Remove DaSiamRPN since we have its superseder VitTrack now (#213)

README.md

@@ -71,9 +71,9 @@ Some examples are listed below. You can find more in the directory of each model
 
 ![yolox demo](./models/object_detection_yolox/example_outputs/3_res.jpg)
 
-### Object Tracking with [DaSiamRPN](./models/object_tracking_dasiamrpn/)
+### Object Tracking with [VitTrack](./models/object_tracking_vittrack/)
 
-![webcam demo](./models/object_tracking_dasiamrpn/example_outputs/dasiamrpn_demo.gif)
+![webcam demo](./models/object_tracking_vittrack/example_outputs/vittrack_demo.gif)
 
 ### Palm Detection with [MP-PalmDet](./models/palm_detection_mediapipe/)
 

benchmark/README.md

@@ -31,7 +31,7 @@ python benchmark.py --all --fp32
 
 # All configs but exclude some of them (fill with config name keywords, not sensitive to upper/lower case, seperate with colons)
 python benchmark.py --all --cfg_exclude wechat
-python benchmark.py --all --cfg_exclude wechat:dasiamrpn
+python benchmark.py --all --cfg_exclude wechat:crnn
 
 # All configs but exclude some of the models (fill with exact model names, sensitive to upper/lower case, seperate with colons)
 python benchmark.py --all --model_exclude license_plate_detection_lpd_yunet_2023mar_int8.onnx:human_segmentation_pphumanseg_2023mar_int8.onnx
@@ -94,7 +94,6 @@ mean       median     min        input size   model
 46.10      47.53      43.06      [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
 144.89     149.58     125.71     [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
 143.83     146.39     119.75     [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-23.43      22.82      20.90      [1280, 720]  DaSiamRPN with ['object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx', 'object_tracking_dasiamrpn_kernel_r1_2021nov.onnx', 'object_tracking_dasiamrpn_model_2021nov.onnx']
 12.99      13.11      12.14      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
 12.64      12.44      10.82      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
 12.64      11.83      11.03      [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
@@ -149,7 +148,6 @@ mean       median     min        input size   model
 212.90     212.93     209.55     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
 1690.06    2303.34    1480.63    [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
 1489.54    1435.48    1308.12    [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-564.90     580.35     527.49     [1280, 720]  DaSiamRPN with ['object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx', 'object_tracking_dasiamrpn_kernel_r1_2021nov.onnx', 'object_tracking_dasiamrpn_model_2021nov.onnx']
 356.63     357.29     354.42     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
 217.52     229.39     101.61     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
 198.63     198.25     196.68     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
@@ -205,7 +203,6 @@ mean       median     min        input size   model
 216.18     216.19     214.30     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
 1207.83    1208.71    1203.64    [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
 1236.98    1250.21    1203.64    [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-456.79     456.90     445.83     [1280, 720]  DaSiamRPN with ['object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx', 'object_tracking_dasiamrpn_kernel_r1_2021nov.onnx', 'object_tracking_dasiamrpn_model_2021nov.onnx']
 124.89     125.25     124.53     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
 107.99     109.82     94.05      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
 108.41     108.33     107.91     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
@@ -244,7 +241,6 @@ mean       median     min        input size   model
 54.24      55.24      52.87      [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
 63.63      63.43      63.32      [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
 371.45     378.00     366.39     [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
-77.50      77.73      76.16      [1280, 720]  DaSiamRPN with ['object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx', 'object_tracking_dasiamrpn_kernel_r1_2021nov.onnx', 'object_tracking_dasiamrpn_model_2021nov.onnx']
 33.85      33.90      33.61      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
 38.16      37.33      37.10      [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
 91.65      91.98      89.90      [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
@@ -275,7 +271,6 @@ mean       median     min        input size   model
 366.46     366.88     363.46     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
 163.06     163.34     161.77     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
 301.10     311.52     297.74     [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
-53.34      54.30      51.79      [1280, 720]  DaSiamRPN with ['object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx', 'object_tracking_dasiamrpn_kernel_r1_2021nov.onnx', 'object_tracking_dasiamrpn_model_2021nov.onnx']
 149.37     149.95     148.01     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
 153.89     153.96     153.43     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
 44.29      44.03      43.62      [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
@@ -323,7 +318,6 @@ mean       median     min        input size   model
 212.69     262.75     170.88     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
 1110.87    1112.27    1085.31    [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
