mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2025-06-11 11:45:30 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Updated TensorFlow Object Detection API (markdown)

Abduragim Shtanchaev 2023-06-09 13:15:47 +03:00
parent 34e5a49ae1
commit 9962ac6f3a
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
TensorFlow-Object-Detection-API.md

@ -63,15 +63,15 @@ You can use one of the configs that has been tested in OpenCV. This choice depen
| Model | Version | ||
|-------|-------------|----|----|
| MobileNet-SSD v1 | 2017_11_17 | [weights](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_coco_2017_11_17.tar.gz) | [config](https://github.com/opencv/opencv_extra/blob/master/testdata/dnn/ssd_mobilenet_v1_coco_2017_11_17.pbtxt)
| MobileNet-SSD v1 PPN | 2018_07_03 | [weights](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_ppn_shared_box_predictor_300x300_coco14_sync_2018_07_03.tar.gz) | [config](https://github.com/opencv/opencv_extra/blob/master/testdata/dnn/ssd_mobilenet_v1_ppn_coco.pbtxt)
| MobileNet-SSD v2 | 2018_03_29 | [weights](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v2_coco_2018_03_29.tar.gz) | [config](https://github.com/opencv/opencv_extra/blob/master/testdata/dnn/ssd_mobilenet_v2_coco_2018_03_29.pbtxt)
| MobileNet-SSD v1 | 2017_11_17 | [weights](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_coco_2017_11_17.tar.gz) | [config](https://github.com/opencv/opencv_extra/blob/4.x/testdata/dnn/ssd_mobilenet_v1_coco_2017_11_17.pbtxt)
| MobileNet-SSD v1 PPN | 2018_07_03 | [weights](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_ppn_shared_box_predictor_300x300_coco14_sync_2018_07_03.tar.gz) | [config](https://github.com/opencv/opencv_extra/blob/4.x/testdata/dnn/ssd_mobilenet_v1_ppn_coco.pbtxt)
| MobileNet-SSD v2 | 2018_03_29 | [weights](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v2_coco_2018_03_29.tar.gz) | [config](https://github.com/opencv/opencv_extra/blob/4.x/testdata/dnn/ssd_mobilenet_v2_coco_2018_03_29.pbtxt)
| Inception-SSD v2 | 2017_11_17 | [weights](http://download.tensorflow.org/models/object_detection/ssd_inception_v2_coco_2017_11_17.tar.gz) | [config](https://github.com/opencv/opencv_extra/blob/4.x/testdata/dnn/ssd_inception_v2_coco_2017_11_17.pbtxt)
| MobileNet-SSD v3 (see [#16760](https://github.com/opencv/opencv/pull/16760)) | 2020_01_14 | [weights](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v3_large_coco_2020_01_14.tar.gz) | [config](https://gist.github.com/dkurt/54a8e8b51beb3bd3f770b79e56927bd7) |
| Faster-RCNN Inception v2 | 2018_01_28 | [weights](http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_v2_coco_2018_01_28.tar.gz) | [config](https://github.com/opencv/opencv_extra/blob/master/testdata/dnn/faster_rcnn_inception_v2_coco_2018_01_28.pbtxt)
| Faster-RCNN ResNet-50 | 2018_01_28 | [weights](http://download.tensorflow.org/models/object_detection/faster_rcnn_resnet50_coco_2018_01_28.tar.gz) | [config](https://github.com/opencv/opencv_extra/blob/master/testdata/dnn/faster_rcnn_resnet50_coco_2018_01_28.pbtxt)
| Mask-RCNN Inception v2 | 2018_01_28 | [weights](http://download.tensorflow.org/models/object_detection/mask_rcnn_inception_v2_coco_2018_01_28.tar.gz) | [config](https://github.com/opencv/opencv_extra/blob/master/testdata/dnn/mask_rcnn_inception_v2_coco_2018_01_28.pbtxt)
| EfficientDet-D0 (see [#17384](https://github.com/opencv/opencv/pull/17384)) | | [weights](https://www.dropbox.com/s/9mqp99fd2tpuqn6/efficientdet-d0.pb?dl=1) | [config](https://github.com/opencv/opencv_extra/blob/master/testdata/dnn/efficientdet-d0.pbtxt)
| Faster-RCNN Inception v2 | 2018_01_28 | [weights](http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_v2_coco_2018_01_28.tar.gz) | [config](https://github.com/opencv/opencv_extra/blob/4.x/testdata/dnn/faster_rcnn_inception_v2_coco_2018_01_28.pbtxt)
| Faster-RCNN ResNet-50 | 2018_01_28 | [weights](http://download.tensorflow.org/models/object_detection/faster_rcnn_resnet50_coco_2018_01_28.tar.gz) | [config](https://github.com/opencv/opencv_extra/blob/4.x/testdata/dnn/faster_rcnn_resnet50_coco_2018_01_28.pbtxt)
| Mask-RCNN Inception v2 | 2018_01_28 | [weights](http://download.tensorflow.org/models/object_detection/mask_rcnn_inception_v2_coco_2018_01_28.tar.gz) | [config](https://github.com/opencv/opencv_extra/blob/4.x/testdata/dnn/mask_rcnn_inception_v2_coco_2018_01_28.pbtxt)
| EfficientDet-D0 (see [#17384](https://github.com/opencv/opencv/pull/17384)) | | [weights](https://www.dropbox.com/s/9mqp99fd2tpuqn6/efficientdet-d0.pb?dl=1) | [config](https://github.com/opencv/opencv_extra/blob/4.x/testdata/dnn/efficientdet-d0.pbtxt)
### Generate a config file
Use one of the scripts which generate a text graph representation for a frozen `.pb` model depends on its architecture: