def main(_):
with tf.Graph().as_default():
out_shape = [FLAGS.train_image_size] * 2
image_input = tf.placeholder(tf.uint8, shape=(None, None, 3))
shape_input = tf.placeholder(tf.int32, shape=(2, ))
features = ssd_preprocessing.preprocess_for_eval(
image_input,
out_shape,
data_format=FLAGS.data_format,
output_rgb=False)
features = tf.expand_dims(features, axis=0)
anchor_creator = anchor_manipulator.AnchorCreator(
out_shape,
layers_shapes=[(38, 38), (19, 19), (10, 10), (5, 5), (3, 3),
(1, 1)],
anchor_scales=[(0.1, ), (0.2, ), (0.375, ), (0.55, ), (0.725, ),
(0.9, )],
extra_anchor_scales=[(0.1414, ), (0.2739, ), (0.4541, ),
(0.6315, ), (0.8078, ), (0.9836, )],
anchor_ratios=[(2., .5),
(2., 3., .5, 0.3333), (2., 3., .5, 0.3333),
(2., 3., .5, 0.3333), (2., .5), (2., .5)],
layer_steps=[8, 16, 32, 64, 100, 300])
all_anchors, all_num_anchors_depth, all_num_anchors_spatial = anchor_creator.get_all_anchors(
)
anchor_encoder_decoder = anchor_manipulator.AnchorEncoder(
allowed_borders=[1.0] * 6,
positive_threshold=None,
ignore_threshold=None,
prior_scaling=[0.1, 0.1, 0.2, 0.2])
decode_fn = lambda pred: anchor_encoder_decoder.ext_decode_all_anchors(
pred, all_anchors, all_num_anchors_depth, all_num_anchors_spatial)
with tf.variable_scope(FLAGS.model_scope,
default_name=None,
values=[features],
reuse=tf.AUTO_REUSE):
backbone = ssd_net.VGG16Backbone(FLAGS.data_format)
feature_layers = backbone.forward(features, training=False)
location_pred, cls_pred = ssd_net.multibox_head(
feature_layers,
FLAGS.num_classes,
all_num_anchors_depth,
data_format=FLAGS.data_format)
if FLAGS.data_format == 'channels_first':
cls_pred = [
tf.transpose(pred, [0, 2, 3, 1]) for pred in cls_pred
]
location_pred = [
tf.transpose(pred, [0, 2, 3, 1]) for pred in location_pred
]
cls_pred = [
tf.reshape(pred, [-1, FLAGS.num_classes]) for pred in cls_pred
]
location_pred = [
tf.reshape(pred, [-1, 4]) for pred in location_pred
]
cls_pred = tf.concat(cls_pred, axis=0)
location_pred = tf.concat(location_pred, axis=0)
with tf.device('/cpu:0'):
bboxes_pred = decode_fn(location_pred)
bboxes_pred = tf.concat(bboxes_pred, axis=0)
selected_bboxes, selected_scores = parse_by_class(
cls_pred, bboxes_pred, FLAGS.num_classes,
FLAGS.select_threshold, FLAGS.min_size, FLAGS.keep_topk,
FLAGS.nms_topk, FLAGS.nms_threshold)
labels_list = []
scores_list = []
bboxes_list = []
for k, v in selected_scores.items():
labels_list.append(tf.ones_like(v, tf.int32) * k)
scores_list.append(v)
bboxes_list.append(selected_bboxes[k])
all_labels = tf.concat(labels_list, axis=0)
all_scores = tf.concat(scores_list, axis=0)
all_bboxes = tf.concat(bboxes_list, axis=0)
saver = tf.train.Saver()
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
saver.restore(sess, get_checkpoint())
np_image = imread('./demo/test.jpg')
labels_, scores_, bboxes_ = sess.run(
[all_labels, all_scores, all_bboxes],
feed_dict={
image_input: np_image,
shape_input: np_image.shape[:-1]
})
img_to_draw = draw_toolbox.bboxes_draw_on_img(np_image,
labels_,
scores_,
bboxes_,
thickness=2)
imsave('./demo/test_out.jpg', img_to_draw)
def main(_):
with tf.Graph().as_default():
out_shape = [FLAGS.train_image_size] * 2
with tf.name_scope('define_input'):
image_input = tf.placeholder(tf.uint8,
shape=(None, None, 3),
name='image_input')
