def train_dlib_detector(self):
# Now let's do the training. The train_simple_object_detector() function has a
# bunch of options, all of which come with reasonable default values. The next
# few lines goes over some of these options.
options = dlib.simple_object_detector_training_options()
# Since faces are left/right symmetric we can tell the trainer to train a
# symmetric detector. This helps it get the most value out of the training
# data.
options.add_left_right_image_flips = True
# The trainer is a kind of support vector machine and therefore has the usual
# SVM C parameter. In general, a bigger C encourages it to fit the training
# data better but might lead to overfitting. You must find the best C value
# empirically by checking how well the trained detector works on a test set of
# images you haven't trained on. Don't just leave the value set at 5. Try a
# few different C values and see what works best for your data.
options.C = 5
# Tell the code how many CPU cores your computer has for the fastest training.
options.num_threads = 4
options.be_verbose = True
options.detection_window_size = 60 * 80
options.upsample_limit = 2
# This function does the actual training. It will save the final detector to
# detector.svm. The input is an XML file that lists the images in the training
# dataset and also contains the positions of the face boxes. To create your
# own XML files you can use the imglab tool which can be found in the
# tools/imglab folder. It is a simple graphical tool for labeling objects in
# images with boxes. To see how to use it read the tools/imglab/README.txt
# file. But for this example, we just use the training.xml file included with
# dlib.
dlib.train_simple_object_detector("../data/training/training_mtb.xml", "../data/models/detector_mtb.svm", options)
options.detection_window_size = 40 * 80
dlib.train_simple_object_detector("../data/training/training_ped.xml", "../data/models/detector_ped.svm", options)
def train(self):
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = True
options.C = 5
dlib.train_simple_object_detector('../resources/model.xml',
'../resources/model.svm', options)
def train(request):
import os
import sys
import glob
import dlib
from skimage import io
# Now let's do the training. The train_simple_object_detector() function has a
# bunch of options, all of which come with reasonable default values. The next
# few lines goes over some of these options.
options = dlib.simple_object_detector_training_options()
# Since faces are left/right symmetric we can tell the trainer to train a
# symmetric detector. This helps it get the most value out of the training
# data.
options.add_left_right_image_flips = True
# The trainer is a kind of support vector machine and therefore has the usual
# SVM C parameter. In general, a bigger C encourages it to fit the training
# data better but might lead to overfitting. You must find the best C value
# empirically by checking how well the trained detector works on a test set of
# images you haven't trained on. Don't just leave the value set at 5. Try a
# few different C values and see what works best for your data.
options.C = 3
# Tell the code how many CPU cores your computer has for the fastest training.
options.num_threads = multiprocessing.cpu_count()
options.be_verbose = True
training_xml_path = os.path.join(settings.BASE_DIR, "training.xml")
dlib.train_simple_object_detector(training_xml_path, "detector.svm", options)
return HttpResponse('{"status": "completed"}', content_type="application/json")
def train(self):
print("start training:")
# 注：必须要将unicode转成普通字符串，否则dlib无法读取，这个编码上的bug也是坑了我两个小时
train_xml_path = str(self.train_xml_path)
model_path = str(self.model_path)
# print(train_xml_path)
# print(model_path)
# print(chardet.detect(train_xml_path))
# xml = 'F:\\Python\\Programs\\my_dlib_face_detection_application\\images\\test_object_detector\\cats_train\\cat.xml'
# model = 'F:\\Python\\Programs\\my_dlib_face_detection_application\\images\\test_object_detector\\cats_train\\detector.svm'
# print(xml)
# print(model)
# print(chardet.detect(xml))
dlib.train_simple_object_detector(train_xml_path, model_path, self.options)
print("Training accuracy: {}".format(dlib.test_simple_object_detector(train_xml_path, model_path)))
print("The SVM model is saved in {0}".format(model_path))
if self.log:
self.log.append(u'--'*30)
self.log.append("Training complete!")
self.log.append("Training accuracy: {}".format(dlib.test_simple_object_detector(train_xml_path, model_path)))
self.log.append("The SVM model is saved in {0}".format(model_path))
self.log.append(u'--'*30)
def train_dlib_detector(self):
# Now let's do the training. The train_simple_object_detector() function has a
# bunch of options, all of which come with reasonable default values. The next
# few lines goes over some of these options.
options = dlib.simple_object_detector_training_options()
# Since faces are left/right symmetric we can tell the trainer to train a
# symmetric detector. This helps it get the most value out of the training
# data.
#options.add_left_right_image_flips = True # seems to degrade performance in this case
