Open Source Computer Vision Library https://opencv.org/

History

Alexander Alekhin 332c37f332 Merge remote-tracking branch 'upstream/3.4' into merge-3.4		6 years ago
..
face_detector	Update face detection network in samples	6 years ago
CMakeLists.txt	Install data for samples to correct directories, do not download face_detector models in cmake	6 years ago
README.md	…
classification.cpp	Add a file with preprocessing parameters for deep learning networks	6 years ago
classification.py	Add a file with preprocessing parameters for deep learning networks	6 years ago
colorization.cpp	samples: use findFile() in dnn	6 years ago
colorization.py	…
common.hpp	Merge remote-tracking branch 'upstream/3.4' into merge-3.4	6 years ago
common.py	samples: use findFile() in dnn	6 years ago
custom_layers.hpp	Merge pull request #12264 from dkurt:dnn_remove_forward_method	6 years ago
edge_detection.py	Fix edge_detection.py sample for Python 3	6 years ago
fast_neural_style.py	samples: use findFile() in dnn	6 years ago
js_face_recognition.html	…
mask_rcnn.py	samples: use findFile() in dnn	6 years ago
mobilenet_ssd_accuracy.py	samples: use findFile() in dnn	6 years ago
models.yml	dnn/samples: add googlenet to model zoo	6 years ago
object_detection.cpp	Update obj. detect sample	6 years ago
object_detection.py	Update obj. detect sample	6 years ago
openpose.cpp	Fix openpose samples	6 years ago
openpose.py	Fix openpose samples	6 years ago
segmentation.cpp	Merge remote-tracking branch 'upstream/3.4' into merge-3.4	6 years ago
segmentation.py	Add a file with preprocessing parameters for deep learning networks	6 years ago
shrink_tf_graph_weights.py	…
text_detection.cpp	core: repair CV_Assert() messages	6 years ago
text_detection.py	Merge pull request #13432 from vishwesh5:patch-1	6 years ago
tf_text_graph_common.py	fix tf_text_graph_common tensor_content type bug	6 years ago
tf_text_graph_faster_rcnn.py	Create text graphs for Faster-RCNN from TensorFlow with dilated convolutions	6 years ago
tf_text_graph_mask_rcnn.py	Enable ResNet-based Mask-RCNN models from TensorFlow Object Detection API	6 years ago
tf_text_graph_ssd.py	Fix priors boxes generation in case of non square inputs for TensorFlow SSDs	6 years ago

README.md

OpenCV deep learning module samples

Model Zoo

Object detection

Model	Scale	Size WxH	Mean subtraction	Channels order
MobileNet-SSD, Caffe	`0.00784 (2/255)`	`300x300`	`127.5 127.5 127.5`	BGR
OpenCV face detector	`1.0`	`300x300`	`104 177 123`	BGR
SSDs from TensorFlow	`0.00784 (2/255)`	`300x300`	`127.5 127.5 127.5`	RGB
YOLO	`0.00392 (1/255)`	`416x416`	`0 0 0`	RGB
VGG16-SSD	`1.0`	`300x300`	`104 117 123`	BGR
Faster-RCNN	`1.0`	`800x600`	`102.9801 115.9465 122.7717`	BGR
R-FCN	`1.0`	`800x600`	`102.9801 115.9465 122.7717`	BGR
Faster-RCNN, ResNet backbone	`1.0`	`300x300`	`103.939 116.779 123.68`	RGB
Faster-RCNN, InceptionV2 backbone	`0.00784 (2/255)`	`300x300`	`127.5 127.5 127.5`	RGB

Face detection

An origin model with single precision floating point weights has been quantized using TensorFlow framework. To achieve the best accuracy run the model on BGR images resized to 300x300 applying mean subtraction of values (104, 177, 123) for each blue, green and red channels correspondingly.

The following are accuracy metrics obtained using COCO object detection evaluation tool on FDDB dataset (see script) applying resize to 300x300 and keeping an origin images' sizes.

AP - Average Precision                            | FP32/FP16 | UINT8          | FP32/FP16 | UINT8          |
AR - Average Recall                               | 300x300   | 300x300        | any size  | any size       |
--------------------------------------------------|-----------|----------------|-----------|----------------|
AP @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] | 0.408     | 0.408          | 0.378     | 0.328 (-0.050) |
AP @[ IoU=0.50      | area=   all | maxDets=100 ] | 0.849     | 0.849          | 0.797     | 0.790 (-0.007) |
AP @[ IoU=0.75      | area=   all | maxDets=100 ] | 0.251     | 0.251          | 0.208     | 0.140 (-0.068) |
AP @[ IoU=0.50:0.95 | area= small | maxDets=100 ] | 0.050     | 0.051 (+0.001) | 0.107     | 0.070 (-0.037) |
AP @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] | 0.381     | 0.379 (-0.002) | 0.380     | 0.368 (-0.012) |
AP @[ IoU=0.50:0.95 | area= large | maxDets=100 ] | 0.455     | 0.455          | 0.412     | 0.337 (-0.075) |
AR @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] | 0.299     | 0.299          | 0.279     | 0.246 (-0.033) |
AR @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] | 0.482     | 0.482          | 0.476     | 0.436 (-0.040) |
AR @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] | 0.496     | 0.496          | 0.491     | 0.451 (-0.040) |
AR @[ IoU=0.50:0.95 | area= small | maxDets=100 ] | 0.189     | 0.193 (+0.004) | 0.284     | 0.232 (-0.052) |
AR @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] | 0.481     | 0.480 (-0.001) | 0.470     | 0.458 (-0.012) |
AR @[ IoU=0.50:0.95 | area= large | maxDets=100 ] | 0.528     | 0.528          | 0.520     | 0.462 (-0.058) |

Classification

Model	Scale	Size WxH	Mean subtraction	Channels order
GoogLeNet	`1.0`	`224x224`	`104 117 123`	BGR
SqueezeNet	`1.0`	`227x227`	`0 0 0`	BGR

Semantic segmentation

Model	Scale	Size WxH	Mean subtraction	Channels order
ENet	`0.00392 (1/255)`	`1024x512`	`0 0 0`	RGB
FCN8s	`1.0`	`500x500`	`0 0 0`	BGR