features = ssd_preprocessing.preprocess_for_eval(
image_input,
out_shape,
data_format=FLAGS.data_format,
output_rgb=False)
features = tf.expand_dims(features, axis=0)
anchor_creator = anchor_manipulator.AnchorCreator(
out_shape,
layers_shapes=[(38, 38), (19, 19), (10, 10), (5, 5), (3, 3),
(1, 1)],
anchor_scales=[(0.1, ), (0.2, ), (0.375, ), (0.55, ), (0.725, ),
(0.9, )],
extra_anchor_scales=[(0.1414, ), (0.2739, ), (0.4541, ),
(0.6315, ), (0.8078, ), (0.9836, )],
anchor_ratios=[(1., 2., .5), (1., 2., 3., .5, 0.3333),
(1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333),
(1., 2., .5), (1., 2., .5)],
#anchor_ratios = [(2., .5), (2., 3., .5, 0.3333), (2., 3., .5, 0.3333),
#(2., 3., .5, 0.3333), (2., .5), (2., .5)],
layer_steps=[8, 16, 32, 64, 100, 300])
all_anchors, all_num_anchors_depth, all_num_anchors_spatial = anchor_creator.get_all_anchors(
)
anchor_encoder_decoder = anchor_manipulator.AnchorEncoder(
allowed_borders=[1.0] * 6,
positive_threshold=None,
ignore_threshold=None,
prior_scaling=[0.1, 0.1, 0.2, 0.2])
def decode_fn(pred):
return anchor_encoder_decoder.ext_decode_all_anchors(
pred, all_anchors, all_num_anchors_depth,
all_num_anchors_spatial)
with tf.variable_scope(FLAGS.model_scope,
default_name=None,
values=[features],
reuse=tf.AUTO_REUSE):
backbone = ssd_net.VGG16Backbone(FLAGS.data_format)
feature_layers = backbone.forward(features, training=False)
location_pred, cls_pred = ssd_net.multibox_head(
feature_layers,
FLAGS.num_classes,
all_num_anchors_depth,
data_format=FLAGS.data_format)
if FLAGS.data_format == 'channels_first':
cls_pred = [
tf.transpose(pred, [0, 2, 3, 1]) for pred in cls_pred
]
location_pred = [
tf.transpose(pred, [0, 2, 3, 1]) for pred in location_pred
]
cls_pred = [
tf.reshape(pred, [-1, FLAGS.num_classes]) for pred in cls_pred
]
location_pred = [
tf.reshape(pred, [-1, 4]) for pred in location_pred
]
with tf.variable_scope('cls_pred'):
cls_pred = tf.concat(cls_pred, axis=0)
with tf.variable_scope('location_pred'):
location_pred = tf.concat(location_pred, axis=0)
with tf.device('/cpu:0'):
bboxes_pred = decode_fn(location_pred)
bboxes_pred = tf.concat(bboxes_pred, axis=0)
selected_bboxes, selected_scores = parse_by_class(
cls_pred, bboxes_pred, FLAGS.num_classes,
FLAGS.select_threshold, FLAGS.min_size, FLAGS.keep_topk,
FLAGS.nms_topk, FLAGS.nms_threshold)
labels_list = []
scores_list = []
bboxes_list = []
for k, v in selected_scores.items():
labels_list.append(tf.ones_like(v, tf.int32) * k)
scores_list.append(v)
bboxes_list.append(selected_bboxes[k])
all_labels = tf.concat(labels_list, axis=0)
all_scores = tf.concat(scores_list, axis=0)
all_bboxes = tf.concat(bboxes_list, axis=0)
saver = tf.train.Saver()
'''
config = tf.ConfigProto(allow_soft_placement=True, inter_op_parallelism_threads=1, intra_op_parallelism_threads=1)
config.mlu_options.data_parallelism = 1
config.mlu_options.model_parallelism = 1
config.mlu_options.core_num = 1
config.mlu_options.core_version = 'MLU270'
config.mlu_options.precision = 'float'
with tf.Session(config = config) as sess:
'''
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
saver.restore(sess, get_checkpoint())
np_image = imread('demo/test.jpg')
labels_, scores_, bboxes_ = sess.run(
[all_labels, all_scores, all_bboxes],
feed_dict={image_input: np_image})