# The trainer is a kind of support vector machine and therefore has the usual
# SVM C parameter. In general, a bigger C encourages it to fit the training
# data better but might lead to overfitting. You must find the best C value
# empirically by checking how well the trained detector works on a test set of
# images you haven't trained on. Don't just leave the value set at 5. Try a
# few different C values and see what works best for your data.
options.C = 9
# Tell the code how many CPU cores your computer has for the fastest training.
options.num_threads = 4
options.be_verbose = True
options.upsample_limit = 2
# This function does the actual training. It will save the final detector to
# detector.svm. The input is an XML file that lists the images in the training
# dataset and also contains the positions of the face boxes. To create your
# own XML files you can use the imglab tool which can be found in the
# tools/imglab folder. It is a simple graphical tool for labeling objects in
# images with boxes. To see how to use it read the tools/imglab/README.txt
# file. But for this example, we just use the training.xml file included with
# dlib.
#options.detection_window_size = 60 * 80
options.detection_window_size = int((50 * 70)) # 468, 1.44
dlib.train_simple_object_detector("../data/annotations/bb/training/combined_mtb.xml", "../data/models/detector_mtb.svm", options)
options.detection_window_size = int((40 * 90)) # 448, 2.29
dlib.train_simple_object_detector("../data/annotations/bb/training/combined_ped.xml", "../data/models/detector_ped.svm", options)
def trainObjects(images_folder):
folders = os.listdir(images_folder)
folders.remove('extras')
detectors = []
for folder in folders:
xml = os.path.join(images_folder, "{0}\{0}.xml".format(folder))
#print("{0}.svm".format(folder))
dlib.train_simple_object_detector(xml, "{0}.svm".format(folder),
options)
# save all detectors as list
detectors.append("{0}.svm".format(folder))
# Next, suppose you have trained multiple detectors and you want to run them
# efficiently as a group. You can do this as follows
detectorsModels = list()
for detector in detectors:
detectorsModels.append(dlib.fhog_object_detector(detector))
# testing multiple detectors with image
image = dlib.load_rgb_image(
images_folder +
'/head n shoulder/head-and-shoulder-best-oily-hair-shampoo.jpg')
[boxes, confidences, detector_idxs
] = dlib.fhog_object_detector.run_multiple(detectorsModels,
image,
upsample_num_times=1,
adjust_threshold=0.5)
for i in range(len(boxes)):
print("detector {} found box {} with confidence {}.".format(
detector_idxs[i], boxes[i], confidences[i]))
return detectorsModels, detectors
def test_params(C, nuclear_norm):
options = dlib.simple_object_detector_training_options()
# our dataset is oriented, so definitely don't add in flips.
options.add_left_right_image_flips = False
options.C = C
options.num_threads = 1
options.be_verbose = False
options.nuclear_norm_regularization_strength = nuclear_norm
options.max_runtime_seconds = 5 # SET REALLY SMALL SO THE DEMO DOESN'T TAKE TO LONG, USE BIGGER VALUES FOR REAL USE!!!!!
dlib.train_simple_object_detector(
"images/small_face_dataset/cluster_001_train.xml", "detector1_.svm",
options)
# You can do a lot here. Run the detector through
# dlib.threshold_filter_singular_values() for instance to make sure it
# learns something that will work once thresholded. We can also add a
# penalty for having a lot of filters. Run this program a few times and
# try out different ways of penalizing the return from test_params() and
# see what happens.
result = dlib.test_simple_object_detector(
"images/small_face_dataset/cluster_001_test.xml", "detector1_.svm")
print("C = {}, nuclear_norm = {}".format(C, nuclear_norm))
print("testing accuracy: ", result)
sys.stdout.flush()
# For settings with the same average precision, we should prefer smaller C
# since smaller C has better generalization.
return result.average_precision - C * 1e-8
def train_object_detector(self):
self.__print_training_message('object detector')
opt = dlib.simple_object_detector_training_options()
opt.add_left_right_image_flips = True
opt.C = 5
opt.num_threads = self.cpu_cores
opt.be_verbose = True
opt.detection_window_size = self.window_size**2
dlib.train_simple_object_detector(self.xml, DETECTOR_SVM, opt)
def test_train_xml_detector(self):
# This effectively tests that we can successfully load images
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = True
options.C = 1
options.num_threads = 1
dlib.train_simple_object_detector('images.xml', "test.svm", options)
self.assertTrue(os.path.exists('./test.svm'))
def train_object_detector_for_path(self, xmlPath, outputPath):
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = False
options.C = 5
options.num_threads = 4
options.be_verbose = True
training_xml_path = os.path.join('tmp', xmlPath)
dlib.train_simple_object_detector(training_xml_path, outputPath,
options)
def training_data(train_xml, test_xml, detectorName, Csvm=5):
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = True
options.C = Csvm
options.num_threads = 4
options.be_verbose = True
dlib.train_simple_object_detector(train_xml, detectorName + ".svm",
options)
print("Testing accuracy: {}".format(
dlib.test_simple_object_detector(test_xml, detectorName + ".svm")))
def test_train_xml_detector(self):
# This effectively tests that we can successfully load images
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = True
options.C = 1
options.num_threads = 1
dlib.train_simple_object_detector(self.images_xml_path, './test.svm',
options)
self.assertTrue(os.path.exists('./test.svm'))
def train_shape_detector(self, output_name, input_xml):
print('[INFO] training shape detector....')
# get the training options
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = False
options.C = 5
options.num_threads = 4
options.be_verbose = True
# start training the model
dlib.train_simple_object_detector(input_xml, output_name, options)
def train_with_dlib(self, obj_folder, detector_path, train_file_name, test_file_name):
pdb.set_trace()
logger = MyUtils.Tee("{0}/{1}.log".format(obj_folder, 'run'), 'w')
logger.write('tee: dlib training called')
logger.write('dlib training called')
# Now let's do the training. The train_simple_object_detector() function has a
# bunch of options, all of which come with reasonable default values. The next
# few lines goes over some of these options.
options = dlib.simple_object_detector_training_options()
# The trainer is a kind of support vector machine and therefore has the usual
# SVM C parameter. In general, a bigger C encourages it to fit the training
# data better but might lead to overfitting. You must find the best C value
# empirically by checking how well the trained detector works on a test set of
# images you haven't trained on. Don't just leave the value set at 5. Try a
# few different C values and see what works best for your data.
options.C = 5
# Tell the code how many CPU cores your computer has for the fastest training.
options.num_threads = 2
options.be_verbose = True
training_xml_path = os.path.join(obj_folder, train_file_name)
testing_xml_path = os.path.join(obj_folder, test_file_name)
