def Infer(img_name, mod):
system_dict["image"] = img_name
if system_dict["gpu"]:
ctx = mx.gpu(int(system_dict["gpu"]))
else:
ctx = mx.cpu(0)
# load single test
im_tensor, im_info, im_orig = load_test(
system_dict["image"],
short=system_dict["img_short_side"],
max_size=system_dict["img_long_side"],
mean=system_dict["img_pixel_means"],
std=system_dict["img_pixel_stds"])
# generate data batch
data_batch = generate_batch(im_tensor, im_info)
# forward
mod.forward(data_batch)
rois, scores, bbox_deltas = mod.get_outputs()
rois = rois[:, 1:]
scores = scores[0]
bbox_deltas = bbox_deltas[0]
im_info = im_info[0]
# decode detection
det = im_detect(rois,
scores,
bbox_deltas,
im_info,
bbox_stds=system_dict["rcnn_bbox_stds"],
nms_thresh=system_dict["rcnn_nms_thresh"],
conf_thresh=system_dict["rcnn_conf_thresh"])
output = []
conf_scores = []
for [cls, conf, x1, y1, x2, y2] in det:
output.append(
[system_dict["classes"][int(cls)], conf, [x1, y1, x2, y2]])
conf_scores.append(conf)
if cls > 0 and conf > system_dict["vis_thresh"]:
print(system_dict["classes"][int(cls)], conf, [x1, y1, x2, y2])
max_index = conf_scores.index(max(conf_scores))
print(output[max_index])
if system_dict["vis"]:
vis_detection(im_orig,
det,
system_dict["classes"],
thresh=system_dict["vis_thresh"])
save_detection(im_orig,
det,
system_dict["classes"],
thresh=system_dict["vis_thresh"])
return output
def demo_net(sym, class_names, args):
# print config
print('called with args\n{}'.format(pprint.pformat(vars(args))))
# setup context
if args.gpu:
ctx = mx.gpu(int(args.gpu))
else:
ctx = mx.cpu(0)
# load single test
im_tensor, im_info, im_orig = load_test(args.image, short=args.img_short_side, max_size=args.img_long_side,
mean=args.img_pixel_means, std=args.img_pixel_stds)
# generate data batch
data_batch = generate_batch(im_tensor, im_info)
# load params
arg_params, aux_params = load_param(args.params, ctx=ctx)
# produce shape max possible
data_names = ['data', 'im_info']
label_names = None
data_shapes = [('data', (1, 3, args.img_long_side, args.img_long_side)), ('im_info', (1, 3))]
label_shapes = None
# check shapes
check_shape(sym, data_shapes, arg_params, aux_params)
# create and bind module
mod = Module(sym, data_names, label_names, context=ctx)
mod.bind(data_shapes, label_shapes, for_training=False)
mod.init_params(arg_params=arg_params, aux_params=aux_params)
# forward
mod.forward(data_batch)
rois, scores, bbox_deltas = mod.get_outputs()
rois = rois[:, 1:]
scores = scores[0]
bbox_deltas = bbox_deltas[0]
im_info = im_info[0]
# decode detection
det = im_detect(rois, scores, bbox_deltas, im_info,
bbox_stds=args.rcnn_bbox_stds, nms_thresh=args.rcnn_nms_thresh,
conf_thresh=args.rcnn_conf_thresh)
# print out
for [cls, conf, x1, y1, x2, y2] in det:
if cls > 0 and conf > args.vis_thresh:
print(class_names[int(cls)], conf, [x1, y1, x2, y2])
# if vis
if args.vis:
vis_detection(im_orig, det, class_names, thresh=args.vis_thresh)
def demo_net(sym, class_names, args):
# print config
print('called with args\n{}'.format(pprint.pformat(vars(args))))
# setup context
if args.gpu:
ctx = mx.gpu(int(args.gpu))
else:
ctx = mx.cpu(0)
# load single test
im_tensor, im_info, im_orig = load_test(args.image,
short=args.img_short_side,
max_size=args.img_long_side,
mean=args.img_pixel_means,
std=args.img_pixel_stds)
