def test_pretrained(self):
kwargs = {
'n_fg_class': self.n_fg_class,
'pretrained_model': self.pretrained_model,
}
if self.pretrained_model == 'voc0712':
valid = self.n_fg_class in {None, 20}
if valid:
YOLOv3(**kwargs)
else:
with self.assertRaises(ValueError):
YOLOv3(**kwargs)
def runYOLO():
'''parser = argparse.ArgumentParser()
parser.add_argument(
'--model', choices=('yolo_v2', 'yolo_v3'),
default='yolo_v2')
parser.add_argument('--gpu', type=int, default=-1)
parser.add_argument('--pretrained-model', default='voc0712')
parser.add_argument('image')
args = parser.parse_args()'''
aimage = 'sample7.jpg'
amodel = 'yolo_v2'
apretrained_model = 'voc0712'
agpu = -1
if amodel == 'yolo_v2':
model = YOLOv2(n_fg_class=len(voc_bbox_label_names),
pretrained_model=apretrained_model)
elif amodel == 'yolo_v3':
model = YOLOv3(n_fg_class=len(voc_bbox_label_names),
pretrained_model=apretrained_model)
if agpu >= 0:
chainer.cuda.get_device_from_id(agpu).use()
model.to_gpu()
img = utils.read_image(aimage, color=True)
bboxes, labels, scores = model.predict([img])
bbox, label, score = bboxes[0], labels[0], scores[0]
vis_bbox(img, bbox, label, score, label_names=voc_bbox_label_names)
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'--model', choices=('yolo_v2', 'yolo_v3'),
default='yolo_v2')
parser.add_argument('--n_fg_class', type=int, default=80)
parser.add_argument('darknetmodel')
parser.add_argument('output')
args = parser.parse_args()
if args.model == 'yolo_v2':
model = YOLOv2(n_fg_class=args.n_fg_class)
elif args.model == 'yolo_v3':
model = YOLOv3(n_fg_class=args.n_fg_class)
with chainer.using_config('train', False):
model(np.empty((1, 3, model.insize, model.insize), dtype=np.float32))
with open(args.darknetmodel, mode='rb') as f:
major = np.fromfile(f, dtype=np.int32, count=1)
minor = np.fromfile(f, dtype=np.int32, count=1)
np.fromfile(f, dtype=np.int32, count=1) # revision
assert(major * 10 + minor >= 2 and major < 1000 and minor < 1000)
np.fromfile(f, dtype=np.int64, count=1) # seen
if args.model == 'yolo_v2':
load_yolo_v2(f, model)
elif args.model == 'yolo_v3':
load_yolo_v3(f, model)
serializers.save_npz(args.output, model)
def main():
dataset = VOCBboxDataset(year='2007', split='test') \
.slice[[29, 301, 189, 229], 'img']
models = [
('Faster R-CNN', FasterRCNNVGG16(pretrained_model='voc07')),
('SSD300', SSD300(pretrained_model='voc0712')),
('SSD512', SSD512(pretrained_model='voc0712')),
('YOLOv2', YOLOv2(pretrained_model='voc0712')),
('YOLOv3', YOLOv3(pretrained_model='voc0712')),
]
fig = plt.figure(figsize=(30, 20))
for i, img in enumerate(dataset):
for j, (name, model) in enumerate(models):
bboxes, labels, scores = model.predict([img])
bbox, label, score = bboxes[0], labels[0], scores[0]
ax = fig.add_subplot(
len(dataset), len(models), i * len(models) + j + 1)
vis_bbox(
img, bbox, label, score,
label_names=voc_bbox_label_names, ax=ax
)
# Set MatplotLib parameters
ax.set_aspect('equal')
if i == 0:
font = FontProperties()
font.set_family('serif')
font.set_size(35)
ax.set_title(name, y=1.03, fontproperties=font)
plt.axis('off')
plt.tight_layout()
plt.show()
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'--model', choices=('yolo_v2', 'yolo_v2_tiny', 'yolo_v3'),
