mirror of
https://github.com/opencv/opencv.git
synced 2024-12-11 14:39:11 +08:00
073488896e
Improved and refactored text detection sample in dnn module #25326 Clean up samples: #25006 This pull requests merges and simplifies different text detection samples in dnn module of opencv in to one file. An option has been provided to choose the detection model from EAST or DB ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [x] The PR is proposed to the proper branch - [x] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [x] The feature is well documented and sample code can be built with the project CMake
351 lines
11 KiB
YAML
351 lines
11 KiB
YAML
%YAML 1.0
|
|
---
|
|
################################################################################
|
|
# Object detection models.
|
|
################################################################################
|
|
|
|
# YOLOv8 object detection family from ultralytics (https://github.com/ultralytics/ultralytics)
|
|
# Might be used for all YOLOv8n YOLOv8s YOLOv8m YOLOv8l and YOLOv8x
|
|
yolov8x:
|
|
load_info:
|
|
url: "https://huggingface.co/cabelo/yolov8/resolve/main/yolov8x.onnx?download=true"
|
|
sha1: "462f15d668c046d38e27d3df01fe8142dd004cb4"
|
|
model: "yolov8x.onnx"
|
|
mean: 0.0
|
|
scale: 0.00392
|
|
width: 640
|
|
height: 640
|
|
rgb: true
|
|
classes: "object_detection_classes_yolo.txt"
|
|
background_label_id: 0
|
|
sample: "yolo_detector"
|
|
|
|
yolov8s:
|
|
load_info:
|
|
url: "https://github.com/CVHub520/X-AnyLabeling/releases/download/v0.1.0/yolov8s.onnx"
|
|
sha1: "82cd83984396fe929909ecb58212b0e86d0904b1"
|
|
model: "yolov8s.onnx"
|
|
mean: 0.0
|
|
scale: 0.00392
|
|
width: 640
|
|
height: 640
|
|
rgb: true
|
|
classes: "object_detection_classes_yolo.txt"
|
|
background_label_id: 0
|
|
sample: "yolo_detector"
|
|
|
|
yolov8n:
|
|
load_info:
|
|
url: "https://github.com/CVHub520/X-AnyLabeling/releases/download/v0.1.0/yolov8n.onnx"
|
|
sha1: "68f864475d06e2ec4037181052739f268eeac38d"
|
|
model: "yolov8n.onnx"
|
|
mean: 0.0
|
|
scale: 0.00392
|
|
width: 640
|
|
height: 640
|
|
rgb: true
|
|
classes: "object_detection_classes_yolo.txt"
|
|
background_label_id: 0
|
|
sample: "yolo_detector"
|
|
|
|
yolov8m:
|
|
load_info:
|
|
url: "https://github.com/CVHub520/X-AnyLabeling/releases/download/v0.1.0/yolov8m.onnx"
|
|
sha1: "656ffeb4f3b067bc30df956728b5f9c61a4cb090"
|
|
model: "yolov8m.onnx"
|
|
mean: 0.0
|
|
scale: 0.00392
|
|
width: 640
|
|
height: 640
|
|
rgb: true
|
|
classes: "object_detection_classes_yolo.txt"
|
|
background_label_id: 0
|
|
sample: "yolo_detector"
|
|
|
|
yolov8l:
|
|
load_info:
|
|
url: "https://github.com/CVHub520/X-AnyLabeling/releases/download/v0.1.0/yolov8l.onnx"
|
|
sha1: "462df53ca3a85d110bf6be7fc2e2bb1277124395"
|
|
model: "yolov8l.onnx"
|
|
mean: 0.0
|
|
scale: 0.00392
|
|
width: 640
|
|
height: 640
|
|
rgb: true
|
|
classes: "object_detection_classes_yolo.txt"
|
|
background_label_id: 0
|
|
sample: "yolo_detector"
|
|
|
|