 1128.73    1157.12    1085.31    [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-382.57     464.42     354.66     [1280, 720]  DaSiamRPN with ['object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx', 'object_tracking_dasiamrpn_kernel_r1_2021nov.onnx', 'object_tracking_dasiamrpn_model_2021nov.onnx']
 147.01     144.01     139.27     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
 119.70     118.95     94.09      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
 107.63     107.09     105.61     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
@@ -404,7 +398,6 @@ mean       median     min        input size   model
 322.98     323.45     312.13     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
 1875.33    1877.53    1871.26    [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
 1989.04    2005.25    1871.26    [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-637.54     640.61     626.98     [1280, 720]  DaSiamRPN with ['object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx', 'object_tracking_dasiamrpn_kernel_r1_2021nov.onnx', 'object_tracking_dasiamrpn_model_2021nov.onnx']
 159.80     159.62     159.40     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
 152.18     152.86     145.56     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
 145.83     145.77     145.45     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
@@ -426,7 +419,7 @@ mean       median     min        input size   model
 NPU (CANN):
 
 ```
-$ python3 benchmark.py --all --fp32 --cfg_exclude wechat:dasiamrpn:crnn --model_exclude pose_estimation_mediapipe_2023mar.onnx --cfg_overwrite_backend_target 4
+$ python3 benchmark.py --all --fp32 --cfg_exclude wechat:crnn --model_exclude pose_estimation_mediapipe_2023mar.onnx --cfg_overwrite_backend_target 4
 Benchmarking ...
 backend=cv.dnn.DNN_BACKEND_CANN
 target=cv.dnn.DNN_TARGET_NPU
@@ -485,7 +478,6 @@ mean       median     min        input size   model
 1903.82    1962.71    1533.79    [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
 37604.10   37569.30   37502.48   [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
 24229.20   25577.94   13483.54   [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-14860.23   14988.15   14769.91   [1280, 720]  DaSiamRPN with ['object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx', 'object_tracking_dasiamrpn_kernel_r1_2021nov.onnx', 'object_tracking_dasiamrpn_model_2021nov.onnx']
 1133.44    1131.54    1124.83    [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
 883.96     919.07     655.33     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
 1430.98    1424.55    1415.68    [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
@@ -541,7 +533,6 @@ mean       median     min        input size   model
 117.28     150.31     83.33      [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
 553.58     558.76     535.47     [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
 594.18     592.64     535.47     [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-138.82     151.00     113.82     [1280, 720]  DaSiamRPN with ['object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx', 'object_tracking_dasiamrpn_kernel_r1_2021nov.onnx', 'object_tracking_dasiamrpn_model_2021nov.onnx']
 56.35      55.73      55.25      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
 57.07      57.19      55.25      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
 47.94      48.41      47.05      [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
@@ -596,7 +587,6 @@ mean       median     min        input size   model
 406.28     416.58     385.68     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
 2608.90    2612.42    2597.93    [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
 2609.88    2609.39    2597.93    [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-809.55     814.66     794.67     [1280, 720]  DaSiamRPN with ['object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx', 'object_tracking_dasiamrpn_kernel_r1_2021nov.onnx', 'object_tracking_dasiamrpn_model_2021nov.onnx']
 228.95     228.74     228.35     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
 227.97     228.61     226.76     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
 192.29     192.26     191.74     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
@@ -653,7 +643,6 @@ mean       median     min        input size   model
 3002.36    3047.94    2655.38    [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
 50678.08   50651.82   50651.19   [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
 36249.71   37771.22   24606.37   [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-19974.99   19984.80   19948.63   [1280, 720]  DaSiamRPN with ['object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx', 'object_tracking_dasiamrpn_kernel_r1_2021nov.onnx', 'object_tracking_dasiamrpn_model_2021nov.onnx']
 1502.15    1501.98    1500.99    [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
 1300.15    1320.44    1137.60    [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
 1993.05    1993.98    1991.86    [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
@@ -680,9 +669,9 @@ Specs: [details_cn](https://doc.rvspace.org/VisionFive2/PB/VisionFive_2/specific
 
 CPU:
 <!-- config wechat is excluded due to it needs building with opencv_contrib -->
-<!-- config dasiam is excluded due to opencv cannot find ffmpeg and its components -->
+<!-- config vittrack is excluded due to opencv cannot find ffmpeg and its components -->
 ```
-$ python3 benchmark.py --all --cfg_exclude wechat:dasiam
+$ python3 benchmark.py --all --cfg_exclude wechat:vittrack
 Benchmarking ...
 backend=cv.dnn.DNN_BACKEND_OPENCV
 target=cv.dnn.DNN_TARGET_CPU

benchmark/config/object_tracking_dasiamrpn.yaml

@@ -1,14 +0,0 @@
-Benchmark:
-  name: "Object Tracking Benchmark"
-  type: "Tracking"
-  data:
-    type: "TrackingVideoLoader"
-    path: "data/object_tracking"
-    files: ["throw_cup.mp4"]
-  metric:
-    type: "Tracking"
-  backend: "default"
-  target: "cpu"
-
-Model:
-  name: "DaSiamRPN"

benchmark/table_config.yaml

@@ -122,13 +122,6 @@ Models:
     acceptable_time: 100
     keyword: "WeChatQRCode"
 
-  - name: "DaSiamRPN"
-    task: "Object Tracking"
-    input_size: "1280x720"
-    folder: "object_tracking_dasiamrpn"
-    acceptable_time: 3000
-    keyword: "object_tracking_dasiamrpn"
-
   - name: "YoutuReID"
     task: "Person Re-Identification"
     input_size: "128x256"

models/__init__.py

@@ -11,7 +11,6 @@ from .human_segmentation_pphumanseg.pphumanseg import PPHumanSeg
 from .person_detection_mediapipe.mp_persondet import MPPersonDet
 from .pose_estimation_mediapipe.mp_pose import MPPose
 from .qrcode_wechatqrcode.wechatqrcode import WeChatQRCode
-from .object_tracking_dasiamrpn.dasiamrpn import DaSiamRPN
 from .person_reid_youtureid.youtureid import YoutuReID
 from .image_classification_mobilenet.mobilenet import MobileNet
 from .palm_detection_mediapipe.mp_palmdet import MPPalmDet
@@ -85,7 +84,6 @@ MODELS.register(PPHumanSeg)
 MODELS.register(MPPersonDet)
 MODELS.register(MPPose)
 MODELS.register(WeChatQRCode)
-MODELS.register(DaSiamRPN)
 MODELS.register(YoutuReID)
 MODELS.register(MobileNet)
 MODELS.register(MPPalmDet)

models/object_tracking_dasiamrpn/LICENSE

@@ -1,202 +0,0 @@
-
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [yyyy] [name of copyright owner]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.

models/object_tracking_dasiamrpn/README.md

@@ -1,37 +0,0 @@
-# DaSiamRPN
-
-[Distractor-aware Siamese Networks for Visual Object Tracking](https://arxiv.org/abs/1808.06048)
-
-Note:
-
-- Model source: [opencv/samples/dnn/diasiamrpn_tracker.cpp](https://github.com/opencv/opencv/blob/ceb94d52a104c0c1287a43dfa6ba72705fb78ac1/samples/dnn/dasiamrpn_tracker.cpp#L5-L7)
-- Visit https://github.com/foolwood/DaSiamRPN for training details.
-
-## Demo
-
-Run the following command to try the demo:
-
-```shell
-# track on camera input
-python demo.py
-# track on video input
-python demo.py --input /path/to/video -v
-
-# get help regarding various parameters
-python demo.py --help
-```
-
-### Example outputs
-
-![webcam demo](./example_outputs/dasiamrpn_demo.gif)
-
-## License
-
-All files in this directory are licensed under [Apache 2.0 License](./LICENSE).
-
-## Reference:
-
-- DaSiamRPN Official Repository: https://github.com/foolwood/DaSiamRPN
-- Paper: https://arxiv.org/abs/1808.06048
-- OpenCV API `TrackerDaSiamRPN` Doc: https://docs.opencv.org/4.x/de/d93/classcv_1_1TrackerDaSiamRPN.html
-- OpenCV Sample: https://github.com/opencv/opencv/blob/4.x/samples/dnn/dasiamrpn_tracker.cpp

models/object_tracking_dasiamrpn/dasiamrpn.py

@@ -1,48 +0,0 @@
-# This file is part of OpenCV Zoo project.
-# It is subject to the license terms in the LICENSE file found in the same directory.
-#
-# Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
-# Third party copyrights are property of their respective owners.
-
-import numpy as np
-import cv2 as cv
-
-class DaSiamRPN:
-    def __init__(self, kernel_cls1_path, kernel_r1_path, model_path, backend_id=0, target_id=0):
-        self._model_path = model_path
-        self._kernel_cls1_path = kernel_cls1_path
-        self._kernel_r1_path = kernel_r1_path
-        self._backend_id = backend_id
-        self._target_id = target_id
-
-        self._param = cv.TrackerDaSiamRPN_Params()
-        self._param.model = self._model_path
-        self._param.kernel_cls1 = self._kernel_cls1_path
-        self._param.kernel_r1 = self._kernel_r1_path
-        self._param.backend = self._backend_id
-        self._param.target = self._target_id
-        self._model = cv.TrackerDaSiamRPN.create(self._param)
-
-    @property
-    def name(self):
-        return self.__class__.__name__
-
-    def setBackendAndTarget(self, backendId, targetId):
-        self._backend_id = backendId
-        self._target_id = targetId
-
-        self._param = cv.TrackerDaSiamRPN_Params()
-        self._param.model = self._model_path
-        self._param.kernel_cls1 = self._kernel_cls1_path
-        self._param.kernel_r1 = self._kernel_r1_path
-        self._param.backend = self._backend_id
-        self._param.target = self._target_id
-        self._model = cv.TrackerDaSiamRPN.create(self._param)
-
-    def init(self, image, roi):
-        self._model.init(image, roi)
-
-    def infer(self, image):
-        isLocated, bbox = self._model.update(image)
-        score = self._model.getTrackingScore()
-        return isLocated, bbox, score