#print('labels_', labels_, type(labels_), labels_.shape)
#print('scores_', scores_, type(scores_), scores_.shape)
#print('bboxes_', bboxes_, type(bboxes_), bboxes_.shape, bboxes_.shape[0])
img_to_draw = draw_toolbox.bboxes_draw_on_img(np_image,
labels_,
scores_,
bboxes_,
thickness=2)
imsave('demo/test_out.jpg', img_to_draw)
saver.save(sess, 'model/ssd300_vgg16/ssd300_vgg16', global_step=0)
def main(_):
with tf.Graph().as_default():
out_shape = [FLAGS.train_image_size] * 2
image_input = tf.placeholder(tf.uint8, shape=(None, None, 3))
shape_input = tf.placeholder(tf.int32, shape=(2, ))
features, output_shape = ssd_preprocessing.preprocess_for_eval(
image_input,
out_shape,
data_format=FLAGS.data_format,
output_rgb=False)
features = tf.expand_dims(features, axis=0)
output_shape = tf.expand_dims(output_shape, axis=0)
all_anchor_scales = [(30., ), (60., ), (112.5, ), (165., ), (217.5, ),
(270., )]
all_extra_scales = [(42.43, ), (82.17, ), (136.23, ), (189.45, ),
(242.34, ), (295.08, )]
all_anchor_ratios = [(1., 2., .5), (1., 2., 3., .5, 0.3333),
(1., 2., 3., .5, 0.3333),
(1., 2., 3., .5, 0.3333), (1., 2., .5),
(1., 2., .5)]
# all_anchor_ratios = [(2., .5), (2., 3., .5, 0.3333), (2., 3., .5, 0.3333), (2., 3., .5, 0.3333), (2., .5), (2., .5)]
with tf.variable_scope(FLAGS.model_scope,
default_name=None,
values=[features],
reuse=tf.AUTO_REUSE):
backbone = ssd_net.VGG16Backbone(FLAGS.data_format)
feature_layers = backbone.forward(features, training=False)
with tf.device('/cpu:0'):
anchor_encoder_decoder = anchor_manipulator.AnchorEncoder(
positive_threshold=None,
ignore_threshold=None,
prior_scaling=[0.1, 0.1, 0.2, 0.2])
if FLAGS.data_format == 'channels_first':
all_layer_shapes = [
tf.shape(feat)[2:] for feat in feature_layers
]
else:
all_layer_shapes = [
tf.shape(feat)[1:3] for feat in feature_layers
]
all_layer_strides = [8, 16, 32, 64, 100, 300]
total_layers = len(all_layer_shapes)
anchors_height = list()
anchors_width = list()
anchors_depth = list()
for ind in range(total_layers):
_anchors_height, _anchors_width, _anchor_depth = anchor_encoder_decoder.get_anchors_width_height(
all_anchor_scales[ind],
all_extra_scales[ind],
all_anchor_ratios[ind],
name='get_anchors_width_height{}'.format(ind))
anchors_height.append(_anchors_height)
anchors_width.append(_anchors_width)
anchors_depth.append(_anchor_depth)
anchors_ymin, anchors_xmin, anchors_ymax, anchors_xmax, _ = anchor_encoder_decoder.get_all_anchors(
tf.squeeze(output_shape, axis=0), anchors_height,
anchors_width, anchors_depth, [0.5] * total_layers,
all_layer_shapes, all_layer_strides, [0.] * total_layers,
[False] * total_layers)
location_pred, cls_pred = ssd_net.multibox_head(
feature_layers,
FLAGS.num_classes,
anchors_depth,
data_format=FLAGS.data_format)
if FLAGS.data_format == 'channels_first':
cls_pred = [
tf.transpose(pred, [0, 2, 3, 1]) for pred in cls_pred
]
location_pred = [
tf.transpose(pred, [0, 2, 3, 1]) for pred in location_pred
]
cls_pred = [
tf.reshape(pred, [-1, FLAGS.num_classes]) for pred in cls_pred
]
location_pred = [
tf.reshape(pred, [-1, 4]) for pred in location_pred
]
cls_pred = tf.concat(cls_pred, axis=0)
location_pred = tf.concat(location_pred, axis=0)
with tf.device('/cpu:0'):
bboxes_pred = anchor_encoder_decoder.decode_anchors(