# This function does the actual training. It will save the final detector to
# detector.svm. The input is an XML file that lists the images in the training
# dataset and also contains the positions of the face boxes. To create your
# own XML files you can use the imglab tool which can be found in the
# tools/imglab folder. It is a simple graphical tool for labeling objects in
# images with boxes. To see how to use it read the tools/imglab/README.txt
# file. But for this example, we just use the training.xml file included with
# dlib.
logger.write('start training. saved detector path: ' + detector_path)
dlib.train_simple_object_detector(training_xml_path, detector_path, options)
logger.write( 'end training')
# Now that we have a face detector we can test it. The first statement tests
# it on the training data. It will logger.write((the precision, recall, and then)
# average precision.
logger.write("") # Print blank line to create gap from previous output
logger.write("Training accuracy: {}".format(
dlib.test_simple_object_detector(training_xml_path, detector_path)))
# However, to get an idea if it really worked without overfitting we need to
# run it on images it wasn't trained on. The next line does this. Happily, we
# see that the object detector works perfectly on the testing images.
accuracy = dlib.test_simple_object_detector(testing_xml_path, "detector.svm")
logger.write("Testing accuracy: {}".format(accuracy))
logger.flush()
return accuracy
def train():
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = True
options.C = 5
options.num_threads = 4
options.be_verbose = True
options.detection_window_size = 1024
options.match_eps = 0.1
training_xml_path = "../pics/train/training-single.xml"
# training_xml_path = "/home/external/moderation-p**n-detector/oboobs.dlibxml"
dlib.train_simple_object_detector(training_xml_path, "../boobs.svm", options)
print("Training accuracy: {}".format(dlib.test_simple_object_detector(training_xml_path, "../boobs.svm")))
def training():
""" 训练样本 """
print('training samples ...')
options = dlib.simple_object_detector_training_options()
# 要识别的图形是否左右对称
options.add_left_right_image_flips = True
# C越大表示更好地去拟合训练集，当然也有可能造成过拟合。通过尝试不同C在测试集上的效果得到最佳值
options.C = 5
# 训练数据时开启的线程数
options.num_threads = 2
# 是否输出详细日志
options.be_verbose = False
dlib.train_simple_object_detector(samples_xml, samples_svm, options)
print('finished.')
def create_svm(request,pk,template_name='create_svm.html'):
brand = get_object_or_404(Brands, pk=pk)
data = {}
data[ 'pk' ] = pk
if request.method == 'POST':
svm = request.POST.get('svm')
cval = request.POST.get('cval')
paths = Paths.objects.filter( brand_id = pk )
if paths.exists():
for pt in paths:
train_path = pt.train_path
train_path = os.path.relpath(train_path,settings.MEDIA_ROOT)
test_path = pt.test_path
test_path = os.path.relpath(test_path,settings.MEDIA_ROOT)
svm_path = pt.svm_path
#cmd = "python 35Hawkdetect.py /var/sites/thirdauth/static/images/companies/Stovekraft\ Private\ Limited\(mohsin\)/idea/test/ cola123.svm jpg"
print svm_path
print settings.MEDIA_ROOT+"/"+train_path+"/"
faces_folder = settings.MEDIA_ROOT+"/"+train_path+"/"
test_folder = settings.MEDIA_ROOT+"/"+test_path+"/"
print faces_folder
#dest = "/var/sites/thirdauth/static/images/companies/Stovekraft Private Limited(mohsin)/Docomo/svm"
timestr = svm+time.strftime("_%m_%d_%H_%M")+".svm"
print timestr
outputpath = str(svm)+".svm"
cval = cval
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = True
options.C = int(cval)
options.num_threads = 4
options.be_verbose = True
training_xml_path = os.path.join(str(faces_folder), "training.xml")
testing_xml_path = os.path.join(str(test_folder), "training.xml")
dlib.train_simple_object_detector(training_xml_path,outputpath, options)
print("")
print("Training accuracy: {}".format(
dlib.test_simple_object_detector(training_xml_path, outputpath)))
print("Testing accuracy: {}".format(
dlib.test_simple_object_detector(testing_xml_path, outputpath)))
result = "Training accuracy: {}"+format(dlib.test_simple_object_detector(training_xml_path, outputpath))+" Testing accuracy: {}"+format(dlib.test_simple_object_detector(testing_xml_path, outputpath))
os.rename(str(outputpath),timestr)
if os.path.exists(str(svm_path)+"/"+str(timestr)):
os.remove(str(svm_path)+"/"+str(timestr))
shutil.move("/var/sites/thirdauth/"+str(timestr),str(svm_path))
Svms(svm_name = str(timestr), brand_id = pk , company_id = brand.company_id ).save()
return HttpResponse(result)
else:
return render(request,template_name, data ,context_instance=RequestContext(request))
def do_training(self):
trainpath = os.path.join(self.translate_path(self.path), "train.txt")
trainfile = open(trainpath, 'r')
testdatadef = trainfile.readlines()
trainfile.close()
result = []
images = []
boxes = []
for testdata in testdatadef:
testvalues = testdata.split(";")
boxes.append([
dlib.rectangle(int(testvalues[0]), int(testvalues[1]),
int(testvalues[2]), int(testvalues[3]))
])
imagepath = os.path.join(self.translate_path(self.path),
testvalues[4].strip("\n"))
result.append(testvalues[4])
images.append(dlib.load_grayscale_image(imagepath))
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = True
options.C = 5
# options.be_verbose = False
start_time = time.clock()
SimpleHTTPRequestHandler.trained_detector = dlib.train_simple_object_detector(
images, boxes, options)
self.step_times.append("Trained HOG + SVM Detection: %.3f s" %
(time.clock() - start_time))
print(type(SimpleHTTPRequestHandler.trained_detector))
return result
def fit(self,
paths,
annotations,
target_path,
vis=True,
n_thread=1,
C=5,
verbose=True,
add_left_right_image_flips=True):
self.__option.num_threads = n_thread
self.__option.C = C
self.__option.be_verbose = verbose
self.__option.add_left_right_image_flips = add_left_right_image_flips
images = self.__prep_image(paths)
print('[IMAGE SIZE] {:.2f} MB'.format(
sys.getsizeof(images) / 1024 * 1024))
annotations = self.__prep_annotations(annotations)
print('[ANNOT SIZE] {:.2f} MB'.format(
sys.getsizeof(annotations) / 1024 * 1024))
self.__detector = dlib.train_simple_object_detector(
images, annotations, self.__option)
if vis:
win = dlib.image_window()
win.set_image(self.__detector)
dlib.hit_enter_to_continue()
self.__detector.save(target_path)
def training(boxes, images):
u"""学習"""
# simple_object_detectorの訓練用オプションを取ってくる
options = dlib.simple_object_detector_training_options()
# 左右対照に学習データを増やすならtrueで訓練(メモリを使う)
options.add_left_right_image_flips = True
# SVMを使ってるのでC値を設定する必要がある
options.C = 5
# スレッド数指定
options.num_threads = 16
# 学習途中の出力をするかどうか
options.be_verbose = True
# 停止許容範囲
# options.epsilon = 0.001
options.epsilon = 0.01
# サンプルを増やす最大数(大きすぎるとメモリを使う)
options.upsample_limit = 1
# 矩形検出の最小窓サイズ(80*80=6400となる)
options.detection_window_size = 6400
# options.detection_window_size = 100
# 学習してsvmファイルを保存
print('train...')
