def main(args):
net = args.input_size
anno_file = 'wider_face_train.txt'
# im_dir = 'head_data/images'
save_dir = 'native_' + str(net)
pos_save_dir = save_dir + '/positive'
part_save_dir = save_dir + '/part'
neg_save_dir = save_dir + '/negative'
if not os.path.exists(save_dir):
os.mkdir(save_dir)
if not os.path.exists(pos_save_dir):
os.mkdir(pos_save_dir)
if not os.path.exists(part_save_dir):
os.mkdir(part_save_dir)
if not os.path.exists(neg_save_dir):
os.mkdir(neg_save_dir)
f1 = open(os.path.join(save_dir, 'pos_' + str(net) + '.txt'), 'w')
f2 = open(os.path.join(save_dir, 'neg_' + str(net) + '.txt'), 'w')
f3 = open(os.path.join(save_dir, 'part_' + str(net) + '.txt'), 'w')
with open(anno_file, 'r') as f:
annotations = f.readlines()
num = len(annotations)
print('%d pics in total' % num)
p_idx = 0 # positive
n_idx = 0 # negative
d_idx = 0 # dont care
idx = 0
box_idx = 0
for annotation in annotations:
annotation = annotation.strip().split(' ')
im_path = annotation[0]
bbox = list(map(float, annotation[1:]))
boxes = np.array(bbox, dtype=np.float32).reshape(-1, 4)
img = cv2.imread(os.path.join(im_path))
idx += 1
if idx % 10000 == 0:
print(idx, 'images done')
height, width, channel = img.shape
neg_num = 0
while neg_num < 50:
size = npr.randint(40, min(width, height) / 2)
nx = npr.randint(0, width - size)
ny = npr.randint(0, height - size)
crop_box = np.array([nx, ny, nx + size, ny + size])
Iou = IoU(crop_box, boxes)
cropped_im = img[ny:ny + size, nx:nx + size, :]
resized_im = cv2.resize(cropped_im, (net, net),
interpolation=cv2.INTER_LINEAR)
try:
if np.max(Iou) < 0.3:
save_file = os.path.join(neg_save_dir, '%s.jpg' % n_idx)
f2.write(save_dir + '/negative/%s' % n_idx + ' 0\n')
cv2.imwrite(save_file, resized_im)
n_idx += 1
neg_num += 1
except:
print(im_path)
print("crop_box:", crop_box)
print("boxes:", boxes)
print("Iou:", Iou)
exit(-1)
print('%s images done, pos: %s part: %s neg: %s' %
(idx, p_idx, d_idx, n_idx))
for box in boxes:
x1, y1, x2, y2 = box
w = x2 - x1 + 1
h = y2 - y1 + 1
if max(w, h) < 40 or x1 < 0 or y1 < 0:
continue
for i in range(20):
size = npr.randint(int(min(w, h) * 0.8),
np.ceil(1.25 * max(w, h)))
delta_x = npr.randint(-w * 0.2, w * 0.2)
delta_y = npr.randint(-h * 0.2, h * 0.2)
nx1 = int(max(x1 + w / 2 + delta_x - size / 2, 0))
ny1 = int(max(y1 + h / 2 + delta_y - size / 2, 0))
nx2 = nx1 + size
ny2 = ny1 + size
if nx2 > width or ny2 > height:
continue
crop_box = np.array([nx1, ny1, nx2, ny2])
offset_x1 = (x1 - nx1) / float(size)
offset_y1 = (y1 - ny1) / float(size)
offset_x2 = (x2 - nx2) / float(size)
offset_y2 = (y2 - ny2) / float(size)
cropped_im = img[ny1:ny2, nx1:nx2, :]
resized_im = cv2.resize(cropped_im, (net, net),
interpolation=cv2.INTER_LINEAR)
box_ = box.reshape(1, -1)
if IoU(crop_box, box_) >= 0.65:
save_file = os.path.join(pos_save_dir, '%s.jpg' % p_idx)
f1.write(save_dir + '/positive/%s' % p_idx +
' 1 %.2f %.2f %.2f %.2f\n' %
(offset_x1, offset_y1, offset_x2, offset_y2))
cv2.imwrite(save_file, resized_im)
p_idx += 1
elif IoU(crop_box, box_) >= 0.4:
save_file = os.path.join(part_save_dir, '%s.jpg' % d_idx)
f3.write(save_dir + '/part/%s' % d_idx +
' -1 %.2f %.2f %.2f %.2f\n' %
(offset_x1, offset_y1, offset_x2, offset_y2))
cv2.imwrite(save_file, resized_im)
d_idx += 1
box_idx += 1
print('%s images done, pos: %s part: %s neg: %s' %
(idx, p_idx, d_idx, n_idx))
f1.close()
f2.close()
f3.close()
def main(args):
image_size = 48
save_dir = str(image_size)
anno_file = 'wider_face_train.txt'
im_dir = 'WIDER_train/images/'