# generate data batch
data_batch = generate_batch(im_tensor, im_info)
# load params
arg_params, aux_params = load_param(args.params, ctx=ctx)
# produce shape max possible
data_names = ['data', 'im_info']
label_names = None
data_shapes = [('data', (1, 3, args.img_long_side, args.img_long_side)),
('im_info', (1, 3))]
label_shapes = None
# check shapes
check_shape(sym, data_shapes, arg_params, aux_params)
# create and bind module
mod = Module(sym, data_names, label_names, context=ctx)
mod.bind(data_shapes, label_shapes, for_training=False)
mod.init_params(arg_params=arg_params, aux_params=aux_params)
# forward
mod.forward(data_batch)
rois, scores, bbox_deltas = mod.get_outputs()
rois = rois[:, 1:]
scores = scores[0]
bbox_deltas = bbox_deltas[0]
im_info = im_info[0]
# decode detection
det = im_detect(rois,
scores,
bbox_deltas,
im_info,
bbox_stds=args.rcnn_bbox_stds,
nms_thresh=args.rcnn_nms_thresh,
conf_thresh=args.rcnn_conf_thresh,
use_soft_nms=args.use_soft_nms,
soft_nms_thresh=args.soft_nms_thresh,
max_per_image=args.max_per_image)
# print out
for [cls, conf, x1, y1, x2, y2] in det:
if cls > 0 and conf > args.vis_thresh:
print(class_names[int(cls)], conf, [x1, y1, x2, y2])
# if vis
if args.vis:
vis_detection(im_orig, det, class_names, thresh=args.vis_thresh)
def Infer(img_name, mod):
'''
User function: Run inference on image and visualize it
Args:
img_name (str): Relative path to the image file
mod (mxnet model): Mxnet model returned from load_model() function
Returns:
list: Contaning IDs, Scores and bounding box locations of predicted objects.
'''
system_dict["image"] = img_name
if system_dict["gpu"]:
ctx = mx.gpu(int(system_dict["gpu"]))
else:
ctx = mx.cpu(0)
# load single test
im_tensor, im_info, im_orig = load_test(
system_dict["image"],
short=system_dict["img_short_side"],
max_size=system_dict["img_long_side"],
mean=system_dict["img_pixel_means"],
std=system_dict["img_pixel_stds"])
# generate data batch
data_batch = generate_batch(im_tensor, im_info)
# forward
mod.forward(data_batch)
rois, scores, bbox_deltas = mod.get_outputs()
rois = rois[:, 1:]
scores = scores[0]
bbox_deltas = bbox_deltas[0]
im_info = im_info[0]
# decode detection
det = im_detect(rois,
scores,
bbox_deltas,
im_info,
bbox_stds=system_dict["rcnn_bbox_stds"],
nms_thresh=system_dict["rcnn_nms_thresh"],
conf_thresh=system_dict["rcnn_conf_thresh"])
output = []
conf_scores = []
for [cls, conf, x1, y1, x2, y2] in det:
output.append(
[system_dict["classes"][int(cls)], conf, [x1, y1, x2, y2]])
conf_scores.append(conf)
if cls > 0 and conf > system_dict["vis_thresh"]:
print(system_dict["classes"][int(cls)], conf, [x1, y1, x2, y2])
max_index = conf_scores.index(max(conf_scores))
print(output[max_index])
if system_dict["vis"]:
vis_detection(im_orig,
det,
system_dict["classes"],
thresh=system_dict["vis_thresh"])
save_detection(im_orig,
det,
system_dict["classes"],
thresh=system_dict["vis_thresh"])
return output
def demo_net(sym, class_names, args):
# print config
# setup context
if args.gpu:
ctx = mx.gpu(int(args.gpu))
else:
ctx = mx.cpu(0)
print('called with args\n{}'.format(pprint.pformat(vars(args))))
# load params
arg_params, aux_params = load_param(args.params, ctx=ctx)
# produce shape max possible
data_names = ['data', 'im_info']
label_names = None
data_shapes = [('data', (1, 3, args.img_long_side, args.img_long_side)),