detector = dlib.train_simple_object_detector(images, boxes, options)
detector.save('./detector.svm')
def train_detector_given_image_list(myImageList, Annotation_Path,
DetectorOutputFolder):
# Set Default Options
options = dlib.simple_object_detector_training_options()
images = []
imagename = []
boxes = []
annotations = []
for imagefilename in myImageList:
images.append(cv2.imread(imagefilename))
imagename.append(name)
annotations = loadmat(os.path.join(Annotation_Path, name + ".xml"))
bb = [
dlib.rectangle(left=x, top=y, right=w, bottom=h)
for (y, h, x, w) in annotations
]
boxes.append(bb)
# Train the object detector
print("[INFO] Training the Support Vector Machine Deector")
mySVM_Detector = dlib.train_simple_object_detector(images, boxes, options)
# Save the detector
print("[INFO] Saving SVM Detector")
mySVM_Detector.save(DetectorOutputFolder)
def train_detector(FolderName_Class, Annotation_Path, DetectorOutputFolder):
# Set Default Options
options = dlib.simple_object_detector_training_options()
images = []
imagename = []
boxes = []
annotations = []
exts = [
'.bmp', '.pbm', '.pgm', '.ppm', '.sr', '.ras', '.jpeg', '.jpg', '.jpe',
'.jp2', '.tiff', '.tif', '.png'
]
# Loop over all images inside the specified folder (single class)
myImageList = os.listdir(FolderName_Class)
for imagefilename in myImageList:
name, ext = os.path.splitext(imagefilename)
if ext in exts:
images.append(cv2.imread(imagefilename))
imagename.append(name)
annotations = loadmat(os.path.join(Annotation_Path, name + ".xml"))
bb = [
dlib.rectangle(left=x, top=y, right=w, bottom=h)
for (y, h, x, w) in annotations
]
boxes.append(bb)
# Train the object detector
print("[INFO] Training the Support Vector Machine Deector")
mySVM_Detector = dlib.train_simple_object_detector(images, boxes, options)
# Save the detector
print("[INFO] Saving SVM Detector")
mySVM_Detector.save(DetectorOutputFolder)
def model_training(imgs_path, xml_name):
# 训练参数
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = True
# 支持向量机的C参数，通常默认取为5.自己适当更改参数以达到最好的效果
options.C = 5
# 线程数，根据CPU核心数填写
options.num_threads = 1
options.be_verbose = True
import time
start_time = time.time()
print(' -- 开始训练 -- ')
dlib.train_simple_object_detector(imgs_path + xml_name, 'detector.svm', options)
# print("训练精准度: {}".format(
# dlib.test_simple_object_detector(imgs_path + xml_name, "detector.svm")))
print(f'--训练完成-- 耗时:{time.time() - start_time}s')
def main():
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = True
options.C = 4
options.epsilon = 0.05
options.num_threads = 8
options.be_verbose = True
training_xml_path = os.path.join(training_dir, file_name)
# testing_xml_path = os.path.join(testing_dir, file_name)
dlib.train_simple_object_detector(training_xml_path, detector_name,
options)
print("")
print("================================")
print("")
def do_train(self, training_xml_path, testing_xml_path, name_svm,
hyperparameters):
options = dlib.simple_object_detector_training_options()
options.detection_window_size = int(hyperparameters[0])
# options.add_left_right_image_flips = True
options.C = int(hyperparameters[2])
options.num_threads = int(hyperparameters[1])
options.epsilon = hyperparameters[3]
options.be_verbose = True
dlib.train_simple_object_detector(training_xml_path, name_svm, options)
print("") # Print blank line to create gap from previous output
print("Training accuracy: {}".format(
dlib.test_simple_object_detector(training_xml_path, name_svm)))
print("Testing accuracy: {}".format(
dlib.test_simple_object_detector(testing_xml_path, name_svm)))
self.detector = name_svm
def train():
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = True
options.C = 5
options.num_threads = 4
options.be_verbose = True
options.detection_window_size = 1024
options.match_eps = 0.1
training_xml_path = "../pics/train/training-single.xml"
# training_xml_path = "/home/external/moderation-p**n-detector/oboobs.dlibxml"
dlib.train_simple_object_detector(training_xml_path, "../boobs.svm",
options)
print("Training accuracy: {}".format(
dlib.test_simple_object_detector(training_xml_path, "../boobs.svm")))
def train(training_xml_path, model_file="detector.svm"):
assert os.path.isfile(training_xml_path)
assert not os.path.isfile(model_file)