neg_save_dir = save_dir+'/negative'
pos_save_dir = save_dir+'/positive'
part_save_dir = save_dir+'/part'
if not os.path.exists(save_dir):
os.mkdir(save_dir)
if not os.path.exists(pos_save_dir):
os.mkdir(pos_save_dir)
if not os.path.exists(part_save_dir):
os.mkdir(part_save_dir)
if not os.path.exists(neg_save_dir):
os.mkdir(neg_save_dir)
f1 = open(save_dir+'/pos_48.txt', 'w')
f2 = open(save_dir+'/neg_48.txt', 'w')
f3 = open(save_dir+'/part_48.txt', 'w')
threshold = [0.6, 0.6]
with open(anno_file, 'r') as f:
annotations = f.readlines()
num = len(annotations)
print('%d pics in total' % num)
p_idx = 0 # positive
n_idx = 0 # negative
d_idx = 0 # dont care
image_idx = 0
with tf.device('/gpu:0'):
minsize = 20
factor = 0.709
model_file_pnet = args.pnet_model
model_file_rnet = args.rnet_model
with tf.Graph().as_default():
config = tf.ConfigProto(allow_soft_placement=True)
config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
image_pnet = tf.placeholder(tf.float32, [None, None, None, 3])
pnet = PNet({'data': image_pnet}, mode='test')
out_tensor_pnet = pnet.get_all_output()
image_rnet = tf.placeholder(tf.float32, [None, 24, 24, 3])
rnet = RNet({'data': image_rnet}, mode='test')
out_tensor_rnet = rnet.get_all_output()
saver_pnet = tf.train.Saver([v for v in tf.global_variables()
if v.name[0:4] == 'pnet'])
saver_rnet = tf.train.Saver([v for v in tf.global_variables()
if v.name[0:4] == 'rnet'])
saver_pnet.restore(sess, model_file_pnet)
saver_rnet.restore(sess, model_file_rnet)
def pnet_fun(img): return sess.run(
out_tensor_pnet, feed_dict={image_pnet: img})
def rnet_fun(img): return sess.run(
out_tensor_rnet, feed_dict={image_rnet: img})
for annotation in annotations:
annotation = annotation.strip().split(' ')
bbox = list(map(float, annotation[1:]))
gts = np.array(bbox, dtype=np.float32).reshape(-1, 4)
#img_path = im_dir + annotation[0] + '.jpg'
img_path = annotation[0]
img = cv2.imread(img_path)
rectangles = detect_face_24net(img, minsize,
pnet_fun, rnet_fun,
threshold, factor)
image_idx += 1
view_bar(image_idx, num)
for box in rectangles:
lis = box.astype(np.int32)
mask = lis < 0
lis[mask] = 0
x_left, y_top, x_right, y_bottom, _ = lis
crop_w = x_right - x_left + 1
crop_h = y_bottom - y_top + 1
# ignore box that is too small or beyond image border
if crop_w < image_size or crop_h < image_size:
continue
Iou = IoU(box, gts)
cropped_im = img[y_top: y_bottom+1, x_left: x_right+1]
resized_im = cv2.resize(cropped_im,
(image_size, image_size),
interpolation=cv2.INTER_LINEAR)
# save negative images and write label
if np.max(Iou) < 0.3:
# Iou with all gts must below 0.3
save_file = os.path.join(neg_save_dir,
'%s.jpg' % n_idx)
f2.write('%s/negative/%s' %
(image_size, n_idx) + ' 0\n')
cv2.imwrite(save_file, resized_im)
n_idx += 1
else:
# find gt_box with the highest iou
idx = np.argmax(Iou)
assigned_gt = gts[idx]
x1, y1, x2, y2 = assigned_gt
# compute bbox reg label
offset_x1 = (x1 - x_left) / float(crop_w)
offset_y1 = (y1 - y_top) / float(crop_h)
offset_x2 = (x2 - x_right) / float(crop_w)
offset_y2 = (y2 - y_bottom) / float(crop_h)
if np.max(Iou) >= 0.65:
save_file = os.path.join(pos_save_dir,
'%s.jpg' % p_idx)
f1.write('%s/positive/%s' %
(image_size, p_idx) +
' 1 %.2f %.2f %.2f %.2f\n' %
(offset_x1, offset_y1,
offset_x2, offset_y2))
cv2.imwrite(save_file, resized_im)
p_idx += 1
elif np.max(Iou) >= 0.4:
save_file = os.path.join(part_save_dir,
'%s.jpg' % d_idx)
f3.write('%s/part/%s' % (image_size, d_idx) +
' -1 %.2f %.2f %.2f %.2f\n' %