location_pred, anchors_ymin, anchors_xmin, anchors_ymax,
anchors_xmax)
selected_bboxes, selected_scores = bbox_util.parse_by_class(
tf.squeeze(output_shape, axis=0), cls_pred, bboxes_pred,
FLAGS.num_classes, FLAGS.select_threshold, FLAGS.min_size,
FLAGS.keep_topk, FLAGS.nms_topk, FLAGS.nms_threshold)
labels_list = []
scores_list = []
bboxes_list = []
for k, v in selected_scores.items():
labels_list.append(tf.ones_like(v, tf.int32) * k)
scores_list.append(v)
bboxes_list.append(selected_bboxes[k])
all_labels = tf.concat(labels_list, axis=0)
all_scores = tf.concat(scores_list, axis=0)
all_bboxes = tf.concat(bboxes_list, axis=0)
saver = tf.train.Saver()
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
saver.restore(sess, get_checkpoint())
np_image = imread('./demo/test.jpg')
labels_, scores_, bboxes_, output_shape_ = sess.run(
[all_labels, all_scores, all_bboxes, output_shape],
feed_dict={
image_input: np_image,
shape_input: np_image.shape[:-1]
})
bboxes_[:,
0] = bboxes_[:, 0] * np_image.shape[0] / output_shape_[0,
0]
bboxes_[:,
1] = bboxes_[:, 1] * np_image.shape[1] / output_shape_[0,
1]
bboxes_[:,
2] = bboxes_[:, 2] * np_image.shape[0] / output_shape_[0,
0]
bboxes_[:,
3] = bboxes_[:, 3] * np_image.shape[1] / output_shape_[0,
1]
img_to_draw = draw_toolbox.bboxes_draw_on_img(np_image,
labels_,
scores_,
bboxes_,
thickness=2)
imsave('./demo/test_out.jpg', img_to_draw)
def ssd(path):
# def ssd_res(img_path):
with tf.Graph().as_default():
out_shape = [FLAGS.train_image_size] * 2
image_input = tf.placeholder(tf.uint8, shape=(None, None, 3))
shape_input = tf.placeholder(tf.int32, shape=(2,))
features = ssd_preprocessing.preprocess_for_eval(image_input, out_shape, data_format=FLAGS.data_format, output_rgb=False)
features = tf.expand_dims(features, axis=0)
anchor_creator = anchor_manipulator.AnchorCrealog_device_placementtor(out_shape,
layers_shapes = [(38, 38), (19, 19), (10, 10), (5, 5), (3, 3), (1, 1)],
anchor_scales = [(0.1,), (0.2,), (0.375,), (0.55,), (0.725,), (0.9,)],
extra_anchor_scales = [(0.1414,), (0.2739,), (0.4541,), (0.6315,), (0.8078,), (0.9836,)],
anchor_ratios = [(1., 2., .5), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., .5), (1., 2., .5)],
#anchor_ratios = [(2., .5), (2., 3., .5, 0.3333), (2., 3., .5, 0.3333), (2., 3., .5, 0.3333), (2., .5), (2., .5)],
layer_steps = [8, 16, 32, 64, 100, 300])
all_anchors, all_num_anchors_depth, all_num_anchors_spatial = anchor_creator.get_all_anchors()
anchor_encoder_decoder = anchor_manipulator.AnchorEncoder(allowed_borders = [1.0] * 6,
positive_threshold = None,
ignore_threshold = None,
prior_scaling=[0.1, 0.1, 0.2, 0.2])
decode_fn = lambda pred : anchor_encoder_decoder.ext_decode_all_anchors(pred, all_anchors, all_num_anchors_depth, all_num_anchors_spatial)
with tf.variable_scope(FLAGS.model_scope, default_name=None, values=[features], reuse=tf.AUTO_REUSE):
backbone = ssd_net.VGG16Backbone(FLAGS.data_format)
feature_layers = backbone.forward(features, training=False)
location_pred, cls_pred = ssd_net.multibox_head(feature_layers, FLAGS.num_classes, all_num_anchors_depth, data_format=FLAGS.data_format)
if FLAGS.data_format == 'channels_first':
cls_pred = [tf.transpose(pred, [0, 2, 3, 1]) for pred in cls_pred]
location_pred = [tf.transpose(pred, [0, 2, 3, 1]) for pred in location_pred]