# Now let's do the training. The train_simple_object_detector() function has a
# bunch of options, all of which come with reasonable default values. The next
# few lines goes over some of these options.
options = dlib.simple_object_detector_training_options()
# Since faces are left/right symmetric we can tell the trainer to train a
# symmetric detector. This helps it get the most value out of the training
# data.
options.add_left_right_image_flips = True
# The trainer is a kind of support vector machine and therefore has the usual
# SVM C parameter. In general, a bigger C encourages it to fit the training
# data better but might lead to overfitting. You must find the best C value
# empirically by checking how well the trained detector works on a test set of
# images you haven't trained on. Don't just leave the value set at 5. Try a
# few different C values and see what works best for your data.
options.C = 10
# Tell the code how many CPU cores your computer has for the fastest training.
options.num_threads = 6
options.epsilon = 0.001
options.be_verbose = True
options.detection_window_size = 4096 #(32, 32)
# options.upsample_limit = 8
# This function does the actual training. It will save the final detector to
# detector.svm. The input is an XML file that lists the images in the training
# dataset and also contains the positions of the face boxes. To create your
# own XML files you can use the imglab tool which can be found in the
# tools/imglab folder. It is a simple graphical tool for labeling objects in
# images with boxes. To see how to use it read the tools/imglab/README.txt
# file. But for this example, we just use the training.xml file included with
# dlib.
print("Goingt to train ...")
dlib.train_simple_object_detector(training_xml_path, model_file, options)
# Now that we have a face detector we can test it. The first statement tests
# it on the training data. It will print(the precision, recall, and then)
# average precision.
print("") # Print blank line to create gap from previous output
print("Training accuracy: {}".format(
dlib.test_simple_object_detector(training_xml_path, model_file)))
def train(path_xml):
# objeto contenedor de las opciones para la rutina train_simple_object_detector()
# todas las opciones vienen con valores por defecto razonables
# http://dlib.net/python/index.html#dlib.simple_object_detector_training_options
options = dlib.simple_object_detector_training_options()
options.C = 6 # parametro C de las SVM, valores grandes pueden llevar al overfitting
options.add_left_right_image_flips = True # para objetos simetricos como las caras
options.be_verbose = True
options.epsilon = 0.005 # epsilon de detencion, valores pequeños -> accurate training
# utilizando la herramienta https://imglab.ml
dlib.train_simple_object_detector(path_xml, "detector.svm", options)
print("\nTraining accuracy: ",
dlib.test_simple_object_detector(path_xml, "detector.svm"))
def CREATE_SVM_DETECTOR():
options = dlib.simple_object_detector_training_options()
options.C = 5
options.num_threads = 4
options.be_verbose = True
# options.add_left_right_image_flips = True
fname_xml_train = 'data/xml/cat_BHS.xml'
# fname_xml_test = 'data/xml/testing.xml'
dlib.train_simple_object_detector(fname_xml_train, "cat_detector.svm",
options)
print()
print("Training accuracy: {}".format(
dlib.test_simple_object_detector(fname_xml_train, "cat_detector.svm")))
def learnFeatureDlib(feat, tester):
testImages = []
testImageBoxes = []
featureName = feat.featureName
pathToClippingDirectory = tester.basePath + "Training/" + featureName + '/TrainDlib'
pathToTrainingDirectory = pathToClippingDirectory + '/' + 'dlibTraining'
trainingList = getListOfDlibSamples(pathToTrainingDirectory)
for file in trainingList:
testImageColor = cv2.imread(file)
testImages.append(cv2.cvtColor(testImageColor, cv2.COLOR_BGR2GRAY))
numRows, numCols, numColors = testImageColor.shape
boxList = getBoundingBoxList(file)
boxesForThisImage = []
if not boxList is None:
for box in boxList:
left = box[0]
right = left + feat.roiSideLength
top = box[1]
bottom = top + feat.roiSideLength
print("Left: " + str(left) + ", Top: " + str(top) + "Right: " +
str(right) + ", Bottom: " + str(bottom))
# if left<0 or top<0 or right>=numCols or bottom>=numRows:
# print("Tossed box: Left: " + str(left) + ", Top: " + str(top) + "Right: " + str(right) + ", Bottom: " + str(bottom))
# else:
# testBox=dlib.rectangle(left=box.xLeft,top=box.yTop,right=box.xRight,bottom=box.yBottom)
testBox = dlib.rectangle(left=left,
top=top,
right=right,
bottom=bottom)
boxesForThisImage.append(testBox)
testImageBoxes.append(boxesForThisImage)
# Now let's do the training. The train_simple_object_detector() function has a
# bunch of options, all of which come with reasonable default values. The next
# few lines goes over some of these options.
options = dlib.simple_object_detector_training_options()
