opencv/samples/dnn/models.yml

%YAML:1.0

################################################################################
# Object detection models.
################################################################################

# OpenCV's face detection network
opencv_fd:
  model: "opencv_face_detector.caffemodel"
  config: "opencv_face_detector.prototxt"
  mean: [104, 177, 123]
  scale: 1.0
  width: 300
  height: 300
  rgb: false
  sample: "object_detection"

# YOLO object detection family from Darknet (https://pjreddie.com/darknet/yolo/)
# Might be used for all YOLOv2, TinyYolov2 and YOLOv3
yolo:
  model: "yolov3.weights"
  config: "yolov3.cfg"
  mean: [0, 0, 0]
  scale: 0.00392
  width: 416
  height: 416
  rgb: true
  classes: "object_detection_classes_yolov3.txt"
  sample: "object_detection"

tiny-yolo-voc:
  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"
  sample: "object_detection"

# Caffe implementation of SSD model from https://github.com/chuanqi305/MobileNet-SSD
ssd_caffe:
  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:
  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:
  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 v1.1 from https://github.com/DeepScale/SqueezeNet
squeezenet:
  model: "squeezenet_v1.1.caffemodel"
  config: "squeezenet_v1.1.prototxt"
  mean: [0, 0, 0]
  scale: 1.0
  width: 227
  height: 227
  rgb: false
  classes: "classification_classes_ILSVRC2012.txt"
  sample: "classification"

# Googlenet from https://github.com/BVLC/caffe/tree/master/models/bvlc_googlenet
googlenet:
  model: "bvlc_googlenet.caffemodel"
  config: "bvlc_googlenet.prototxt"
  mean: [104, 117, 123]
  scale: 1.0
  width: 224
  height: 224
  rgb: false
  classes: "classification_classes_ILSVRC2012.txt"
  sample: "classification"

################################################################################
# Semantic segmentation models.
################################################################################

# ENet road scene segmentation network from https://github.com/e-lab/ENet-training
# Works fine for different input sizes.
enet:
  model: "Enet-model-best.net"
  mean: [0, 0, 0]
  scale: 0.00392
  width: 512
  height: 256
  rgb: true
  classes: "enet-classes.txt"
  sample: "segmentation"

fcn8s:
  model: "fcn8s-heavy-pascal.caffemodel"
  config: "fcn8s-heavy-pascal.prototxt"
  mean: [0, 0, 0]
  scale: 1.0
  width: 500
  height: 500
  rgb: false
  sample: "segmentation"