models/object_tracking_dasiamrpn/demo.py

@@ -1,118 +0,0 @@
-# This file is part of OpenCV Zoo project.
-# It is subject to the license terms in the LICENSE file found in the same directory.
-#
-# Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
-# Third party copyrights are property of their respective owners.
-
-import argparse
-
-import numpy as np
-import cv2 as cv
-
-from dasiamrpn import DaSiamRPN
-
-# Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
-       "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
-
-# Valid combinations of backends and targets
-backend_target_pairs = [
-    [cv.dnn.DNN_BACKEND_OPENCV, cv.dnn.DNN_TARGET_CPU],
-    [cv.dnn.DNN_BACKEND_CUDA,   cv.dnn.DNN_TARGET_CUDA],
-    [cv.dnn.DNN_BACKEND_CUDA,   cv.dnn.DNN_TARGET_CUDA_FP16],
-    [cv.dnn.DNN_BACKEND_TIMVX,  cv.dnn.DNN_TARGET_NPU],
-    [cv.dnn.DNN_BACKEND_CANN,   cv.dnn.DNN_TARGET_NPU]
-]
-
-parser = argparse.ArgumentParser(
-    description="Distractor-aware Siamese Networks for Visual Object Tracking (https://arxiv.org/abs/1808.06048)")
-parser.add_argument('--input', '-i', type=str,
-                    help='Usage: Set path to the input video. Omit for using default camera.')
-parser.add_argument('--model_path', type=str, default='object_tracking_dasiamrpn_model_2021nov.onnx',
-                    help='Usage: Set model path, defaults to object_tracking_dasiamrpn_model_2021nov.onnx.')
-parser.add_argument('--kernel_cls1_path', type=str, default='object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx',
-                    help='Usage: Set path to dasiamrpn_kernel_cls1.onnx.')
-parser.add_argument('--kernel_r1_path', type=str, default='object_tracking_dasiamrpn_kernel_r1_2021nov.onnx',
-                    help='Usage: Set path to dasiamrpn_kernel_r1.onnx.')
-parser.add_argument('--backend_target', '-bt', type=int, default=0,
-                    help='''Choose one of the backend-target pair to run this demo:
-                        {:d}: (default) OpenCV implementation + CPU,
-                        {:d}: CUDA + GPU (CUDA),
-                        {:d}: CUDA + GPU (CUDA FP16),
-                        {:d}: TIM-VX + NPU,
-                        {:d}: CANN + NPU
-                    '''.format(*[x for x in range(len(backend_target_pairs))]))
-parser.add_argument('--save', '-s', action='store_true',
-                    help='Usage: Specify to save a file with results. Invalid in case of camera input.')
-parser.add_argument('--vis', '-v', action='store_true',
-                    help='Usage: Specify to open a new window to show results. Invalid in case of camera input.')
-args = parser.parse_args()
-
-def visualize(image, bbox, score, isLocated, fps=None, box_color=(0, 255, 0),text_color=(0, 255, 0), fontScale = 1, fontSize = 1):
-    output = image.copy()
-    h, w, _ = output.shape
-
-    if fps is not None:
-        cv.putText(output, 'FPS: {:.2f}'.format(fps), (0, 30), cv.FONT_HERSHEY_DUPLEX, fontScale, text_color, fontSize)
-
-    if isLocated and score >= 0.6:
-        # bbox: Tuple of length 4
-        x, y, w, h = bbox
-        cv.rectangle(output, (x, y), (x+w, y+h), box_color, 2)
-        cv.putText(output, '{:.2f}'.format(score), (x, y+20), cv.FONT_HERSHEY_DUPLEX, fontScale, text_color, fontSize)
-    else:
-        text_size, baseline = cv.getTextSize('Target lost!', cv.FONT_HERSHEY_DUPLEX, fontScale, fontSize)
-        text_x = int((w - text_size[0]) / 2)
-        text_y = int((h - text_size[1]) / 2)
-        cv.putText(output, 'Target lost!', (text_x, text_y), cv.FONT_HERSHEY_DUPLEX, fontScale, (0, 0, 255), fontSize)
-
-    return output
-
-if __name__ == '__main__':
-    backend_id = backend_target_pairs[args.backend_target][0]
-    target_id = backend_target_pairs[args.backend_target][1]
-
-    # Instantiate DaSiamRPN
-    model = DaSiamRPN(
-        kernel_cls1_path=args.kernel_cls1_path,
-        kernel_r1_path=args.kernel_r1_path,
-        model_path=args.model_path,
-        backend_id=backend_id,
-        target_id=target_id)
-
-    # Read from args.input
-    _input = args.input
-    if args.input is None:
-        device_id = 0
-        _input = device_id
-    video = cv.VideoCapture(_input)
-
-    # Select an object
-    has_frame, first_frame = video.read()
-    if not has_frame:
-        print('No frames grabbed!')
-        exit()
-    first_frame_copy = first_frame.copy()
-    cv.putText(first_frame_copy, "1. Drag a bounding box to track.", (0, 15), cv.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0))
-    cv.putText(first_frame_copy, "2. Press ENTER to confirm", (0, 35), cv.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0))
-    roi = cv.selectROI('DaSiamRPN Demo', first_frame_copy)
-    print("Selected ROI: {}".format(roi))
-
-    # Init tracker with ROI
-    model.init(first_frame, roi)
-
-    # Track frame by frame
-    tm = cv.TickMeter()
-    while cv.waitKey(1) < 0:
-        has_frame, frame = video.read()
-        if not has_frame:
-            print('End of video')
-            break
-        # Inference
-        tm.start()
-        isLocated, bbox, score = model.infer(frame)
-        tm.stop()
-        # Visualize
-        frame = visualize(frame, bbox, score, isLocated, fps=tm.getFPS())
-        cv.imshow('DaSiamRPN Demo', frame)
-        tm.reset()

tools/quantize/quantize-ort.py

@@ -102,7 +102,7 @@ models=dict(
     ppresnet50=Quantize(model_path='../../models/image_classification_ppresnet/image_classification_ppresnet50_2022jan.onnx',
                         calibration_image_dir='../../benchmark/data/image_classification',
                         transforms=Compose([Resize(size=(224, 224))])),
-    # TBD: DaSiamRPN
+    # TBD: VitTrack
     youtureid=Quantize(model_path='../../models/person_reid_youtureid/person_reid_youtu_2021nov.onnx',
                        calibration_image_dir='../../benchmark/data/person_reid',
                        transforms=Compose([Resize(size=(128, 256))])),