cls_pred = [tf.reshape(pred, [-1, FLAGS.num_classes]) for pred in cls_pred]
location_pred = [tf.reshape(pred, [-1, 4]) for pred in location_pred]
cls_pred = tf.concat(cls_pred, axis=0)
location_pred = tf.concat(location_pred, axis=0)
with tf.device('/cpu:0'):
bboxes_pred = decode_fn(location_pred)
bboxes_pred = tf.concat(bboxes_pred, axis=0)
selected_bboxes, selected_scores = parse_by_class(cls_pred, bboxes_pred,
FLAGS.num_classes, FLAGS.select_threshold, FLAGS.min_size,
FLAGS.keep_topk, FLAGS.nms_topk, FLAGS.nms_threshold)
labels_list = []
scores_list = []
bboxes_list = []
for k, v in selected_scores.items():
labels_list.append(tf.ones_like(v, tf.int32) * k)
scores_list.append(v)
bboxes_list.append(selected_bboxes[k])
all_labels = tf.concat(labels_list, axis=0)
all_scores = tf.concat(scores_list, axis=0)
all_bboxes = tf.concat(bboxes_list, axis=0)
saver = tf.train.Saver()
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
saver.restore(sess, get_checkpoint())
np_image = imread(path)
im = Image.open(path)
print(np_image.shape)
labels_, scores_, bboxes_ = sess.run([all_labels, all_scores, all_bboxes], feed_dict = {image_input : np_image, shape_input : np_image.shape[:-1]})
all_bboxes = sess.run([bboxes_pred], feed_dict = {image_input : np_image, shape_input : np_image.shape[:-1]})
shape = np_image.shape
for j in range(len(all_bboxes[0])):
all_box = all_bboxes[0][j]
p1 = (int(all_box[0] * shape[0]), int(all_box[1] * shape[1]))
p2 = (int(all_box[2] * shape[0]), int(all_box[3] * shape[1]))
if (p2[0] - p1[0] < 1) or (p2[1] - p1[1] < 1):
continue
x1 = p1[1]
y1 = p1[0]
x2 = p2[1]
y2 = p2[0]
obj = im.crop((x1, y1, x2, y2))
num_str = str(j)
num_str = num_str.zfill(5)
obj.save('./res/img/{}.jpg'.format(num_str))
cor = str(x1) + ',' + str(y1) + ',' + str(x2) + ',' +str(y2)
f2 = open('./res/cor.txt', 'a')
f2.write(cor + '\n')
zero_str = str(0)
f = open('./res/label.txt', 'a')
f.write(num_str + ',' + zero_str + '\n')
f.close()
num1 = 0
for i in range(bboxes_.shape[0]):
bbox = bboxes_[i]
p1 = (int(bbox[0] * shape[0]), int(bbox[1] * shape[1]))
p2 = (int(bbox[2] * shape[0]), int(bbox[3] * shape[1]))
num1 = num1 + 1
if (p2[0] - p1[0] < 1) or (p2[1] - p1[1] < 1):
continue
x1 = p1[1]
y1 = p1[0]
x2 = p2[1]
y2 = p2[0]
cor1 = str(x1) + ',' + str(y1) + ',' + str(x2) + ',' + str(y2)
num = 0
with open('./res/cor.txt', 'r') as f11, open('./res/label.txt', '+r') as f22:
for line in f11:
num = num + 1
if cor1 in line:
num11 = str(num)
print(num11 + '\n')
num11 = num11.zfill(5)
ber = num11 + ',' + str(0)
aft = num11 + ',' + str(labels_[i])
t = f22.read()
t = t.replace(ber, aft)
f22.seek(0, 0)
f22.write(t)
print(num1)
img_to_draw = draw_toolbox.bboxes_draw_on_img(np_image, labels_, scores_, bboxes_, thickness=2)
imsave('./demo/out.jpg', img_to_draw)
def main(_):
with tf.Graph().as_default():
out_shape = [FLAGS.train_image_size] * 2
image_input = tf.placeholder(tf.uint8, shape=(None, None, 3))
shape_input = tf.placeholder(tf.int32, shape=(2, ))
features = ssd_preprocessing.preprocess_for_eval(
image_input,
out_shape,
data_format=FLAGS.data_format,
output_rgb=False)
features = tf.expand_dims(features, axis=0)
anchor_creator = anchor_manipulator.AnchorCreator(
out_shape,
layers_shapes=[(38, 38), (19, 19), (10, 10), (5, 5), (3, 3),
(1, 1)],
