-train | half-val | N     | 18.6 |   62.0 | 57.8 | 15171 | 40437 | 5841 | [config](sort_faster-rcnn_fpn_4e_mot17-private-half.py) | [detector](https://download.openmmlab.com/mmtracking/mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-half-64ee2ed4.pth) |
-| R50-FasterRCNN-FPN | R50 | half-train | half-val | Y     | 20.4  |  48.1 | 60.8 | 283   | 82445 | 1199 | [config](deepsort_faster-rcnn_fpn_4e_mot17-public-half.py) | [detector](https://download.openmmlab.com/mmtracking/mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-half-64ee2ed4.pth) [reid](https://download.openmmlab.com/mmtracking/mot/reid/tracktor_reid_r50_iter25245-a452f51f.pth) |
-| R50-FasterRCNN-FPN | R50 | half-train | half-val | N     | 13.8  |  63.8 | 69.6 | 15060 | 40326 | 3183 | [config](deepsort_faster-rcnn_fpn_4e_mot17-private-half.py) | [detector](https://download.openmmlab.com/mmtracking/mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-half-64ee2ed4.pth) [reid](https://download.openmmlab.com/mmtracking/mot/reid/tracktor_reid_r50_iter25245-a452f51f.pth) |
-| R50-FasterRCNN-FPN | - | train | train | Y               | 28.3  | 50.9 | 44.5 | 1108 | 153950 | 10522 | [config](sort_faster-rcnn_fpn_4e_mot17-public.py) | [detector](https://download.openmmlab.com/mmtracking/mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-ffa52ae7.pth) |
-| R50-FasterRCNN-FPN | - | train | train | N               | 18.6  | 80.8 | 61.3 | 21537 | 29280 | 13947 | [config](sort_faster-rcnn_fpn_4e_mot17-private.py) | [detector](https://download.openmmlab.com/mmtracking/mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-ffa52ae7.pth) |
+|    Method     |    Detector     |  ReID  | Train Set | Test Set | Public | Inf time (fps) | MOTA | IDF1 | FP | FN | IDSw. | Config | Download |
+| :-------------: | :-------------: | :----: | :-------: | :------: | :----: | :------------: | :--: | :--: |:--:|:--:| :---: | :----: | :------: |
+| SORT | R50-FasterRCNN-FPN | -  | half-train | half-val | Y     | 28.3 |   46.0 | 46.6 | 289 | 82451 | 4581 | [config](sort_faster-rcnn_fpn_4e_mot17-public-half.py) |  [detector](https://download.openmmlab.com/mmtracking/mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-half-64ee2ed4.pth) |
+| SORT | R50-FasterRCNN-FPN | -  | half-train | half-val | N     | 18.6 |   62.0 | 57.8 | 15171 | 40437 | 5841 | [config](sort_faster-rcnn_fpn_4e_mot17-private-half.py) | [detector](https://download.openmmlab.com/mmtracking/mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-half-64ee2ed4.pth) |
+| DeepSORT | R50-FasterRCNN-FPN | R50 | half-train | half-val | Y     | 20.4  |  48.1 | 60.8 | 283   | 82445 | 1199 | [config](deepsort_faster-rcnn_fpn_4e_mot17-public-half.py) | [detector](https://download.openmmlab.com/mmtracking/mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-half-64ee2ed4.pth) [reid](https://download.openmmlab.com/mmtracking/mot/reid/tracktor_reid_r50_iter25245-a452f51f.pth) |
+| DeepSORT | R50-FasterRCNN-FPN | R50 | half-train | half-val | N     | 13.8  |  63.8 | 69.6 | 15060 | 40326 | 3183 | [config](deepsort_faster-rcnn_fpn_4e_mot17-private-half.py) | [detector](https://download.openmmlab.com/mmtracking/mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-half-64ee2ed4.pth) [reid](https://download.openmmlab.com/mmtracking/mot/reid/tracktor_reid_r50_iter25245-a452f51f.pth) |
 
 Note: When running `demo_mot.py`, we suggest you use the config containing `private`, since `private` means the MOT method doesn't need external detections.
diff --git a/configs/mot/deepsort/metafile.yml b/configs/mot/deepsort/metafile.yml
@@ -102,43 +102,3 @@ Models:
     Weights:
       - https://download.openmmlab.com/mmtracking/mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-half-64ee2ed4.pth
       - https://download.openmmlab.com/mmtracking/mot/reid/tracktor_reid_r50_iter25245-a452f51f.pth
-
-  - Name: sort_faster-rcnn_fpn_4e_mot17-public
-    In Collection: SORT
-    Config: configs/mot/deepsort/sort_faster-rcnn_fpn_4e_mot17-public.py
-    Metadata:
-      Training Data: MOT17-train
-      inference time (ms/im):
-        - value: 35.3
-          hardware: V100
-          backend: PyTorch
-          batch size: 1
-          mode: FP32
-          resolution: (640, 1088)
-    Results:
-      - Task: Multiple Object Tracking
-        Dataset: MOT17-train
-        Metrics:
-          MOTA: 50.9
-          IDF1: 44.5
-    Weights: https://download.openmmlab.com/mmtracking/mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-ffa52ae7.pth
-
-  - Name: sort_faster-rcnn_fpn_4e_mot17-private
-    In Collection: SORT
-    Config: configs/mot/deepsort/sort_faster-rcnn_fpn_4e_mot17-private.py
-    Metadata:
-      Training Data: MOT17-train
-      inference time (ms/im):
-        - value: 53.8
-          hardware: V100
-          backend: PyTorch
-          batch size: 1
-          mode: FP32
-          resolution: (640, 1088)
-    Results:
-      - Task: Multiple Object Tracking
-        Dataset: MOT17-train
-        Metrics:
-          MOTA: 80.8
-          IDF1: 61.3
-    Weights: https://download.openmmlab.com/mmtracking/mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-ffa52ae7.pth