default='yolo_v2')
parser.add_argument('--gpu', type=int, default=-1)
parser.add_argument('--pretrained-model', default='voc0712')
parser.add_argument('image')
args = parser.parse_args()
if args.model == 'yolo_v2':
model = YOLOv2(
n_fg_class=len(voc_bbox_label_names),
pretrained_model=args.pretrained_model)
elif args.model == 'yolo_v2_tiny':
model = YOLOv2Tiny(
n_fg_class=len(voc_bbox_label_names),
pretrained_model=args.pretrained_model)
elif args.model == 'yolo_v3':
model = YOLOv3(
n_fg_class=len(voc_bbox_label_names),
pretrained_model=args.pretrained_model)
if args.gpu >= 0:
chainer.cuda.get_device_from_id(args.gpu).use()
model.to_gpu()
img = utils.read_image(args.image, color=True)
bboxes, labels, scores = model.predict([img])
bbox, label, score = bboxes[0], labels[0], scores[0]
vis_bbox(
img, bbox, label, score, label_names=voc_bbox_label_names)
plt.show()
def __init__(self, opts):
self.pretrained_models = ('voc0712', )
assert opts[
'pretrained_model'] in self.pretrained_models, "{} pretrained model doesn't exist".format(
opts.pretrained_model)
self.model = YOLOv3(n_fg_class=opts['n_classes'],
pretrained_model=opts['pretrained_model'])
def __init__(self, gpu, model, nms_thresh= 0.45, score_thresh=0.6):
self.gpu = gpu
if model == 'yolo_v2_tiny':
self.model = YOLOv2Tiny(
n_fg_class=len(voc_bbox_label_names),
pretrained_model='voc0712')
elif model == 'yolo_v3':
self.model = YOLOv3(
n_fg_class=len(voc_bbox_label_names),
pretrained_model='voc0712')
elif model == 'ssd300':
self.model = SSD300(
n_fg_class=len(voc_bbox_label_names),
pretrained_model='voc0712')
elif model == 'ssd512':
self.model = SSD512(
n_fg_class=len(voc_bbox_label_names),
pretrained_model='voc0712')
elif model == 'fasterrcnnvgg16':
self.model = FasterRCNNVGG16(
n_fg_class=len(coco_bbox_label_names),
pretrained_model='voc0712')
elif model == 'fasterrcnnfpnresnet50':
self.model = FasterRCNNFPNResNet50(
n_fg_class=len(coco_bbox_label_names),
pretrained_model='coco')
elif model == 'fasterrcnnfpnresnet101':
self.model = FasterRCNNFPNResNet101(
n_fg_class=len(coco_bbox_label_names),
pretrained_model='coco')
else:
self.model = YOLOv2(
n_fg_class=len(voc_bbox_label_names),
pretrained_model='voc0712')
#self.model.nms_thresh = nms_thresh
#self.model.score_thresh = score_thresh
if self.gpu >= 0:
chainer.cuda.get_device_from_id(self.gpu).use()
self.model.to_gpu()
def recog(file, outdir):
model = YOLOv3(
n_fg_class=len(voc_bbox_label_names),
pretrained_model='voc0712')
model.to_cpu()
image = file
img = utils.read_image(image, color=True)
bboxes, labels, scores = model.predict([img])
bbox, label, score = bboxes[0], labels[0], scores[0]
base_out_path = outdir + '/' + Path(file).stem
for (b, l, s) in zip(bbox, label, score):
dog_label_number = 11
count = 1
if l == dog_label_number:
crop_image(str(file), base_out_path + '_' + str(count) + '.jpg', int(b[1]), int(b[0]), int(b[3]), int(b[2]))
count += 1
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--model',
choices=('yolo_v2', 'yolo_v2_tiny', 'yolo_v3'),
default='yolo_v3')
parser.add_argument('--n-fg-class', type=int, default=7)
parser.add_argument('--darknetmodel', default='yolo-obj_6000.weights')
parser.add_argument('--output', default='accident_KitDashV_6000.npz')
