Administrator/opencv-MIRROR
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-09-15 07:29:07 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/3.4' into merge-3.4

Browse Source
This commit is contained in:
Alexander Alekhin
2018-08-07 20:09:27 +03:00
parent 053259fd92 9f2edc1135
commit 4eb2966559
80 changed files with 1272 additions and 822 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
samples/CMakeLists.txt
View File

@@ -70,9 +70,7 @@ endif()
ocv_install_example_src("." CMakeLists.txt)
if(INSTALL_C_EXAMPLES)
install(DIRECTORY data
DESTINATION "${OPENCV_SAMPLES_SRC_INSTALL_PATH}/data"
COMPONENT samples_data)
install(DIRECTORY data DESTINATION "${OPENCV_SAMPLES_SRC_INSTALL_PATH}" COMPONENT samples_data)
endif()
else()

5
samples/cpp/stitching_detailed.cpp
View File

@@ -82,7 +82,7 @@ static void printUsage()
"\nMotion Estimation Flags:\n"
" --work_megapix <float>\n"
" Resolution for image registration step. The default is 0.6 Mpx.\n"
" --features (surf|orb)\n"
" --features (surf|orb|sift)\n"
" Type of features used for images matching. The default is surf.\n"
" --matcher (homography|affine)\n"
" Matcher used for pairwise image matching.\n"
@@ -430,6 +430,9 @@ int main(int argc, char* argv[])
{
finder = makePtr<OrbFeaturesFinder>();
}
else if (features_type == "sift") {
finder = makePtr<SiftFeaturesFinder>();
}
else
{
cout << "Unknown 2D features type: '" << features_type << "'.\n";

2
samples/cpp/train_HOG.cpp
View File

@@ -204,7 +204,7 @@ int main( int argc, char** argv )
const char* keys =
{
"{help h| | show help message}"
"{pd | | path of directory contains possitive images}"
"{pd | | path of directory contains positive images}"
"{nd | | path of directory contains negative images}"
"{td | | path of directory contains test images}"
"{tv | | test video file name}"

2
samples/cpp/tutorial_code/ml/introduction_to_pca/introduction_to_pca.cpp
View File

@@ -1,6 +1,6 @@
/**
* @file introduction_to_pca.cpp
* @brief This program demonstrates how to use OpenCV PCA to extract the orienation of an object
* @brief This program demonstrates how to use OpenCV PCA to extract the orientation of an object
* @author OpenCV team
*/

2
samples/cpp/warpPerspective_demo.cpp
View File

@@ -26,7 +26,7 @@ static void help(char** argv)
"\tESC, q - quit the program\n"
"\tr - change order of points to rotate transformation\n"
"\tc - delete selected points\n"
"\ti - change order of points to invers transformation \n"
"\ti - change order of points to inverse transformation \n"
"\nUse your mouse to select a point and move it to see transformation changes" << endl;
}

26
samples/dnn/CMakeLists.txt
View File

@@ -13,32 +13,6 @@ if(NOT BUILD_EXAMPLES OR NOT OCV_DEPENDENCIES_FOUND)
return()
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)

2
samples/dnn/custom_layers.hpp
View File

@@ -198,7 +198,7 @@ private:
//! [ResizeBilinearLayer]
//
// The folowing code is used only to generate tutorials documentation.
// The following code is used only to generate tutorials documentation.
//
//! [A custom layer interface]

