opencv/samples/dnn
2020-08-26 15:51:25 +00:00
..
face_detector Restore face detection train.prototxt from #9516 2020-04-27 23:07:33 +03:00
action_recognition.py Merge pull request #14627 from l-bat:demo_kinetics 2019-05-30 17:36:00 +03:00
classification.cpp Add a file with preprocessing parameters for deep learning networks 2018-09-25 18:28:37 +03:00
classification.py Add a file with preprocessing parameters for deep learning networks 2018-09-25 18:28:37 +03:00
CMakeLists.txt Merge pull request #16150 from alalek:cmake_avoid_deprecated_link_private 2019-12-13 17:52:40 +03:00
colorization.cpp samples: use findFile() in dnn 2018-11-16 18:08:22 +00:00
colorization.py Make Intel's Inference Engine backend is default if no preferable backend is specified. 2018-06-04 18:31:46 +03:00
common.hpp Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2018-10-26 17:56:55 +03:00
common.py samples: use findFile() in dnn 2018-11-16 18:08:22 +00:00
custom_layers.hpp Merge pull request #12264 from dkurt:dnn_remove_forward_method 2018-09-06 13:26:47 +03:00
dasiamrpn_tracker.py Merge pull request #18033 from ieliz:dasiamrpn 2020-08-11 11:46:47 +03:00
edge_detection.py Fix edge_detection.py sample for Python 3 2019-01-09 15:28:10 +03:00
fast_neural_style.py fix pylint warnings 2019-10-16 18:49:33 +03:00
human_parsing.cpp dnn: add a human parsing cpp sample 2020-05-31 09:50:20 +02:00
human_parsing.py Merge pull request #16472 from l-bat:cp_vton 2020-02-17 22:29:37 +03:00
js_face_recognition.html Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-07-25 19:21:47 +00:00
mask_rcnn.py Merge pull request #17394 from huningxin:fix_segmentation_py 2020-05-27 11:20:07 +03:00
mobilenet_ssd_accuracy.py fix pylint warnings 2019-10-16 18:49:33 +03:00
models.yml dnn/samples: add googlenet to model zoo 2019-01-17 12:14:35 +01:00
object_detection.cpp Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2020-05-28 23:53:54 +00:00
object_detection.py Merge pull request #17332 from l-bat:fix_nms 2020-05-25 12:34:11 +00:00
openpose.cpp Fix openpose samples 2018-12-25 14:12:44 -01:00
openpose.py FIx misc. source and comment typos 2019-08-15 13:09:52 +03:00
optical_flow.py support flownet2 with arbitary input size 2020-08-12 00:50:58 +08:00
README.md Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-04-19 15:43:58 +03:00
segmentation.cpp Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2018-10-13 16:19:05 +00:00
segmentation.py Merge pull request #17394 from huningxin:fix_segmentation_py 2020-05-27 11:20:07 +03:00
shrink_tf_graph_weights.py Text TensorFlow graphs parsing. MobileNet-SSD for 90 classes. 2017-10-08 22:25:29 +03:00
siamrpnpp.py Merge pull request #17647 from jinyup100:add-siamrpnpp 2020-08-25 20:01:16 +00:00
text_detection.cpp add OpenCV sample for digit and text recongnition, and provide multiple OCR models. 2020-08-22 01:02:13 +08:00
text_detection.py add OpenCV sample for digit and text recongnition, and provide multiple OCR models. 2020-08-22 01:02:13 +08:00
tf_text_graph_common.py dnn: EfficientDet 2020-05-28 17:23:42 +03:00
tf_text_graph_efficientdet.py dnn: EfficientDet 2020-05-28 17:23:42 +03:00
tf_text_graph_faster_rcnn.py StridedSlice from TensorFlow 2019-05-22 12:45:52 +03:00
tf_text_graph_mask_rcnn.py Enable ResNet-based Mask-RCNN models from TensorFlow Object Detection API 2019-02-06 13:05:11 +03:00
tf_text_graph_ssd.py Determine SSD input shape 2020-05-14 08:16:45 +03:00
virtual_try_on.py Fixed virtual try on sample 2020-06-04 09:41:24 +03:00

OpenCV deep learning module samples

Model Zoo

Check a wiki for a list of tested models.

If OpenCV is built with Intel's Inference Engine support you can use Intel's pre-trained models.

There are different preprocessing parameters such mean subtraction or scale factors for different models. You may check the most popular models and their parameters at models.yml configuration file. It might be also used for aliasing samples parameters. In example,

python object_detection.py opencv_fd --model /path/to/caffemodel --config /path/to/prototxt

Check -h option to know which values are used by default:

python object_detection.py opencv_fd -h

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) |

References