('im_info', (1, 3))]
label_shapes = None
# check shapes
check_shape(sym, data_shapes, arg_params, aux_params)
# create and bind module
mod = Module(sym, data_names, label_names, context=ctx)
mod.bind(data_shapes, label_shapes, for_training=False)
mod.init_params(arg_params=arg_params, aux_params=aux_params)
f = open(
"/home/skutukov/datasets/VOCdevkit/VOC2007/ImageSets/Main/test.txt",
"r")
for file in tqdm.tqdm(f.readlines()):
path = os.path.join(args.image, str(file).strip() + '.jpg')
path = '/home/skutukov/Pictures/demo.jpg'
# load single test
im_tensor, im_info, im_orig = load_test(path,
short=args.img_short_side,
max_size=args.img_long_side,
mean=args.img_pixel_means,
std=args.img_pixel_stds,
ctx=ctx)
# generate data batch
data_batch = generate_batch(im_tensor, im_info)
# forward
mod.forward(data_batch)
rois, scores, bbox_deltas = mod.get_outputs()
rois = rois[:, 1:]
scores = scores[0]
bbox_deltas = bbox_deltas[0]
im_info = im_info[0]
# decode detection
det = im_detect(rois,
scores,
bbox_deltas,
im_info,
bbox_stds=args.rcnn_bbox_stds,
nms_thresh=args.rcnn_nms_thresh,
conf_thresh=args.rcnn_conf_thresh)
# print out
for [cls, conf, x1, y1, x2, y2] in det:
if cls > 0 and conf > args.vis_thresh:
print(class_names[int(cls)], conf, [x1, y1, x2, y2])
# if vis
if args.vis:
vis_detection(im_orig,
det,
class_names,
thresh=args.vis_thresh,
file=file)
break
def demo_net(sym, class_names, args):
# print config
print('called with args\n{}'.format(pprint.pformat(vars(args))))
# setup context
if args.gpu:
ctx = mx.gpu(int(args.gpu))
else:
ctx = mx.cpu(0)
# load single test
im_tensor, im_info, im_orig = load_test(args.image,
short=args.img_short_side,
max_size=args.img_long_side,
mean=args.img_pixel_means,
std=args.img_pixel_stds)
# generate data batch
data_batch = generate_batch(im_tensor, im_info)
# load params
arg_params, aux_params = load_param(args.params, ctx=ctx)
# produce shape max possible
data_names = ['data', 'im_info']
label_names = None
data_shapes = [('data', (1, 3, args.img_long_side, args.img_long_side)),
('im_info', (1, 3))]
label_shapes = None
# check shapes
check_shape(sym, data_shapes, arg_params, aux_params)
# create and bind module
mod = Module(sym, data_names, label_names, context=ctx)
mod.bind(data_shapes, label_shapes, for_training=False)
mod.init_params(arg_params=arg_params, aux_params=aux_params)
# forward
mod.forward(data_batch)
rois, scores, bbox_deltas, mask_prob = mod.get_outputs()
rois = rois[:, 1:]
scores = scores[0]
bbox_deltas = bbox_deltas[0]
im_info = im_info[0]
# decode detection
det, masks = im_detect(rois,
scores,
bbox_deltas,
mask_prob,
im_info,
bbox_stds=args.rcnn_bbox_stds,
nms_thresh=args.rcnn_nms_thresh,
conf_thresh=args.rcnn_conf_thresh)
im = cv2.imread(args.image)
print(im.shape)
print(im_info)
# print out
for index, [cls, conf, x1, y1, x2, y2] in enumerate(det):
print(masks[index].max())
if cls > 0 and conf > args.vis_thresh:
print(class_names[int(cls)], conf, [x1, y1, x2, y2])
print((int(x1), int(y1)), (int(x2), int(y2)))
cv2.rectangle(im, (int(x1), int(y1)), (int(x2), int(y2)),
(255, 0, 0), 10)
cv2.imwrite("mask{}.png".format(index),
np.uint8(masks[index] * 255))
cv2.imwrite('demo.png', im)
# if vis
if args.vis:
vis_detection(im_orig, det, class_names, thresh=args.vis_thresh)