# YOLO4 object detection family from Darknet (https://github.com/AlexeyAB/darknet)
|
|
# YOLO object detection family from Darknet (https://pjreddie.com/darknet/yolo/)
|
|
# Might be used for all YOLOv2, TinyYolov2, YOLOv3, YOLOv4 and TinyYolov4
|
|
yolov4:
|
|
load_info:
|
|
url: "https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v3_optimal/yolov4.weights"
|
|
sha1: "0143deb6c46fcc7f74dd35bf3c14edc3784e99ee"
|
|
model: "yolov4.weights"
|
|
config: "yolov4.cfg"
|
|
mean: [0, 0, 0]
|
|
scale: 0.00392
|
|
width: 416
|
|
height: 416
|
|
rgb: true
|
|
classes: "object_detection_classes_yolo.txt"
|
|
background_label_id: 0
|
|
sample: "object_detection"
|
|
|
|
yolov4-tiny:
|
|
load_info:
|
|
url: "https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v4_pre/yolov4-tiny.weights"
|
|
sha1: "451caaab22fb9831aa1a5ee9b5ba74a35ffa5dcb"
|
|
model: "yolov4-tiny.weights"
|
|
config: "yolov4-tiny.cfg"
|
|
mean: [0, 0, 0]
|
|
scale: 0.00392
|
|
width: 416
|
|
height: 416
|
|
rgb: true
|
|
classes: "object_detection_classes_yolo.txt"
|
|
background_label_id: 0
|
|
sample: "object_detection"
|
|
|
|
yolov3:
|
|
load_info:
|
|
url: "https://pjreddie.com/media/files/yolov3.weights"
|
|
sha1: "520878f12e97cf820529daea502acca380f1cb8e"
|
|
model: "yolov3.weights"
|
|
config: "yolov3.cfg"
|
|
mean: [0, 0, 0]
|
|
scale: 0.00392
|
|
width: 416
|
|
height: 416
|
|
rgb: true
|
|
classes: "object_detection_classes_yolo.txt"
|
|
background_label_id: 0
|
|
sample: "object_detection"
|
|
|
|
tiny-yolo-voc:
|
|
load_info:
|
|
url: "https://pjreddie.com/media/files/yolov2-tiny-voc.weights"
|
|
sha1: "24b4bd049fc4fa5f5e95f684a8967e65c625dff9"
|
|
model: "tiny-yolo-voc.weights"
|
|
config: "tiny-yolo-voc.cfg"
|
|
mean: [0, 0, 0]
|
|
scale: 0.00392
|
|
width: 416
|
|
height: 416
|
|
rgb: true
|
|
classes: "object_detection_classes_pascal_voc.txt"
|
|
background_label_id: 0
|
|
sample: "object_detection"
|
|
|
|
yolov8:
|
|
load_info:
|
|
url: "https://github.com/CVHub520/X-AnyLabeling/releases/download/v0.1.0/yolov8n.onnx"
|
|
sha1: "68f864475d06e2ec4037181052739f268eeac38d"
|
|
model: "yolov8n.onnx"
|
|
mean: [0, 0, 0]
|
|
scale: 0.00392
|
|
width: 640
|
|
height: 640
|
|
rgb: true
|
|
postprocessing: "yolov8"
|
|
classes: "object_detection_classes_yolo.txt"
|
|
sample: "object_detection"
|
|
|
|
# Caffe implementation of SSD model from https://github.com/chuanqi305/MobileNet-SSD
|
|
ssd_caffe:
|
|
load_info:
|
|
url: "https://drive.google.com/uc?export=download&id=0B3gersZ2cHIxRm5PMWRoTkdHdHc"
|
|
sha1: "994d30a8afaa9e754d17d2373b2d62a7dfbaaf7a"
|
|
model: "MobileNetSSD_deploy.caffemodel"
|
|
config: "MobileNetSSD_deploy.prototxt"
|
|
mean: [127.5, 127.5, 127.5]
|
|
scale: 0.007843
|
|
width: 300
|
|
height: 300
|
|
rgb: false
|
|
classes: "object_detection_classes_pascal_voc.txt"
|
|
sample: "object_detection"
|
|
|
|
# TensorFlow implementation of SSD model from https://github.com/tensorflow/models/tree/master/research/object_detection
|
|
ssd_tf:
|
|
load_info:
|
|
url: "http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_coco_2017_11_17.tar.gz"
|
|
sha1: "9e4bcdd98f4c6572747679e4ce570de4f03a70e2"
|
|
download_sha: "6157ddb6da55db2da89dd561eceb7f944928e317"
|
|
download_name: "ssd_mobilenet_v1_coco_2017_11_17.tar.gz"
|
|
member: "ssd_mobilenet_v1_coco_2017_11_17/frozen_inference_graph.pb"
|
|
model: "ssd_mobilenet_v1_coco_2017_11_17.pb"
|
|
config: "ssd_mobilenet_v1_coco_2017_11_17.pbtxt"
|
|
mean: [0, 0, 0]
|
|
scale: 1.0
|
|
width: 300
|
|
height: 300
|
|
rgb: true
|
|
classes: "object_detection_classes_coco.txt"
|
|
sample: "object_detection"
|
|
|
|
# TensorFlow implementation of Faster-RCNN model from https://github.com/tensorflow/models/tree/master/research/object_detection
|
|
faster_rcnn_tf:
|
|
load_info:
|
|
url: "http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_v2_coco_2018_01_28.tar.gz"
|
|
sha1: "f2e4bf386b9bb3e25ddfcbbd382c20f417e444f3"
|
|
download_sha: "c710f25e5c6a3ce85fe793d5bf266d581ab1c230"
|
|
download_name: "faster_rcnn_inception_v2_coco_2018_01_28.tar.gz"
|
|
member: "faster_rcnn_inception_v2_coco_2018_01_28/frozen_inference_graph.pb"
|
|
model: "faster_rcnn_inception_v2_coco_2018_01_28.pb"
|
|
config: "faster_rcnn_inception_v2_coco_2018_01_28.pbtxt"
|
|
mean: [0, 0, 0]
|
|
scale: 1.0
|
|
width: 800
|
|
height: 600
|
|
rgb: true
|
|
sample: "object_detection"
|
|
|
|
################################################################################
|
|
# Image classification models.
|
|
################################################################################
|
|
|
|
squeezenet:
|
|
load_info:
|
|
url: "https://github.com/onnx/models/raw/main/validated/vision/classification/squeezenet/model/squeezenet1.1-7.onnx?download="
|
|
sha1: "ec31942d17715941bb9b81f3a91dc59def9236be"
|
|
model: "squeezenet1.1-7.onnx"
|
|
mean: [0.485, 0.456, 0.406]
|
|
std: [0.229, 0.224, 0.225]
|
|
scale: 0.003921
|
|
width: 224
|
|
height: 224
|
|
rgb: true
|
|
labels: "classification_classes_ILSVRC2012.txt"
|
|
sample: "classification"
|
|
|
|
googlenet:
|
|
load_info:
|
|
url: "https://github.com/onnx/models/raw/69c5d3751dda5349fd3fc53f525395d180420c07/vision/classification/inception_and_googlenet/googlenet/model/googlenet-8.onnx"
|
|
sha1: "da39a3ee5e6b4b0d3255bfef95601890afd80709"
|
|
model: "googlenet-8.onnx"
|
|
mean: [103.939, 116.779, 123.675]
|
|
std: [1, 1, 1]
|
|
scale: 1.0
|
|
width: 224
|
|
height: 224
|
|
rgb: false
|
|
labels: "classification_classes_ILSVRC2012.txt"
|
|
sample: "classification"
|
|
|
|
resnet:
|
|
load_info:
|
|
url: "https://github.com/onnx/models/raw/main/validated/vision/classification/resnet/model/resnet50-v2-7.onnx"
|
|
sha1: "c3a67b3cb2f0a61a7eb75eb8bd9139c89557cbe0"
|
|
model: "resnet50-v2-7.onnx"
|
|
mean: [123.675, 116.28, 103.53]
|
|
std: [58.395, 57.12, 57.375]
|
|
scale: 1.0
|
|
width: 224
|
|
height: 224
|
|
rgb: true
|
|
labels: "classification_classes_ILSVRC2012.txt"
|
|
sample: "classification"