74
samples/dnn/face_detector/download_weights.py Executable file
View File

@@ -0,0 +1,74 @@
#!/usr/bin/env python
from __future__ import print_function
import hashlib
import time
import sys
import xml.etree.ElementTree as ET
if sys.version_info[0] < 3:
from urllib2 import urlopen
else:
from urllib.request import urlopen
class HashMismatchException(Exception):
def __init__(self, expected, actual):
Exception.__init__(self)
self.expected = expected
self.actual = actual
def __str__(self):
return 'Hash mismatch: {} vs {}'.format(self.expected, self.actual)
class MetalinkDownloader(object):
BUFSIZE = 10*1024*1024
NS = {'ml': 'urn:ietf:params:xml:ns:metalink'}
tick = 0
def download(self, metalink_file):
status = True
for file_elem in ET.parse(metalink_file).getroot().findall('ml:file', self.NS):
url = file_elem.find('ml:url', self.NS).text
fname = file_elem.attrib['name']
hash_sum = file_elem.find('ml:hash', self.NS).text
print('*** {}'.format(fname))
try:
self.verify(hash_sum, fname)
except Exception as ex:
print(' {}'.format(ex))
try:
print(' {}'.format(url))
with open(fname, 'wb') as file_stream:
self.buffered_read(urlopen(url), file_stream.write)
self.verify(hash_sum, fname)
except Exception as ex:
print(' {}'.format(ex))
print(' FAILURE')
status = False
continue
print(' SUCCESS')
return status
def print_progress(self, msg, timeout = 0):
if time.time() - self.tick > timeout:
print(msg, end='')
sys.stdout.flush()
self.tick = time.time()
def buffered_read(self, in_stream, processing):
self.print_progress(' >')
while True:
buf = in_stream.read(self.BUFSIZE)
if not buf:
break
processing(buf)
self.print_progress('>', 5)
print(' done')
def verify(self, hash_sum, fname):
sha = hashlib.sha1()
with open(fname, 'rb') as file_stream:
self.buffered_read(file_stream, sha.update)
if hash_sum != sha.hexdigest():
raise HashMismatchException(hash_sum, sha.hexdigest())
if __name__ == '__main__':
sys.exit(0 if MetalinkDownloader().download('weights.meta4') else 1)

13
samples/dnn/face_detector/weights.meta4 Normal file
View File

@@ -0,0 +1,13 @@
<?xml version="1.0" encoding="UTF-8"?>
<metalink xmlns="urn:ietf:params:xml:ns:metalink">
<file name="res10_300x300_ssd_iter_140000_fp16.caffemodel">
<identity>OpenCV face detector FP16 weights</identity>
<hash type="sha-1">31fc22bfdd907567a04bb45b7cfad29966caddc1</hash>
<url>https://raw.githubusercontent.com/opencv/opencv_3rdparty/dnn_samples_face_detector_20180205_fp16/res10_300x300_ssd_iter_140000_fp16.caffemodel</url>
</file>
<file name="opencv_face_detector_uint8.pb">
<identity>OpenCV face detector UINT8 weights</identity>
<hash type="sha-1">4f2fdf6f231d759d7bbdb94353c5a68690f3d2ae</hash>
<url>https://raw.githubusercontent.com/opencv/opencv_3rdparty/dnn_samples_face_detector_20180220_uint8/opencv_face_detector_uint8.pb</url>
</file>
</metalink>

25
samples/dnn/tf_text_graph_common.py Normal file
View File

@@ -0,0 +1,25 @@
import tensorflow as tf
from tensorflow.core.framework.node_def_pb2 import NodeDef
from google.protobuf import text_format
def tensorMsg(values):
if all([isinstance(v, float) for v in values]):
dtype = 'DT_FLOAT'
field = 'float_val'
elif all([isinstance(v, int) for v in values]):
dtype = 'DT_INT32'
field = 'int_val'
else:
raise Exception('Wrong values types')
msg = 'tensor { dtype: ' + dtype + ' tensor_shape { dim { size: %d } }' % len(values)
for value in values:
msg += '%s: %s ' % (field, str(value))
return msg + '}'
def addConstNode(name, values, graph_def):
node = NodeDef()
node.name = name
node.op = 'Const'
text_format.Merge(tensorMsg(values), node.attr["value"])
graph_def.node.extend([node])