args = parser.parse_args()
if args.model == 'yolo_v2':
model = YOLOv2(n_fg_class=args.n_fg_class)
# elif args.model == 'yolo_v2_tiny':
# model = YOLOv2Tiny(n_fg_class=args.n_fg_class)
elif args.model == 'yolo_v3':
model = YOLOv3(n_fg_class=args.n_fg_class)
with chainer.using_config('train', False):
model(np.empty((1, 3, model.insize, model.insize), dtype=np.float32))
with open(args.darknetmodel, mode='rb') as f:
major = np.fromfile(f, dtype=np.int32, count=1)
minor = np.fromfile(f, dtype=np.int32, count=1)
np.fromfile(f, dtype=np.int32, count=1) # revision
if major * 10 + minor >= 2 and major < 1000 and minor < 1000:
np.fromfile(f, dtype=np.int64, count=1) # seen
else:
np.fromfile(f, dtype=np.int32, count=1) # seen
if args.model == 'yolo_v2':
load_yolo_v2(f, model)
elif args.model == 'yolo_v2_tiny':
load_yolo_v2(f, model)
elif args.model == 'yolo_v3':
load_yolo_v3(f, model)
serializers.save_npz(args.output, model)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--model',
choices=('faster_rcnn', 'ssd300', 'ssd512', 'yolo_v3'),
default='ssd300')
parser.add_argument('--pretrained_model')
parser.add_argument('--gpu', type=int, default=-1)
parser.add_argument('--batchsize', type=int, default=32)
args = parser.parse_args()
if args.model == 'faster_rcnn':
if args.pretrained_model:
model = FasterRCNNVGG16(n_fg_class=len(voc_bbox_label_names),
pretrained_model=args.pretrained_model)
else:
model = FasterRCNNVGG16(pretrained_model='voc07')
elif args.model == 'ssd300':
if args.pretrained_model:
model = SSD300(n_fg_class=len(voc_bbox_label_names),
pretrained_model=args.pretrained_model)
else:
model = SSD300(pretrained_model='voc0712')
elif args.model == 'ssd512':
if args.pretrained_model:
model = SSD512(n_fg_class=len(voc_bbox_label_names),
pretrained_model=args.pretrained_model)
else:
model = SSD512(pretrained_model='voc0712')
elif args.model == 'yolo_v3':
if args.pretrained_model:
model = YOLOv3(n_fg_class=len(voc_bbox_label_names),
pretrained_model=args.pretrained_model)
else:
model = YOLOv3(pretrained_model='voc0712')
if args.gpu >= 0:
chainer.cuda.get_device_from_id(args.gpu).use()
model.to_gpu()
model.use_preset('evaluate')
dataset = VOCBboxDataset(year='2007',
split='test',
use_difficult=True,
return_difficult=True)
iterator = iterators.SerialIterator(dataset,
args.batchsize,
repeat=False,
shuffle=False)
in_values, out_values, rest_values = apply_to_iterator(model.predict,
iterator,
hook=ProgressHook(
len(dataset)))
# delete unused iterators explicitly
del in_values
pred_bboxes, pred_labels, pred_scores = out_values
gt_bboxes, gt_labels, gt_difficults = rest_values
result = eval_detection_voc(pred_bboxes,
pred_labels,
pred_scores,
gt_bboxes,
gt_labels,
gt_difficults,
use_07_metric=True)
print()
print('mAP: {:f}'.format(result['map']))
for l, name in enumerate(voc_bbox_label_names):
if result['ap'][l]:
print('{:s}: {:f}'.format(name, result['ap'][l]))
else:
print('{:s}: -'.format(name))
method = 'POST'
headers = {'Content-Type': 'application/json'}
dic = {}
response_body = {}
process_time = {}
yolo_input_size = 416
period_list = [
'cap_read', 'cv2_resize', 'image_encode', 'image_post', 'object_detection',
'bbox_draw', 'textbox_draw', 'text_put', 'cv2_imshow'
]
