Merge pull request #10983 from dkurt:dnn_face_detection_uint8

7 years ago · 7bc980edaf
parent 8c1d8eccdd 8d8f3bca6f
commit 7bc980edaf
5 changed files with 2350 additions and 23 deletions
--- a/modules/dnn/misc/face_detector_accuracy.py
+++ b/modules/dnn/misc/face_detector_accuracy.py
@ -17,7 +17,6 @@ parser = argparse.ArgumentParser(
                    'using COCO evaluation tool, http://cocodataset.org/#detections-eval')
 parser.add_argument('--proto', help='Path to .prototxt of Caffe model or .pbtxt of TensorFlow graph')
 parser.add_argument('--model', help='Path to .caffemodel trained in Caffe or .pb from TensorFlow')
-parser.add_argument('--caffe', help='Indicate that tested model is from Caffe. Otherwise model from TensorFlow is expected.', action='store_true')
 parser.add_argument('--cascade', help='Optional path to trained Haar cascade as '
                                      'an additional model for evaluation')
 parser.add_argument('--ann', help='Path to text file with ground truth annotations')
@ -141,10 +140,7 @@ with open('annotations.json', 'wt') as f:
 ### Obtain detections ##########################################################
 detections = []
 if args.proto and args.model:
-    if args.caffe:
-        net = cv.dnn.readNetFromCaffe(args.proto, args.model)
-    else:
-        net = cv.dnn.readNetFromTensorflow(args.model, args.proto)
+    net = cv.dnn.readNet(args.proto, args.model)

    def detect(img, imageId):
        imgWidth = img.shape[1]
--- a/samples/dnn/CMakeLists.txt
+++ b/samples/dnn/CMakeLists.txt
@ -13,23 +13,32 @@ if(NOT BUILD_EXAMPLES OR NOT OCV_DEPENDENCIES_FOUND)
  return()
 endif()

-# Model branch name: dnn_samples_face_detector_20170830
-set(DNN_FACE_DETECTOR_MODEL_COMMIT "b2bfc75f6aea5b1f834ff0f0b865a7c18ff1459f")
-set(DNN_FACE_DETECTOR_MODEL_HASH "afbb6037fd180e8d2acb3b58ca737b9e")
-set(DNN_FACE_DETECTOR_MODEL_NAME "res10_300x300_ssd_iter_140000.caffemodel")
-set(DNN_FACE_DETECTOR_MODEL_DOWNLOAD_DIR "${CMAKE_CURRENT_LIST_DIR}/face_detector")
-if(COMMAND ocv_download)
-  ocv_download(FILENAME ${DNN_FACE_DETECTOR_MODEL_NAME}
-             HASH ${DNN_FACE_DETECTOR_MODEL_HASH}
-             URL
-               "$ENV{OPENCV_DNN_MODELS_URL}"
-               "${OPENCV_DNN_MODELS_URL}"
-               "https://raw.githubusercontent.com/opencv/opencv_3rdparty/${DNN_FACE_DETECTOR_MODEL_COMMIT}/"
-             DESTINATION_DIR ${DNN_FACE_DETECTOR_MODEL_DOWNLOAD_DIR}
-             ID DNN_FACE_DETECTOR
-             RELATIVE_URL
-             STATUS res)
-endif()
+function(download_net name commit hash)
+  set(DNN_FACE_DETECTOR_MODEL_DOWNLOAD_DIR "${CMAKE_CURRENT_LIST_DIR}/face_detector")
+  if(COMMAND ocv_download)
+    ocv_download(FILENAME ${name}
+               HASH ${hash}
+               URL
+                 "$ENV{OPENCV_DNN_MODELS_URL}"
+                 "${OPENCV_DNN_MODELS_URL}"
+                 "https://raw.githubusercontent.com/opencv/opencv_3rdparty/${commit}/"
+               DESTINATION_DIR ${DNN_FACE_DETECTOR_MODEL_DOWNLOAD_DIR}
+               ID DNN_FACE_DETECTOR
+               RELATIVE_URL
+               STATUS res)
+  endif()
+endfunction()
+
+# Model branch name: dnn_samples_face_detector_20180205_fp16
+download_net("res10_300x300_ssd_iter_140000_fp16.caffemodel"
+             "19512576c112aa2c7b6328cb0e8d589a4a90a26d"
+             "f737f886e33835410c69e3ccfe0720a1")
+
+# Model branch name: dnn_samples_face_detector_20180220_uint8
+download_net("opencv_face_detector_uint8.pb"
+             "7b425df276ba2161b8edaab0f0756f4a735d61b9"
+             "56acf81f55d9b9e96c3347bc65409b9e")
+
 project(dnn_samples)
 ocv_include_modules_recurse(${OPENCV_DNN_SAMPLES_REQUIRED_DEPS})
 file(GLOB_RECURSE dnn_samples RELATIVE ${CMAKE_CURRENT_SOURCE_DIR} *.cpp)
--- a/samples/dnn/README.md
+++ b/samples/dnn/README.md
@ -14,6 +14,34 @@
 | [Faster-RCNN](https://github.com/rbgirshick/py-faster-rcnn) | `1.0` | `800x600` | `102.9801, 115.9465, 122.7717` | BGR |
 | [R-FCN](https://github.com/YuwenXiong/py-R-FCN) | `1.0` | `800x600` | `102.9801 115.9465 122.7717` | BGR |

+#### Face detection
+[An origin model](https://github.com/opencv/opencv/tree/master/samples/dnn/face_detector)
+with single precision floating point weights has been quantized using [TensorFlow framework](https://www.tensorflow.org/).
+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](http://cocodataset.org/#detections-eval) on [FDDB dataset](http://vis-www.cs.umass.edu/fddb/)
+(see [script](https://github.com/opencv/opencv/blob/master/modules/dnn/misc/face_detector_accuracy.py))
+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 |
 |---------------|-------|-----------|--------------------|-------|
--- a/samples/dnn/face_detector/opencv_face_detector.pbtxt
+++ b/samples/dnn/face_detector/opencv_face_detector.pbtxt
--- a/samples/dnn/js_face_recognition.html
+++ b/samples/dnn/js_face_recognition.html
@ -70,7 +70,7 @@ function recognize(face) {
 function loadModels(callback) {
  var utils = new Utils('');
  var proto = 'https://raw.githubusercontent.com/opencv/opencv/master/samples/dnn/face_detector/deploy.prototxt';
-  var weights = 'https://github.com/opencv/opencv_3rdparty/raw/19512576c112aa2c7b6328cb0e8d589a4a90a26d/res10_300x300_ssd_iter_140000_fp16.caffemodel';
+  var weights = 'https://raw.githubusercontent.com/opencv/opencv_3rdparty/dnn_samples_face_detector_20180205_fp16/res10_300x300_ssd_iter_140000_fp16.caffemodel';
  var recognModel = 'https://raw.githubusercontent.com/pyannote/pyannote-data/master/openface.nn4.small2.v1.t7';
  utils.createFileFromUrl('face_detector.prototxt', proto, () => {
    document.getElementById('status').innerHTML = 'Downloading face_detector.caffemodel';