72
samples/dnn/tf_text_graph_faster_rcnn.py
View File

@@ -6,6 +6,8 @@ from tensorflow.core.framework.node_def_pb2 import NodeDef
from tensorflow.tools.graph_transforms import TransformGraph
from google.protobuf import text_format
from tf_text_graph_common import tensorMsg, addConstNode
parser = argparse.ArgumentParser(description='Run this script to get a text graph of '
'SSD model from TensorFlow Object Detection API. '
'Then pass it with .pb file to cv::dnn::readNetFromTensorflow function.')
@@ -93,21 +95,6 @@ while True:
if node.op == 'CropAndResize':
break
def tensorMsg(values):
if all([isinstance(v, float) for v in values]):
dtype = 'DT_FLOAT'
field = 'float_val'
elif all([isinstance(v, int) for v in values]):
dtype = 'DT_INT32'
field = 'int_val'
else:
raise Exception('Wrong values types')
msg = 'tensor { dtype: ' + dtype + ' tensor_shape { dim { size: %d } }' % len(values)
for value in values:
msg += '%s: %s ' % (field, str(value))
return msg + '}'
def addSlice(inp, out, begins, sizes):
beginsNode = NodeDef()
beginsNode.name = out + '/begins'
@@ -151,17 +138,25 @@ def addSoftMax(inp, out):
softmax.input.append(inp)
graph_def.node.extend([softmax])
def addFlatten(inp, out):
flatten = NodeDef()
flatten.name = out
flatten.op = 'Flatten'
flatten.input.append(inp)
graph_def.node.extend([flatten])
addReshape('FirstStageBoxPredictor/ClassPredictor/BiasAdd',
'FirstStageBoxPredictor/ClassPredictor/reshape_1', [0, -1, 2])
addSoftMax('FirstStageBoxPredictor/ClassPredictor/reshape_1',
'FirstStageBoxPredictor/ClassPredictor/softmax') # Compare with Reshape_4
flatten = NodeDef()
flatten.name = 'FirstStageBoxPredictor/BoxEncodingPredictor/flatten' # Compare with FirstStageBoxPredictor/BoxEncodingPredictor/BiasAdd
flatten.op = 'Flatten'
flatten.input.append('FirstStageBoxPredictor/BoxEncodingPredictor/BiasAdd')
graph_def.node.extend([flatten])
addFlatten('FirstStageBoxPredictor/ClassPredictor/softmax',
'FirstStageBoxPredictor/ClassPredictor/softmax/flatten')
# Compare with FirstStageBoxPredictor/BoxEncodingPredictor/BiasAdd
addFlatten('FirstStageBoxPredictor/BoxEncodingPredictor/BiasAdd',
'FirstStageBoxPredictor/BoxEncodingPredictor/flatten')
proposals = NodeDef()
proposals.name = 'proposals' # Compare with ClipToWindow/Gather/Gather (NOTE: normalized)
@@ -194,7 +189,7 @@ detectionOut.name = 'detection_out'
detectionOut.op = 'DetectionOutput'
detectionOut.input.append('FirstStageBoxPredictor/BoxEncodingPredictor/flatten')
detectionOut.input.append('FirstStageBoxPredictor/ClassPredictor/softmax')
detectionOut.input.append('FirstStageBoxPredictor/ClassPredictor/softmax/flatten')
detectionOut.input.append('proposals')
text_format.Merge('i: 2', detectionOut.attr['num_classes'])
@@ -204,11 +199,21 @@ text_format.Merge('f: 0.7', detectionOut.attr['nms_threshold'])
text_format.Merge('i: 6000', detectionOut.attr['top_k'])
text_format.Merge('s: "CENTER_SIZE"', detectionOut.attr['code_type'])
text_format.Merge('i: 100', detectionOut.attr['keep_top_k'])
text_format.Merge('b: true', detectionOut.attr['clip'])
text_format.Merge('b: true', detectionOut.attr['loc_pred_transposed'])
text_format.Merge('b: false', detectionOut.attr['clip'])
graph_def.node.extend([detectionOut])
addConstNode('clip_by_value/lower', [0.0], graph_def)