# Since faces are left/right symmetric we can tell the trainer to train a
# symmetric detector. This helps it get the most value out of the training
# data.
# The trainer is a kind of support vector machine and therefore has the usual
# SVM C parameter. In general, a bigger C encourages it to fit the training
# data better but might lead to overfitting. You must find the best C value
# empirically by checking how well the trained detector works on a test set of
# images you haven't trained on. Don't just leave the value set at 5. Try a
# few different C values and see what works best for your data.
options.C = feat.cParmValue
options.U = feat.upSampling
# Tell the code how many CPU cores your computer has for the fastest training.
options.num_threads = 4
options.be_verbose = True
detector = dlib.train_simple_object_detector(testImages, testImageBoxes,
options)
# We could save this detector to disk by uncommenting the following.
detectorLocation = pathToClippingDirectory + "/detector.svm"
detector.save(detectorLocation)
print('Dlib Training Done')
feat.model = detector
def step4(self, btn):
#Based on dlib example:
# Now let's do the training. The train_simple_object_detector() function has a
# bunch of options, all of which come with reasonable default values. The next
# few lines goes over some of these options.
options = dlib.simple_object_detector_training_options()
# Since faces are left/right symmetric we can tell the trainer to train a
# symmetric detector. This helps it get the most value out of the training
# data.
options.add_left_right_image_flips = True
# The trainer is a kind of support vector machine and therefore has the usual
# SVM C parameter. In general, a bigger C encourages it to fit the training
# data better but might lead to overfitting. You must find the best C value
# empirically by checking how well the trained detector works on a test set of
# images you haven't trained on. Don't just leave the value set at 5. Try a
# few different C values and see what works best for your data.
options.C = 5
# Tell the code how many CPU cores your computer has for the fastest training.
options.num_threads = 4
options.be_verbose = True
trainingXML = os.path.join(self.tmp, 'training.xml')
#Ideally there would be half training, half testing:
testingXML = os.path.join(self.tmp, "training.xml")
# This function does the actual training. It will save the final detector to
# detector.svm. The input is an XML file that lists the images in the training
# dataset and also contains the positions of the face boxes. To create your
# own XML files you can use the imglab tool which can be found in the
# tools/imglab folder. It is a simple graphical tool for labeling objects in
# images with boxes.
dlib.train_simple_object_detector(
trainingXML, os.path.join(self.tmp, "detector.svm"), options)
print("Training accuracy: {}".format(
dlib.test_simple_object_detector(
trainingXML, os.path.join(self.tmp, "detector.svm"))))
def train_detector(save_name):
#Point to folder
folder = "../data/TrainHOG/"
coins_folder = folder
#Now train a simple object detector using dlib
#Using the folowing options
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = True
options.C = 10
# Tell the code how many CPU cores your computer has for the fastest training.
options.num_threads = 4
options.be_verbose = True
training_xml_path = os.path.join(coins_folder, "merged.xml")
detective = os.path.join(coins_folder, str(save_name))
dlib.train_simple_object_detector(training_xml_path, detective, options)
print("done training")
def trainer(self, imgs, ants):
self.images = imgs
self.annots = ants
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = True
options.C = 5
options.num_threads = 4
options.be_verbose = True
detector = dlib.train_simple_object_detector(self.images, self.annots,
options)
return detector
def simple_training(trainpath="Training/", nbthreads=4, cvalue=5):
train_folder = trainpath
#Para treinarmos nosso dataset, chamaremos a classe train_simple_object_detector() com todos os seus valores default (que são razoavelmente bons)
options = dlib.simple_object_detector_training_options()
#Cartas são de certa forma simétricas, então, melhoraremos a qualidade do resultado mudando o padrão de add_left_right_image_flips para True
options.add_left_right_image_flips = True
#O valor de C encoraja um fitting melhor nos dados, mas um C muito grande encoraja overfitting, valor 5 ainda é experimental, precisamos de mais teste
options.C = cvalue
# Quantos Threads temos disponíveis para treinar em paralelo?
options.num_threads = nbthreads
#Vamos acompanhar o processo
options.be_verbose = True
#Concatene o diretório do treino e seu .xml correspondente numa string
training_xml_path = os.path.join(train_folder, "training.xml")
#testing_xml_path = os.path.join(train_folder, "testing.xml")
#Finalmente chamamos a função que faz o treino de fato. Salva o resultado em um detector .svm
# a partir do nosso .xml (Dados do treino supervisionado)
dlib.train_simple_object_detector(training_xml_path, "detector.svm",
options)
print("Training accuracy: {}".format(
dlib.test_simple_object_detector(training_xml_path, "detector.svm")))
print("Process done sucesssfully")
def fit(self,images,annotations,visualize=False, savePath=None):
annotations = self._prepare_annotations(annotations)
images = self._prepare_images(images)
print('IMAGES',images)
print('annots',annotations)
print(self.options)
self._detector = dlib.train_simple_object_detector(images,annotations,self.options)
if visualize:
win = dlib.image_window()
win.set_image(self._detector)
dlib.hit_enter_to_continue()
if savePath is not None:
self._detector.save(savePath)
return self
# loop over the image paths
for imagePath in paths.list_images(args["class"]):
# extract the image ID from the image path and load the annotations file
imageID = imagePath[imagePath.rfind("/") + 1:].split("_")[1]
imageID = imageID.replace(".png", "")
p = "{}/annotation_{}.txt".format(args["annotations"], imageID)
#annotations = loadmat(p)["box_coord"]
annotations = getAnnotation(p)
# loop over the annotations and add each annotation to the list of bounding
# boxes
bb = [dlib.rectangle(left=long(annotations[0]), top=long(annotations[1]), right=long(annotations[0]+annotations[2]), bottom=long(annotations[1]+annotations[3]))]
boxes.append(bb)
# add the image to the list of images
images.append(io.imread(imagePath))
# train the object detector
print("[INFO] training detector...")
detector = dlib.train_simple_object_detector(images, boxes, options)
# dump the classifier to file
print("[INFO] dumping classifier to file...")
detector.save(args["output"])
# visualize the results of the detector
win = dlib.image_window()
win.set_image(detector)
dlib.hit_enter_to_continue()
import cv2
import dlib
import os
from skimage import filter, data, io
from skimage.viewer import ImageViewer
learning_folder = 'learning'
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = True
options.C = 5
options.num_threads = 1
options.be_verbose = True
training_xml_path = os.path.join(learning_folder,'info.xml')
dlib.train_simple_object_detector(training_xml_path, 'info.svm', options)
print ("")
print ("Training accuracy: {}".format(
dlib.test_simple_object_detector(training_xml_path, "info.svm")
))
detector = dlib.simple_object_detector("info.svm")
win_det = dlib.image_window()
win_det.set_image(detector)
dlib.hit_enter_to_continue()
def train_dlib_detector(images, epsilon=0.01, add_left_right_image_flips=False,
verbose_stdout=False, C=5, detection_window_size=6400,
num_threads=None):
r"""
Train a dlib detector with the given list of images.