period_dict = {period: 0 for period in period_list}
period_dict['environment'] = 'local' if args.local_cpu else 'remote'
# https://github.com/chainer/chainercv/blob/master/chainercv/links/model/yolo/yolo_v3.py
# input image size = 416 x 416 pix
model = YOLOv3(pretrained_model='voc0712') if args.local_cpu else None
if args.local_gpu:
period_dict['environment'] = 'local_gpu'
model = YOLOv3(pretrained_model='voc0712')
chainer.backends.cuda.get_device_from_id(0)
model.to_gpu()
# capture video from web camera
cap = cv2.VideoCapture(0)
while (True):
# Capture frame-by-frame
event_number = int(time.time() * 1000000)
start_time = time.time()
ret, orig_frame = cap.read() # orig_frame.shape = (720, 1280, 3)
period_dict['cap_read'] = time.time() - start_time
def setUp(self):
self.link = YOLOv3(n_fg_class=self.n_fg_class)
self.insize = 416
self.n_bbox = (13 * 13 + 26 * 26 + 52 * 52) * 3
def test_pretrained_wrong_n_fg_class(self):
with self.assertRaises(ValueError):
YOLOv3(n_fg_class=10, pretrained_model='voc0712')
def predict_bbox(img):
chainer_img = trans_img_chainer(img)
model = YOLOv3(pretrained_model="voc0712")
bboxes, labels, scores = model.predict([chainer_img])
return bboxes, labels, scores
path = input(">>")
while not os.path.exists(path2):
print("Please type Output FilePath \n Default is C:\\DriveRecorder\\test")
path2 = input(">>")
if path2 == '':
path2 = r'C:\DriveRecorder\test'
break
flist = glob.glob(path + r"/*.JPG")
# model = FasterRCNNVGG16(n_fg_class=len(voc_bbox_label_names),
# pretrained_model="voc07")
model = YOLOv3(
n_fg_class=len(voc_bbox_label_names),
pretrained_model='voc0712')
chainer.cuda.get_device_from_id(0).use()
print("Runing on GPU")
model.to_gpu()
for f in tqdm(flist):
# start=time.time()
img = imread(f)
result = img.copy()
if img is None:
raise FileNotFoundError('FileNotFound::' + f)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
def main():
model_phase1 = YOLOv3(n_fg_class=len(voc_bbox_label_names),
pretrained_model='voc0712')
#pretrained_model='voc07')
chainer.cuda.get_device_from_id(0).use()
model_phase1.to_gpu()
accum_time = 0
curr_fps = 0
fps = "FPS: ??"
prev_time = timer()
frame_count = 1
while True:
fframes = pipeline.wait_for_frames()
color_frame = fframes.get_color_frame()
depth_frame = fframes.get_depth_frame()
frame = np.asanyarray(color_frame.get_data())
depth_image = np.asanyarray(depth_frame.get_data())
depth_colormap = cv2.applyColorMap(
cv2.convertScaleAbs(depth_image, alpha=0.03), cv2.COLORMAP_JET)
# BGR -> RGB
rgb = cv2.cvtColor(
cv2.resize(frame, (int(frame.shape[1] / LIGHTWEIGHT_COEF),
int(frame.shape[0] / LIGHTWEIGHT_COEF))),
cv2.COLOR_BGR2RGB)
result = frame.copy()
img = np.asarray(rgb, dtype=np.float32).transpose((2, 0, 1))
bboxes, labels, scores = model_phase1.predict([img])
bbox, label, score = bboxes[0], labels[0], scores[0]
if len(bbox) != 0:
for i, bb in enumerate(bbox):
lb = label[i]
if lb != 14:
continue
conf = score[i].tolist()
ymin = int(bb[0] * LIGHTWEIGHT_COEF)
xmin = int(bb[1] * LIGHTWEIGHT_COEF)
ymax = int(bb[2] * LIGHTWEIGHT_COEF)
xmax = int(bb[3] * LIGHTWEIGHT_COEF)
class_num = int(lb)
cv2.rectangle(
result, (xmin, ymin), (xmax, ymax),
voc_semantic_segmentation_label_colors[class_num], 5)
#cv2.rectangle(depth_colormap, (int(xmin * 2 / 3), int(ymin * 2 / 3)), (int(xmax * 2 / 3), int(ymax * 2 / 3)), voc_semantic_segmentation_label_colors[class_num], 5)
text = "person"
ftext = text
text_top = (xmin, ymin - 10)
text_bot = (xmin + 80, ymin + 5)
text_pos = (xmin + 5, ymin)
text_top1 = (int(text_top[0] * 2 / 3),
int(text_top[1] * 2 / 3))
text_bot1 = (int(text_bot[0] * 2 / 3),
int(text_bot[1] * 2 / 3))
text_pos1 = (int(text_pos[0] * 2 / 3),
int(text_pos[1] * 2 / 3))
# Draw label 1
cv2.rectangle(
result, text_top, text_bot,
voc_semantic_segmentation_label_colors[class_num], -1)
cv2.putText(result, ftext, text_pos, cv2.FONT_HERSHEY_SIMPLEX,
0.35, (0, 0, 0), 1)
#cv2.rectangle(depth_colormap, text_top1, text_bot1,
# voc_semantic_segmentation_label_colors[class_num], -1)
#cv2.putText(depth_colormap, ftext, text_pos1,
# cv2.FONT_HERSHEY_SIMPLEX, 0.35, (0, 0, 0), 1)
curr_time = timer()
exec_time = curr_time - prev_time
prev_time = curr_time
accum_time = accum_time + exec_time
curr_fps = curr_fps + 1
if accum_time > 1:
accum_time = accum_time - 1
fps = "FPS:" + str(curr_fps)
curr_fps = 0
#Draw FPS in top right corner
cv2.rectangle(result, (590, 0), (640, 17), (0, 0, 0), -1)
cv2.putText(result, fps, (595, 10), cv2.FONT_HERSHEY_SIMPLEX, 0.35,
(255, 255, 255), 1)
# Draw Frame Number
cv2.rectangle(result, (0, 0), (50, 17), (0, 0, 0), -1)
cv2.putText(result, str(frame_count), (0, 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.35, (255, 255, 255), 1)
#cv2.rectangle(depth_colormap, (590, 0), (640, 17), (0, 0, 0), -1)
#cv2.putText(depth_colormap, fps, (595, 10),
# cv2.FONT_HERSHEY_SIMPLEX, 0.35, (255, 255, 255), 1)
# Draw Frame Number
#cv2.rectangle(depth_colormap, (0, 0), (50, 17), (0, 0, 0), -1)
#cv2.putText(depth_colormap, str(frame_count), (0, 10),
# cv2.FONT_HERSHEY_SIMPLEX, 0.35, (255, 255, 255), 1)
# Output Result
cv2.imshow("Yolo Result", result)
#cv2.imshow("Realsense", depth_colormap)
# Stop Processing
if cv2.waitKey(1) & 0xFF == ord('q'):
break
frame_count += 1
cv2.destroyAllWindows()
def _set_model(self):
self.model = YOLOv3(
n_fg_class=len(voc_bbox_label_names),
pretrained_model='voc0712'
)
args = parser.parse_args()
period_list = ['image_decode', 'image_transform', 'object_detection', 'pack_result']
period_dict = {period: 0 for period in period_list}
#period_dict['environment'] = 'remote'
#dbfile = sqlite3.connect('speed_server.db')
#c = dbfile.cursor()
# Flaskクラスのインスタンスを作成
# __name__は現在のファイルのモジュール名
api = Flask(__name__)
# https://github.com/chainer/chainercv/blob/master/chainercv/links/model/yolo/yolo_v3.py
# input image size = 416 x 416 pix
model = YOLOv3(pretrained_model='voc0712')
if args.gpu:
chainer.backends.cuda.get_device_from_id(0)
model.to_gpu()
# POSTの実装
@api.route('/api/detection', methods=['POST'])
def post():
"""
model.predict([img])の出力例
bboxes: [array([[ 99.97439 , 4.5523834, 192.06816 , 134.67502 ],
[199.90709 , 143.38562 , 352.9582 , 195.82318 ],
[ 75.87911 , 204.2211 , 360.09158 , 426.09985 ],
[ 11.633713 , 264.68134 , 225.85754 , 356.1368 ],
[126.243256 , 429.72067 , 178.3947 , 447.91504 ]], dtype=float32)]
def test_pretrained(self):
YOLOv3(pretrained_model='voc0712')
def test_pretrained_n_fg_class(self):
YOLOv3(n_fg_class=20, pretrained_model='voc0712')