anchor_scales=[(0.1, ), (0.2, ), (0.375, ), (0.55, ), (0.725, ),
(0.9, )],
extra_anchor_scales=[(0.1414, ), (0.2739, ), (0.4541, ),
(0.6315, ), (0.8078, ), (0.9836, )],
anchor_ratios=[(1., 2., .5), (1., 2., 3., .5, 0.3333),
(1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333),
(1., 2., .5), (1., 2., .5)],
#anchor_ratios = [(2., .5), (2., 3., .5, 0.3333), (2., 3., .5, 0.3333), (2., 3., .5, 0.3333), (2., .5), (2., .5)],
layer_steps=[8, 16, 32, 64, 100, 300])
all_anchors, all_num_anchors_depth, all_num_anchors_spatial = anchor_creator.get_all_anchors(
)
anchor_encoder_decoder = anchor_manipulator.AnchorEncoder(
allowed_borders=[1.0] * 6,
positive_threshold=None,
ignore_threshold=None,
prior_scaling=[0.1, 0.1, 0.2, 0.2])
decode_fn = lambda pred: anchor_encoder_decoder.ext_decode_all_anchors(
pred, all_anchors, all_num_anchors_depth, all_num_anchors_spatial)
with tf.variable_scope(FLAGS.model_scope,
default_name=None,
values=[features],
reuse=tf.AUTO_REUSE):
backbone = ssd_net.VGG16Backbone(FLAGS.data_format)
feature_layers = backbone.forward(features, training=False)
location_pred, cls_pred = ssd_net.multibox_head(
feature_layers,
FLAGS.num_classes,
all_num_anchors_depth,
data_format=FLAGS.data_format)
if FLAGS.data_format == 'channels_first':
cls_pred = [
tf.transpose(pred, [0, 2, 3, 1]) for pred in cls_pred
]
location_pred = [
tf.transpose(pred, [0, 2, 3, 1]) for pred in location_pred
]
cls_pred = [
tf.reshape(pred, [-1, FLAGS.num_classes]) for pred in cls_pred
]
location_pred = [
tf.reshape(pred, [-1, 4]) for pred in location_pred
]
cls_pred = tf.concat(cls_pred, axis=0)
location_pred = tf.concat(location_pred, axis=0)
with tf.device('/cpu:0'):
bboxes_pred = decode_fn(location_pred)
bboxes_pred = tf.concat(bboxes_pred, axis=0)
selected_bboxes, selected_scores = parse_by_class(
cls_pred, bboxes_pred, FLAGS.num_classes,
FLAGS.select_threshold, FLAGS.min_size, FLAGS.keep_topk,
FLAGS.nms_topk, FLAGS.nms_threshold)
labels_list = []
scores_list = []
bboxes_list = []
for k, v in selected_scores.items():
labels_list.append(tf.ones_like(v, tf.int32) * k)
scores_list.append(v)
bboxes_list.append(selected_bboxes[k])
all_labels = tf.concat(labels_list, axis=0)
all_scores = tf.concat(scores_list, axis=0)
all_bboxes = tf.concat(bboxes_list, axis=0)
saver = tf.train.Saver()
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
saver.restore(sess, get_checkpoint())
for i in range(video_frame_cnt):
ret, img_ori = vid.read()
# height_ori, width_ori = img_ori.shape[:2]
# img = cv2.resize(img_ori, tuple(args.new_size))
img = cv2.cvtColor(img_ori, cv2.COLOR_BGR2RGB)
np_image = np.asarray(img, np.float32)
start_time = time.time()
labels_, scores_, bboxes_ = sess.run(
[all_labels, all_scores, all_bboxes],
feed_dict={
image_input: np_image,
shape_input: np_image.shape[:-1]
})
end_time = time.time()
img_to_draw = draw_toolbox.bboxes_draw_on_img(np_image,
labels_,
scores_,
bboxes_,
thickness=2)
cv2.putText(img_to_draw,
'{:.2f}ms'.format((end_time - start_time) * 1000),
(40, 40),
0,
fontScale=1,
color=(0, 255, 0),
thickness=2)
imsave('./test_out.jpg', img_to_draw)
new_img = cv2.imread('./test_out.jpg')
cv2.imshow('image', new_img)
videoWriter.write(new_img)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
vid.release()
videoWriter.release()