This is intended to easily train a list of menpo images that have their
bounding boxes attached as landmarks. Each landmark group on the image
will have a tight bounding box extracted from it and then dlib will
train given these images.
Parameters
----------
images : `list` of `menpo.image.Image`
The set of images to learn the detector from. Must have landmarks
attached to **every** image, a bounding box will be extracted for each
landmark group.
epsilon : `float`, optional
The stopping epsilon. Smaller values make the trainer's solver more
accurate but might take longer to train.
add_left_right_image_flips : `bool`, optional
If ``True``, assume the objects are left/right symmetric and add in
left right flips of the training images. This doubles the size of the
training dataset.
verbose_stdout : `bool`, optional
If ``True``, will allow dlib to output its verbose messages. These
will only be printed to the stdout, so will **not** appear in an IPython
notebook.
C : `int`, optional
C is the usual SVM C regularization parameter. Larger values of C will
encourage the trainer to fit the data better but might lead to
overfitting.
detection_window_size : `int`, optional
The number of pixels inside the sliding window used. The default
parameter of ``6400 = 80 * 80`` window size.
num_threads : `int` > 0 or ``None``
How many threads to use for training. If ``None``, will query
multiprocessing for the number of cores.
Returns
-------
detector : `dlib.simple_object_detector`
The trained detector. To save this detector, call save on the returned
object and pass a string path.
Examples
--------
Training a simple object detector from a list of menpo images and save it
for later use:
>>> images = list(mio.import_images('./images/path'))
>>> in_memory_detector = train_dlib_detector(images, verbose_stdout=True)
>>> in_memory_detector.save('in_memory_detector.svm')
"""
rectangles = [[pointgraph_to_rect(lgroup.lms.bounding_box())
for lgroup in im.landmarks.values()]
for im in images]
image_pixels = [menpo_image_to_uint8(im) for im in images]
if num_threads is None:
import multiprocessing
num_threads = multiprocessing.cpu_count()
options = dlib.simple_object_detector_training_options()
options.epsilon = epsilon
options.add_left_right_image_flips = add_left_right_image_flips
options.be_verbose = verbose_stdout
options.C = C
options.detection_window_size = detection_window_size
options.num_threads = num_threads
return dlib.train_simple_object_detector(image_pixels, rectangles, options)
import dlib, sys, glob from skimage import io # cups_training = '/home/jyotiska/Dropbox/Computer Vision/cupdataset.xml' bottle_training = "/home/jyotiska/Dropbox/Computer Vision/bottledataset.xml" # bottle_test_dir = 'bottle_train' options = dlib.simple_object_detector_training_options() options.add_left_right_image_flips = True options.C = 4 options.epsilon = 0.01 options.num_threads = 8 options.be_verbose = True dlib.train_simple_object_detector(bottle_training, "bottledetector.svm", options) # print "\nTraining accuracy: ", dlib.test_simple_object_detector(cups_training,"cupdetector.svm")
# images you haven't trained on. Don't just leave the value set at 5. Try a # few different C values and see what works best for your data. options.C = 5 # Tell the code how many CPU cores your computer has for the fastest training. options.num_threads = 4 options.be_verbose = True # This function does the actual training. It will save the final detector to # detector.svm. The input is an XML file that lists the images in the training # dataset and also contains the positions of the face boxes. To create your # own XML files you can use the imglab tool which can be found in the # tools/imglab folder. It is a simple graphical tool for labeling objects in # images with boxes. To see how to use it read the tools/imglab/README.txt # file. But for this example, we just use the training.xml file included with # dlib. dlib.train_simple_object_detector(faces_folder+"/training.xml","detector.svm", options) # Now that we have a face detector we can test it. The first statement tests # it on the training data. It will print the precision, recall, and then # average precision. print "\ntraining accuracy:", dlib.test_simple_object_detector(faces_folder+"/training.xml", "detector.svm") # However, to get an idea if it really worked without overfitting we need to # run it on images it wasn't trained on. The next line does this. Happily, we # see that the object detector works perfectly on the testing images. print "testing accuracy: ", dlib.test_simple_object_detector(faces_folder+"/testing.xml", "detector.svm") # Now let's use the detector as you would in a normal application. First we
# Tell the code how many CPU cores your computer has for the fastest training.
options.num_threads = 4
options.be_verbose = True
training_xml_path = os.path.join(faces_folder, "training.xml")
testing_xml_path = os.path.join(faces_folder, "testing.xml")
# This function does the actual training. It will save the final detector to
# detector.svm. The input is an XML file that lists the images in the training
# dataset and also contains the positions of the face boxes. To create your
# own XML files you can use the imglab tool which can be found in the
# tools/imglab folder. It is a simple graphical tool for labeling objects in
# images with boxes. To see how to use it read the tools/imglab/README.txt
# file. But for this example, we just use the training.xml file included with
# dlib.
dlib.train_simple_object_detector(training_xml_path, "detector.svm", options)