addConstNode('clip_by_value/upper', [1.0], graph_def)
clipByValueNode = NodeDef()
clipByValueNode.name = 'detection_out/clip_by_value'
clipByValueNode.op = 'ClipByValue'
clipByValueNode.input.append('detection_out')
clipByValueNode.input.append('clip_by_value/lower')
clipByValueNode.input.append('clip_by_value/upper')
graph_def.node.extend([clipByValueNode])
# Save as text.
for node in reversed(topNodes):
graph_def.node.extend([node])
@@ -225,17 +230,13 @@ addReshape('SecondStageBoxPredictor/Reshape_1/slice',
# Replace Flatten subgraph onto a single node.
for i in reversed(range(len(graph_def.node))):
if graph_def.node[i].op == 'CropAndResize':
graph_def.node[i].input.insert(1, 'detection_out')
graph_def.node[i].input.insert(1, 'detection_out/clip_by_value')
if graph_def.node[i].name == 'SecondStageBoxPredictor/Reshape':
shapeNode = NodeDef()
shapeNode.name = 'SecondStageBoxPredictor/Reshape/shape2'
shapeNode.op = 'Const'
text_format.Merge(tensorMsg([1, -1, 4]), shapeNode.attr["value"])
graph_def.node.extend([shapeNode])
addConstNode('SecondStageBoxPredictor/Reshape/shape2', [1, -1, 4], graph_def)
graph_def.node[i].input.pop()
graph_def.node[i].input.append(shapeNode.name)
graph_def.node[i].input.append('SecondStageBoxPredictor/Reshape/shape2')
if graph_def.node[i].name in ['SecondStageBoxPredictor/Flatten/flatten/Shape',
'SecondStageBoxPredictor/Flatten/flatten/strided_slice',
@@ -246,12 +247,15 @@ for node in graph_def.node:
if node.name == 'SecondStageBoxPredictor/Flatten/flatten/Reshape':
node.op = 'Flatten'
node.input.pop()
break
if node.name in ['FirstStageBoxPredictor/BoxEncodingPredictor/Conv2D',
'SecondStageBoxPredictor/BoxEncodingPredictor/MatMul']:
text_format.Merge('b: true', node.attr["loc_pred_transposed"])
################################################################################
### Postprocessing
################################################################################
addSlice('detection_out', 'detection_out/slice', [0, 0, 0, 3], [-1, -1, -1, 4])
addSlice('detection_out/clip_by_value', 'detection_out/slice', [0, 0, 0, 3], [-1, -1, -1, 4])
variance = NodeDef()
variance.name = 'proposals/variance'
@@ -268,12 +272,13 @@ text_format.Merge('i: 2', varianceEncoder.attr["axis"])
graph_def.node.extend([varianceEncoder])
addReshape('detection_out/slice', 'detection_out/slice/reshape', [1, 1, -1])
addFlatten('variance_encoded', 'variance_encoded/flatten')
detectionOut = NodeDef()
detectionOut.name = 'detection_out_final'
detectionOut.op = 'DetectionOutput'
detectionOut.input.append('variance_encoded')
detectionOut.input.append('variance_encoded/flatten')
detectionOut.input.append('SecondStageBoxPredictor/Reshape_1/Reshape')
detectionOut.input.append('detection_out/slice/reshape')
@@ -283,7 +288,6 @@ text_format.Merge('i: %d' % (args.num_classes + 1), detectionOut.attr['backgroun
text_format.Merge('f: 0.6', detectionOut.attr['nms_threshold'])
text_format.Merge('s: "CENTER_SIZE"', detectionOut.attr['code_type'])
text_format.Merge('i: 100', detectionOut.attr['keep_top_k'])
text_format.Merge('b: true', detectionOut.attr['loc_pred_transposed'])
text_format.Merge('b: true', detectionOut.attr['clip'])
text_format.Merge('b: true', detectionOut.attr['variance_encoded_in_target'])
graph_def.node.extend([detectionOut])

57
samples/dnn/tf_text_graph_ssd.py
View File

@@ -15,6 +15,7 @@ from math import sqrt
from tensorflow.core.framework.node_def_pb2 import NodeDef
from tensorflow.tools.graph_transforms import TransformGraph
from google.protobuf import text_format
from tf_text_graph_common import tensorMsg, addConstNode
parser = argparse.ArgumentParser(description='Run this script to get a text graph of '
'SSD model from TensorFlow Object Detection API. '
@@ -29,6 +30,11 @@ parser.add_argument('--aspect_ratios', default=[1.0, 2.0, 0.5, 3.0, 0.333], type
help='Hyper-parameter of ssd_anchor_generator from config file.')
parser.add_argument('--image_width', default=300, type=int, help='Training images width.')
parser.add_argument('--image_height', default=300, type=int, help='Training images height.')
parser.add_argument('--not_reduce_boxes_in_lowest_layer', default=False, action='store_true',
help='A boolean to indicate whether the fixed 3 boxes per '
'location is used in the lowest achors generation layer.')
parser.add_argument('--box_predictor', default='convolutional', type=str,
choices=['convolutional', 'weight_shared_convolutional'])
args = parser.parse_args()
# Nodes that should be kept.
@@ -160,28 +166,6 @@ graph_def.node[1].input.append(weights)
# Create SSD postprocessing head ###############################################
# Concatenate predictions of classes, predictions of bounding boxes and proposals.
def tensorMsg(values):
if all([isinstance(v, float) for v in values]):
dtype = 'DT_FLOAT'
field = 'float_val'
elif all([isinstance(v, int) for v in values]):
dtype = 'DT_INT32'
field = 'int_val'
else:
raise Exception('Wrong values types')
msg = 'tensor { dtype: ' + dtype + ' tensor_shape { dim { size: %d } }' % len(values)
for value in values:
msg += '%s: %s ' % (field, str(value))
return msg + '}'
def addConstNode(name, values):
node = NodeDef()
node.name = name
node.op = 'Const'
text_format.Merge(tensorMsg(values), node.attr["value"])
graph_def.node.extend([node])
def addConcatNode(name, inputs, axisNodeName):
concat = NodeDef()
concat.name = name
@@ -194,12 +178,18 @@ def addConcatNode(name, inputs, axisNodeName):
addConstNode('concat/axis_flatten', [-1])
addConstNode('PriorBox/concat/axis', [-2])
for label in ['ClassPredictor', 'BoxEncodingPredictor']:
for label in ['ClassPredictor', 'BoxEncodingPredictor' if args.box_predictor is 'convolutional' else 'BoxPredictor']:
concatInputs = []
for i in range(args.num_layers):
# Flatten predictions
flatten = NodeDef()
inpName = 'BoxPredictor_%d/%s/BiasAdd' % (i, label)
if args.box_predictor is 'convolutional':
inpName = 'BoxPredictor_%d/%s/BiasAdd' % (i, label)
else:
if i == 0:
inpName = 'WeightSharedConvolutionalBoxPredictor/%s/BiasAdd' % label
else:
inpName = 'WeightSharedConvolutionalBoxPredictor_%d/%s/BiasAdd' % (i, label)
flatten.input.append(inpName)
flatten.name = inpName + '/Flatten'
flatten.op = 'Flatten'
@@ -210,7 +200,9 @@ for label in ['ClassPredictor', 'BoxEncodingPredictor']:
idx = 0
for node in graph_def.node:
if node.name == ('BoxPredictor_%d/BoxEncodingPredictor/Conv2D' % idx):
if node.name == ('BoxPredictor_%d/BoxEncodingPredictor/Conv2D' % idx) or \
node.name == ('WeightSharedConvolutionalBoxPredictor_%d/BoxPredictor/Conv2D' % idx) or \
node.name == 'WeightSharedConvolutionalBoxPredictor/BoxPredictor/Conv2D':
text_format.Merge('b: true', node.attr["loc_pred_transposed"])
idx += 1
assert(idx == args.num_layers)
@@ -224,13 +216,19 @@ for i in range(args.num_layers):
priorBox = NodeDef()
priorBox.name = 'PriorBox_%d' % i
priorBox.op = 'PriorBox'
priorBox.input.append('BoxPredictor_%d/BoxEncodingPredictor/BiasAdd' % i)
if args.box_predictor is 'convolutional':
priorBox.input.append('BoxPredictor_%d/BoxEncodingPredictor/BiasAdd' % i)
else:
if i == 0:
priorBox.input.append('WeightSharedConvolutionalBoxPredictor/BoxPredictor/Conv2D')
else:
priorBox.input.append('WeightSharedConvolutionalBoxPredictor_%d/BoxPredictor/BiasAdd' % i)
priorBox.input.append(graph_def.node[0].name) # image_tensor
text_format.Merge('b: false', priorBox.attr["flip"])
text_format.Merge('b: false', priorBox.attr["clip"])
if i == 0:
if i == 0 and not args.not_reduce_boxes_in_lowest_layer:
widths = [0.1, args.min_scale * sqrt(2.0), args.min_scale * sqrt(0.5)]
heights = [0.1, args.min_scale / sqrt(2.0), args.min_scale / sqrt(0.5)]
else:
@@ -261,7 +259,10 @@ detectionOut = NodeDef()
detectionOut.name = 'detection_out'
detectionOut.op = 'DetectionOutput'
detectionOut.input.append('BoxEncodingPredictor/concat')
if args.box_predictor == 'convolutional':
detectionOut.input.append('BoxEncodingPredictor/concat')
else:
detectionOut.input.append('BoxPredictor/concat')
detectionOut.input.append(sigmoid.name)
detectionOut.input.append('PriorBox/concat')

2
samples/winrt/OcvImageProcessing/OcvImageProcessing/Common/StandardStyles.xaml
View File

@@ -1091,7 +1091,7 @@ Style x:Key="SkipBackAppBarButtonStyle" TargetType="ButtonBase" BasedOn="{Static
</Style>
<Style x:Key="PermissionsAppBarButtonStyle" TargetType="ButtonBase" BasedOn="{StaticResource AppBarButtonStyle}">
<Setter Property="AutomationProperties.AutomationId" Value="PermissionsAppBarButton"/>
<Setter Property="AutomationProperties.Name" Value="Permisions"/>
<Setter Property="AutomationProperties.Name" Value="Permissions"/>
<Setter Property="Content" Value="&#xE192;"/>
</Style>
<Style x:Key="HighlightAppBarButtonStyle" TargetType="ButtonBase" BasedOn="{StaticResource AppBarButtonStyle}">