(offset_x1, offset_y1,
offset_x2, offset_y2))
cv2.imwrite(save_file, resized_im)
d_idx += 1
f1.close()
f2.close()
f3.close()
def main(annotation_fp, image_dir, model_fp, output_dir):
image_size = 24
save_dir = os.path.join(output_dir, str(image_size))
neg_save_dir = save_dir + '/negative'
pos_save_dir = save_dir + '/positive'
part_save_dir = save_dir + '/part'
if not os.path.exists(save_dir):
os.mkdir(save_dir)
if not os.path.exists(pos_save_dir):
os.mkdir(pos_save_dir)
if not os.path.exists(part_save_dir):
os.mkdir(part_save_dir)
if not os.path.exists(neg_save_dir):
os.mkdir(neg_save_dir)
f1 = open(save_dir + '/pos_24.txt', 'w')
f2 = open(save_dir + '/neg_24.txt', 'w')
f3 = open(save_dir + '/part_24.txt', 'w')
threshold = 0.6
with open(annotation_fp, 'r') as f:
annotations = f.readlines()
num = len(annotations)
print('%d pics in total' % num)
p_idx = 0 # positive
n_idx = 0 # negative
d_idx = 0 # dont care
image_idx = 0
with tf.device('/gpu:0'):
minsize = 20
factor = 0.709
with tf.Graph().as_default():
config = tf.ConfigProto(allow_soft_placement=True)
config.gpu_options.per_process_gpu_memory_fraction = 0.5
with tf.Session(config=config) as sess:
image = tf.placeholder(tf.float32, [None, None, None, 3])
pnet = PNet({'data': image}, mode='test')
out_tensor = pnet.get_all_output()
init_op = tf.global_variables_initializer()
sess.run(init_op)
saver = tf.train.Saver()
saver.restore(sess, model_fp)
def pnet_fun(img):
return sess.run(out_tensor, feed_dict={image: img})
for annotation in annotations:
annotation = annotation.strip().split(' ')
bbox = list(map(float, annotation[1:5]))
gts = np.array(bbox, dtype=np.float32).reshape(-1, 4)
img_path = os.path.join(image_dir, annotation[0])
img = cv2.imread(img_path)
rectangles = detect_face_12net(img, minsize, pnet_fun,
threshold, factor)
image_idx += 1
view_bar(image_idx, num)
for box in rectangles:
lis = box.astype(np.int32)
mask = lis < 0
lis[mask] = 0
x_left, y_top, x_right, y_bottom, _ = lis
crop_w = x_right - x_left + 1
crop_h = y_bottom - y_top + 1
# ignore box that is too small or beyond image border
if crop_w < image_size or crop_h < image_size:
continue
iou = IoU(box, gts)
cropped_im = img[y_top:y_bottom + 1,
x_left:x_right + 1]
resized_im = cv2.resize(cropped_im,
(image_size, image_size),
interpolation=cv2.INTER_LINEAR)
# save negative images and write label
if np.max(iou) < 0.3:
filename = str(n_idx) + '.jpg'
# Iou with all gts must below 0.3
save_file = os.path.join(neg_save_dir, filename)
f2.write(
os.path.join(neg_save_dir, filename) + ' 0\n')
cv2.imwrite(save_file, resized_im)
n_idx += 1
else:
# find gt_box with the highest iou
idx = np.argmax(iou)
assigned_gt = gts[idx]
x1, y1, x2, y2 = assigned_gt
# compute bbox reg label
offset_x1 = (x1 - x_left) / float(crop_w)
offset_y1 = (y1 - y_top) / float(crop_h)
offset_x2 = (x2 - x_right) / float(crop_w)
offset_y2 = (y2 - y_bottom) / float(crop_h)
if np.max(iou) >= 0.65:
filename = str(p_idx) + '.jpg'
save_file = os.path.join(
pos_save_dir, filename)
f1.write(
os.path.join(pos_save_dir, filename) +
' 1 %.2f %.2f %.2f %.2f\n' %
(offset_x1, offset_y1, offset_x2,
offset_y2))
cv2.imwrite(save_file, resized_im)
p_idx += 1
elif np.max(iou) >= 0.4:
filename = str(d_idx) + '.jpg'
save_file = os.path.join(
part_save_dir, filename)
f3.write(
os.path.join(part_save_dir, filename) +
' -1 %.2f %.2f %.2f %.2f\n' %
(offset_x1, offset_y1, offset_x2,
offset_y2))
cv2.imwrite(save_file, resized_im)
d_idx += 1
f1.close()
f2.close()
f3.close()