label_scale_up = Label(
tl=label_sub.tl() * WH + label_FR.tl() * WH_sub,
br=label_sub.tl() * WH + label_FR.br() * WH_sub)
tl = label_scale_up.tl().astype(int)
br = label_scale_up.br().astype(int)
txt_file.write(frd[0][0] + ' ' + str('%.2f' % frd[0][1]) +
' ' + str(tl[0]) + ' ' + str(tl[1]) + ' ' +
str(br[0]) + ' ' + str(br[1]) + '\n')
print '\twrote result to', join(
output_dir,
basename(splitext(img_path)[0]) + '.txt')
txt_file.close()
# manual arguments, it will automatically generate .txt file with the format for calculating mAP in this project:
# https://github.com/Cartucho/mAP
# the default dir path for txt files -> output_txt/
FR_weights = '/home/shaoheng/Documents/darknet-Alex/backup/FRNet_YOLOv3/FRNet_YOLOv3_50000.weights'
FR_netcfg = 'data/FRD/FRNet_YOLOv3.cfg'
FR_data = 'data/FRD/FRNet_YOLOv3.data'
valid_dataset = '500'
ROOT = '/home/shaoheng/Documents/mAP/input/images-optional' # root for validation images
print 'FRD Net pre-loading...'
FR_net = dn.load_net(FR_netcfg, FR_weights, 0)
FR_meta = dn.load_meta(FR_data)
threshold = 0.5
imgs_paths = image_files_from_folder(ROOT)
do_fr(imgs_paths)
# do_fr_after_YOLO(imgs_paths)
(WH, WH))).tolist()
tl = np.array([cx - w / 2., cy - h / 2.])
br = np.array([cx + w / 2., cy + h / 2.])
print '\t\t\tFR number', i, 'position:', tl, br, 'prob:', result[1]
FRs.append(Label(tl=tl, br=br))
category.append(result[0])
return np.array(FRs), category
else:
print '\t\t\tFR detection failed'
if __name__ == '__main__':
input_dir = 'samples/kr'
output_dir = 'output'
imgs_paths = image_files_from_folder(input_dir)
imgs_paths.sort()
for img_path in imgs_paths:
img = cv2.imread(img_path)
bname = basename(splitext(img_path)[0])
try:
FRs, cate = fr_detect(img)
for i in range(len(FRs)):
draw_bb(img, FRs[i], cate=cate[i])
except:
traceback.print_exc()
cv2.imwrite(join(output_dir, bname + '_out.jpg'), img)
outdir = args.output_dir
iterations = args.iterations
batch_size = args.batch_size
dim = 208
if not isdir(outdir):
makedirs(outdir)
model, model_stride, xshape, yshape = load_network(args.model, dim)
opt = getattr(keras.optimizers, args.optimizer)(lr=args.learning_rate)
model.compile(loss=loss, optimizer=opt)
print 'Checking input directory...'
Files = image_files_from_folder(train_dir)
Data = []
for file in Files:
labfile = splitext(file)[0] + '.txt'
if isfile(labfile):
L = readShapes(labfile)
I = cv2.imread(file)
Data.append([I, L[0]])
print '%d images with labels found' % len(Data)
dg = DataGenerator( data=Data, \
process_data_item_func=lambda x: process_data_item(x,dim,model_stride),\
xshape=xshape, \
yshape=(yshape[0],yshape[1],yshape[2]+1), \
from glob import glob
from os.path import splitext, basename, isfile
from WPOD_src.utils import crop_region, image_files_from_folder
from WPOD_src.drawing_utils import draw_label, draw_losangle, write2img
from WPOD_src.label import lread, Label, readShapes
from pdb import set_trace as pause
YELLOW = (0, 255, 255)
RED = (0, 0, 255)
input_dir = sys.argv[1]
output_dir = sys.argv[2]
img_files = image_files_from_folder(input_dir)
for img_file in img_files:
bname = splitext(basename(img_file))[0]
I = cv2.imread(img_file)
detected_cars_labels = '%s/%s_cars.txt' % (output_dir, bname)
Lcar = lread(detected_cars_labels)
sys.stdout.write('%s' % bname)
if Lcar: