def main():
parser = argparse.ArgumentParser()
parser.add_argument('--fn', default='assets/demo.jpg', type=str)
parser.add_argument('--output', default='output', type=str)
parser.add_argument('--inres', default='512,512', type=str)
args, _ = parser.parse_known_args()
args.inres = tuple(int(x) for x in args.inres.split(','))
os.makedirs(args.output, exist_ok=True)
kwargs = {
'num_stacks': 2,
'cnv_dim': 256,
'weights': 'hpdet_coco',
'inres': args.inres,
}
heads = {
'hm': 1, # 6
'hm_hp': 17, # 7
'hp_offset': 2, # 8
'hps': 34, # 9
'reg': 2, # 10
'wh': 2, # 11
}
model = HourglassNetwork(heads=heads, **kwargs)
model = HpDetDecode(model)
drawer = COCODrawer()
fns = sorted(glob(args.fn))
for fn in tqdm(fns):
img = cv2.imread(fn)
letterbox_transformer = LetterboxTransformer(args.inres[0],
args.inres[1])
pimg = letterbox_transformer(img)
pimg = normalize_image(pimg)
pimg = np.expand_dims(pimg, 0)
detections = model.predict(pimg)[0]
for d in detections:
score, cl = d[4], d[-1]
if score < 0.3:
break
x1, y1, x2, y2 = d[:4]
kps = d[5:-1]
kps_x = kps[:17]
kps_y = kps[17:]
kps = letterbox_transformer.correct_coords(
np.vstack([kps_x, kps_y])).T
x1, y1, x2, y2 = letterbox_transformer.correct_box(x1, y1, x2, y2)
img = drawer.draw_pose(img, kps)
img = drawer.draw_box(img, x1, y1, x2, y2, cl)
out_fn = os.path.join(args.output, 'hpdet.' + os.path.basename(fn))
cv2.imwrite(out_fn, img)
print("Image saved to: %s" % out_fn)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--fn', default='assets/demo.jpg', type=str)
parser.add_argument('--output', default='output', type=str)
parser.add_argument('--inres', default='512,512', type=str)
args, _ = parser.parse_known_args()
args.inres = tuple(int(x) for x in args.inres.split(','))
os.makedirs(args.output, exist_ok=True)
kwargs = {
'num_stacks': 2,
'cnv_dim': 256,
'weights': 'ctdet_coco',
'inres': args.inres,
}
heads = {
'hm': 80, # 3
'reg': 2, # 4
'wh': 2 # 5
}
model = HourglassNetwork(heads=heads, **kwargs)
model = CtDetDecode(model)
drawer = COCODrawer()
fns = sorted(glob(args.fn))
print(fns)
for fn in tqdm(fns):
img = cv2.imread(fn)
# cv2.imshow(img)
letterbox_transformer = LetterboxTransformer(args.inres[0], args.inres[1])
pimg = letterbox_transformer(img)
pimg = normalize_image(pimg)
pimg = np.expand_dims(pimg, 0)
detections = model.predict(pimg)[0]
for d in detections:
x1, y1, x2, y2, score, cl = d
if score < 0.3:
break
x1, y1, x2, y2 = letterbox_transformer.correct_box(x1, y1, x2, y2)
img = drawer.draw_box(img, x1, y1, x2, y2, cl)
out_fn = os.path.join(args.output, 'ctdet.' + os.path.basename(fn))
cv2.imwrite(out_fn, img)
print("Image saved to: %s" % out_fn)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--output', default='output', type=str)
parser.add_argument('--data', default='val2017', type=str)
parser.add_argument('--annotations', default='annotations', type=str)
parser.add_argument('--inres', default='512,512', type=str)
parser.add_argument('--no-full-resolution', action='store_true')
args, _ = parser.parse_known_args()
args.inres = tuple(int(x) for x in args.inres.split(','))
if not args.no_full_resolution:
args.inres = (None, None)
os.makedirs(args.output, exist_ok=True)
kwargs = {
'num_stacks': 2,
'cnv_dim': 256,
'weights': 'hpdet_coco',
'inres': args.inres,
}
heads = {
'hm': 1, # 6
'hm_hp': 17, # 7
'hp_offset': 2, # 8
'hps': 34, # 9
'reg': 2, # 10
'wh': 2, # 11
}
out_fn_keypoints = os.path.join(
args.output, args.data + '_keypoints_results_%s_%s.json' %
(args.inres[0], args.inres[1]))
model = HourglassNetwork(heads=heads, **kwargs)
model = HpDetDecode(model)
if args.no_full_resolution:
letterbox_transformer = LetterboxTransformer(args.inres[0],
args.inres[1])
else:
letterbox_transformer = LetterboxTransformer(mode='testing',
max_stride=128)
fns = sorted(glob(os.path.join(args.data, '*.jpg')))
results = []
for fn in tqdm(fns):
img = cv2.imread(fn)
image_id = int(os.path.splitext(os.path.basename(fn))[0])
pimg = letterbox_transformer(img)
pimg = normalize_image(pimg)
pimg = np.expand_dims(pimg, 0)
detections = model.predict(pimg)[0]
for d in detections:
score = d[4]
x1, y1, x2, y2 = d[:4]
x1, y1, x2, y2 = letterbox_transformer.correct_box(x1, y1, x2, y2)
x1, y1, x2, y2 = float(x1), float(y1), float(x2), float(y2)
kps = d[5:-1]
kps_x = kps[:17]
kps_y = kps[17:]
kps = letterbox_transformer.correct_coords(
np.vstack([kps_x, kps_y])).T
# add z = 1
kps = np.concatenate([kps, np.ones((17, 1), dtype='float32')], -1)
kps = list(map(float, kps.flatten()))
image_result = {
'image_id': image_id,
'category_id': 1,
'score': float(score),
'bbox': [x1, y1, (x2 - x1), (y2 - y1)],
'keypoints': kps,
}
results.append(image_result)
if not len(results):
print("No predictions were generated.")
return
# write output
with open(out_fn_keypoints, 'w') as f:
json.dump(results, f, indent=2)
print("Predictions saved to: %s" % out_fn_keypoints)
# load results in COCO evaluation tool
gt_fn = os.path.join(args.annotations,
'person_keypoints_%s.json' % args.data)
print("Loading GT: %s" % gt_fn)
coco_true = COCO(gt_fn)
coco_pred = coco_true.loadRes(out_fn_keypoints)
coco_eval = COCOeval(coco_true, coco_pred, 'keypoints')
coco_eval.evaluate()
coco_eval.accumulate()
coco_eval.summarize()
return coco_eval.stats
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--video', default='webcam', type=str)
parser.add_argument('--output', default='output', type=str)
parser.add_argument('--inres', default='512,512', type=str)
parser.add_argument('--outres', default='1080,1920', type=str)
parser.add_argument('--max-frames', default=1000000, type=int)
parser.add_argument('--fps', default=25.0 * 1.0, type=float)
args, _ = parser.parse_known_args()
args.inres = tuple(int(x) for x in args.inres.split(','))
args.outres = tuple(int(x) for x in args.outres.split(','))
os.makedirs(args.output, exist_ok=True)
kwargs = {
'num_stacks': 2,
'cnv_dim': 256,
'weights': 'hpdet_coco',
'inres': args.inres,
}
heads = {
'hm': 1, # 6
'hm_hp': 17, # 7
'hp_offset': 2, # 8
'hps': 34, # 9
'reg': 2, # 10
'wh': 2, # 11
}
model = HourglassNetwork(heads=heads, **kwargs)
model = HpDetDecode(model)
drawer = COCODrawer()
letterbox_transformer = LetterboxTransformer(args.inres[0], args.inres[1])
cap = cv2.VideoCapture(0 if args.video == 'webcam' else args.video)
out_fn = os.path.join(args.output,
'hpdet.' + os.path.basename(args.video)).replace(
'.mp4', '.avi')
fourcc = cv2.VideoWriter_fourcc(*'XVID')
out = cv2.VideoWriter(out_fn, fourcc, args.fps, args.outres[::-1])
k = 0
tic = time.time()
while cap.isOpened():
if k > args.max_frames:
print("Bye")
break
if k > 0 and k % 100 == 0:
toc = time.time()
duration = toc - tic
print("[%05d]: %.3f seconds / 100 iterations" % (k, duration))
tic = toc
k += 1
ret, img = cap.read()
if not ret:
print("Done")
break
pimg = letterbox_transformer(img)
pimg = normalize_image(pimg)
pimg = np.expand_dims(pimg, 0)
detections = model.predict(pimg)[0]
for d in detections:
score, cl = d[4], d[-1]
if score < 0.3:
break
x1, y1, x2, y2 = d[:4]
kps = d[5:-1]
kps_x = kps[:17]
kps_y = kps[17:]
kps = letterbox_transformer.correct_coords(
np.vstack([kps_x, kps_y])).T
x1, y1, x2, y2 = letterbox_transformer.correct_box(x1, y1, x2, y2)
img = drawer.draw_pose(img, kps)
img = drawer.draw_box(img, x1, y1, x2, y2, cl)
out.write(img)
print("Video saved to: %s" % out_fn)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--output', default='output', type=str)
parser.add_argument('--data', default='val2017', type=str)
parser.add_argument('--annotations', default='annotations', type=str)
parser.add_argument('--inres', default='512,512', type=str)
parser.add_argument('--no-full-resolution', action='store_true')
args, _ = parser.parse_known_args()
args.inres = tuple(int(x) for x in args.inres.split(','))
if not args.no_full_resolution:
args.inres = (None, None)
os.makedirs(args.output, exist_ok=True)
kwargs = {
'num_stacks': 2,
'cnv_dim': 256,
'weights': 'ctdet_coco',
'inres': args.inres,
}
heads = {'hm': 80, 'reg': 2, 'wh': 2}
out_fn_box = os.path.join(
args.output, args.data + '_bbox_results_%s_%s.json' %
(args.inres[0], args.inres[1]))
model = HourglassNetwork(heads=heads, **kwargs)
model = CtDetDecode(model)
if args.no_full_resolution:
letterbox_transformer = LetterboxTransformer(args.inres[0],
args.inres[1])
else:
letterbox_transformer = LetterboxTransformer(mode='testing',
max_stride=128)
fns = sorted(glob(os.path.join(args.data, '*.jpg')))
results = []
for fn in tqdm(fns):
img = cv2.imread(fn)
image_id = int(os.path.splitext(os.path.basename(fn))[0])
pimg = letterbox_transformer(img)
pimg = normalize_image(pimg)
pimg = np.expand_dims(pimg, 0)
detections = model.predict(pimg)[0]
for d in detections:
x1, y1, x2, y2, score, cl = d
# if score < 0.001:
# break
x1, y1, x2, y2 = letterbox_transformer.correct_box(x1, y1, x2, y2)
cl = int(cl)
x1, y1, x2, y2 = float(x1), float(y1), float(x2), float(y2)
image_result = {
'image_id': image_id,
'category_id': COCO_IDS[cl + 1],
'score': float(score),
'bbox': [x1, y1, (x2 - x1), (y2 - y1)],
}
results.append(image_result)
if not len(results):
print("No predictions were generated.")
return
# write output
with open(out_fn_box, 'w') as f:
json.dump(results, f, indent=2)
print("Predictions saved to: %s" % out_fn_box)
# load results in COCO evaluation tool
gt_fn = os.path.join(args.annotations, 'instances_%s.json' % args.data)
print("Loading GT: %s" % gt_fn)
coco_true = COCO(gt_fn)
coco_pred = coco_true.loadRes(out_fn_box)
# run COCO evaluation
coco_eval = COCOeval(coco_true, coco_pred, 'bbox')
coco_eval.evaluate()
coco_eval.accumulate()
coco_eval.summarize()
return coco_eval.stats