# Now that we have a face detector we can test it. The first statement tests
# it on the training data. It will print(the precision, recall, and then)
# average precision.
print("") # Print blank line to create gap from previous output
print("Training accuracy: {}".format(
dlib.test_simple_object_detector(training_xml_path, "detector.svm")))
# However, to get an idea if it really worked without overfitting we need to
# run it on images it wasn't trained on. The next line does this. Happily, we
# see that the object detector works perfectly on the testing images.
print("Testing accuracy: {}".format(
dlib.test_simple_object_detector(testing_xml_path, "detector.svm")))
import dlib, sys, glob from skimage import io cups_training = '/home/jyotiska/Dropbox/Computer Vision/cupdataset.xml' cups_training_2 = '/home/jyotiska/Dropbox/Computer Vision/cupdataset_3.xml' cup_test_dir = 'Cups_train' options = dlib.simple_object_detector_training_options() options.add_left_right_image_flips = True options.C = 4 options.epsilon = 0.01 options.num_threads = 8 options.be_verbose = True dlib.train_simple_object_detector(cups_training_2,"cupdetector_3.svm",options) # print "\nTraining accuracy: ", dlib.test_simple_object_detector(cups_training,"cupdetector.svm")
# does all the training import os import sys import glob import dlib # from skimage import io path = os.getcwd() + '/../' options = dlib.simple_object_detector_training_options() options.add_left_right_image_flips = True # The trainer is a kind of support vector machine and therefore has the usual # SVM C parameter. In general, a bigger C encourages it to fit the training # data better but might lead to overfitting. You must find the best C value # empirically by checking how well the trained detector works on a test set of # images you haven't trained on. Don't just leave the value set at 5. Try a # few different C values and see what works best for your data. options.C = 5 # Tell the code how many CPU cores your computer has for the fastest training. options.num_threads = 2 options.be_verbose = True training_xml_path = os.path.join(path, 'data/mdl_detector/train.xml') testing_xml_path = os.path.join(path, 'data/mdl_detector/test.xml') # does the training dlib.train_simple_object_detector(training_xml_path, path + 'data/detector.svm', options)
# Tell the code how many CPU cores your computer has for the fastest training.
options.num_threads = 8
options.be_verbose = True
training_xml_path = "signs.xml"
## testing_xml_path = os.path.join(faces_folder, "testing.xml")
# This function does the actual training. It will save the final detector to
# detector.svm. The input is an XML file that lists the images in the training
# dataset and also contains the positions of the face boxes. To create your
# own XML files you can use the imglab tool which can be found in the
# tools/imglab folder. It is a simple graphical tool for labeling objects in
# images with boxes. To see how to use it read the tools/imglab/README.txt
# file. But for this example, we just use the training.xml file included with
# dlib.
dlib.train_simple_object_detector(training_xml_path, TRAINING, options)
# Now that we have a face detector we can test it. The first statement tests
# it on the training data. It will print(the precision, recall, and then)
# average precision.
print("") # Print blank line to create gap from previous output
print("Training accuracy: {}".format(dlib.test_simple_object_detector(training_xml_path, TRAINING)))
# Now let's use the detector as you would in a normal application. First we
# will load it from disk.
detector = dlib.simple_object_detector(TRAINING)
# We can look at the HOG filter we learned. It should look like a face. Neat!
win_det = dlib.image_window()
win_det.set_image(detector)
options.num_threads = 2
options.be_verbose = True
training_xml_path = os.path.join(obj_folder, "training.xml")
testing_xml_path = os.path.join(obj_folder, "testing.xml")
# This function does the actual training. It will save the final detector to
# detector.svm. The input is an XML file that lists the images in the training
# dataset and also contains the positions of the face boxes. To create your
# own XML files you can use the imglab tool which can be found in the
# tools/imglab folder. It is a simple graphical tool for labeling objects in
# images with boxes. To see how to use it read the tools/imglab/README.txt
# file. But for this example, we just use the training.xml file included with
# dlib.
print "start training"
dlib.train_simple_object_detector(training_xml_path, "detector.svm", options)
print "end training"
# Now that we have a face detector we can test it. The first statement tests
# it on the training data. It will print(the precision, recall, and then)
# average precision.
print ("") # Print blank line to create gap from previous output
print ("Training accuracy: {}".format(dlib.test_simple_object_detector(training_xml_path, "detector.svm")))
# However, to get an idea if it really worked without overfitting we need to
# run it on images it wasn't trained on. The next line does this. Happily, we
# see that the object detector works perfectly on the testing images.
print ("Testing accuracy: {}".format(dlib.test_simple_object_detector(testing_xml_path, "detector.svm")))
# Now let's use the detector as you would in a normal application. First we
import datetime
import os
bottle_training_data = 'helpers/bottles_dataset.xml'
img_list = 'fetch_images/image_urls.txt'
options = dlib.simple_object_detector_training_options()
options.add_left_right_image_flips = True
# options.detection_window_size = 8000
options.C = 4
options.epsilon = 0.01
options.num_threads = 8
options.be_verbose = True
dlib.train_simple_object_detector(bottle_training_data,"square_bottle_classifier.svm",options)
ts = time.time()
st = datetime.datetime.fromtimestamp(ts).strftime('%Y-%m-%d %H:%M:%S') + '/'
parentDir = 'models/'
if not os.path.exists(parentDir + st):
os.makedirs(parentDir + st)
shutil.copyfile("square_bottle_classifier.svm", parentDir + st + "square_bottle_classifier.svm")
shutil.copyfile(bottle_training_data, parentDir + st + "bottles_dataset.xml")
shutil.copyfile(img_list, parentDir + st + "image_urls.txt")
detector = dlib.simple_object_detector("square_bottle_classifier.svm")
win = dlib.image_window()
win.set_image(detector)