|
|
|
|
################################################################################
|
|
# Semantic segmentation models.
|
|
################################################################################
|
|
|
|
fcnresnet50:
|
|
load_info:
|
|
url: "https://github.com/onnx/models/raw/491ce05590abb7551d7fae43c067c060eeb575a6/validated/vision/object_detection_segmentation/fcn/model/fcn-resnet50-12.onnx"
|
|
sha1: "1bb0c7e0034038969aecc6251166f1612a139230"
|
|
model: "fcn-resnet50-12.onnx"
|
|
mean: [103.5, 116.2, 123.6]
|
|
scale: 0.019
|
|
width: 500
|
|
height: 500
|
|
rgb: false
|
|
sample: "segmentation"
|
|
|
|
fcnresnet101:
|
|
load_info:
|
|
url: "https://github.com/onnx/models/raw/fb8271d5d5d9b90dbb1eb5e8e40f8f580fb248b3/vision/object_detection_segmentation/fcn/model/fcn-resnet101-11.onnx"
|
|
sha1: "e7e76474bf6b73334ab32c4be1374c9e605f5aed"
|
|
model: "fcn-resnet101-11.onnx"
|
|
mean: [103.5, 116.2, 123.6]
|
|
scale: 0.019
|
|
width: 500
|
|
height: 500
|
|
rgb: false
|
|
sample: "segmentation"
|
|
|
|
u2netp:
|
|
load_info:
|
|
url: "https://github.com/danielgatis/rembg/releases/download/v0.0.0/u2netp.onnx"
|
|
sha1: "0a99236f0d5c1916a99a8c401b23e5ef32038606"
|
|
model: "u2netp.onnx"
|
|
mean: [123.6, 116.2, 103.5]
|
|
scale: 0.019
|
|
width: 320
|
|
height: 320
|
|
rgb: true
|
|
sample: "segmentation"
|
|
|
|
################################################################################
|
|
# Text detection models.
|
|
################################################################################
|
|
|
|
DB:
|
|
load_info:
|
|
url: "https://drive.google.com/uc?export=dowload&id=17_ABp79PlFt9yPCxSaarVc_DKTmrSGGf"
|
|
sha1: "bef233c28947ef6ec8c663d20a2b326302421fa3"
|
|
model: "DB_IC15_resnet50.onnx"
|
|
ocr_load_info:
|
|
ocr_url: "https://drive.google.com/uc?export=dowload&id=159VavnbvfBQkLIPSAu2SP5Yij1Fy4azw"
|
|
ocr_sha1: "c4ab1fb3f13c1c8ffc04f016e72ec85311de4ebe"
|
|
ocr_model: "VGG_CTC.onnx"
|
|
mean: [122.67891434, 116.66876762, 104.00698793]
|
|
scale: 0.00392
|
|
width: 736
|
|
height: 736
|
|
rgb: false
|
|
sample: "text_detection"
|
|
|
|
East:
|
|
load_info:
|
|
url: "https://www.dropbox.com/s/r2ingd0l3zt8hxs/frozen_east_text_detection.tar.gz?dl=1"
|
|
sha1: "fffabf5ac36f37bddf68e34e84b45f5c4247ed06"
|
|
download_name: "frozen_east_text_detection.tar.gz"
|
|
download_sha: "3ca8233d6edd748f7ed23246c8ca24cbf696bb94"
|
|
model: "frozen_east_text_detection.pb"
|
|
ocr_load_info:
|
|
ocr_url: "https://drive.google.com/uc?export=dowload&id=159VavnbvfBQkLIPSAu2SP5Yij1Fy4azw"
|
|
ocr_sha1: "c4ab1fb3f13c1c8ffc04f016e72ec85311de4ebe"
|
|
ocr_model: "VGG_CTC.onnx"
|
|
mean: [123.68, 116.78, 103.94]
|
|
scale: 1.0
|
|
width: 736
|
|
height: 736
|
|
rgb: false
|
|
sample: "text_detection"
|
|
|
|
OCR:
|
|
load_info:
|
|
url: "https://drive.google.com/uc?export=dowload&id=159VavnbvfBQkLIPSAu2SP5Yij1Fy4azw"
|
|
sha1: "c4ab1fb3f13c1c8ffc04f016e72ec85311de4ebe"
|
|
model: "VGG_CTC.onnx"
|
|
sample: "text_recognition"
|
|
|
|
# Edge Detection models.
|
|
################################################################################
|
|
|
|
dexined:
|
|
load_info:
|
|
url: "https://github.com/gursimarsingh/opencv_zoo/raw/dexined_model/models/edge_detection_dexined/dexined.onnx"
|
|
sha1: "f86f2d32c3cf892771f76b5e6b629b16a66510e9"
|
|
model: "dexined.onnx"
|
|
mean: [103.5, 116.2, 123.6]
|
|
scale: 1.0
|
|
width: 512
|
|
height: 512
|
|
rgb: false
|
|
sample: "edge_detection"
|