def main(checkpoint, input_files):
os.environ['CUDA_VISIBLE_DEVICES'] = auto_select_gpu()
model_config, _, track_config = load_cfgs(checkpoint)
track_config['log_level'] = 1
track_config["is_video"] = False
g = tf.Graph()
with g.as_default():
model = inference_wrapper.InferenceWrapper()
restore_fn = model.build_graph_from_config(model_config, track_config,
checkpoint)
g.finalize()
if not osp.isdir(track_config['log_dir']):
logging.info('Creating inference directory: %s',
track_config['log_dir'])
mkdir_p(track_config['log_dir'])
video_dirs = []
for file_pattern in input_files.split(","):
video_dirs.extend(glob(file_pattern))
logging.info("Running tracking on %d videos matching %s", len(video_dirs),
input_files)
gpu_options = tf.GPUOptions(allow_growth=True)
sess_config = tf.ConfigProto(gpu_options=gpu_options)
with tf.Session(graph=g, config=sess_config) as sess:
restore_fn(sess)
tracker = Tracker(model,
model_config=model_config,
track_config=track_config)
for video_dir in video_dirs:
if not osp.isdir(video_dir):
logging.warning(
'{} is not a directory, skipping...'.format(video_dir))
continue
video_name = osp.basename(video_dir)
video_log_dir = osp.join(track_config['log_dir'], video_name)
mkdir_p(video_log_dir)
filenames = sort_nicely(glob(video_dir + '/img/*.jpg'))
first_line = open(video_dir + '/groundtruth_rect.txt').readline()
bb = [int(v) for v in first_line.strip().split(',')]
# Rectangle: [x,y,width,height]
init_bb = Rectangle(bb[0] - 1, bb[1] - 1, bb[2],
bb[3]) # 0-index in python
trajectory = tracker.track(sess, init_bb, filenames, video_log_dir)
with open(osp.join(video_log_dir, 'track_rect.txt'), 'w') as f:
for region in trajectory:
rect_str = '{},{},{},{}\n'.format(region.x + 1,
region.y + 1,
region.width,
region.height)
f.write(rect_str)
def main(config):
tf.reset_default_graph()
log_dir = config.log_dir
if config.net_type == 'siamese':
model = inference_wrapper.InferenceWrapper(config)
elif config.net_type == 'cfcf':
model = inference_cfcf.InferenceCFCF(config)
else:
raise ValueError('Unknown net_type: ', config.net_type)
var_list = model.build_graph_from_config()
if config.clear_logs and tf.gfile.Exists(log_dir):
print('Clear all files in {}'.format(log_dir))
try:
tf.gfile.DeleteRecursively(log_dir)
except:
print('Fail to delete {}. You probably have to kill tensorboard process.'.format(log_dir))
seq_names = read_text(config.seq_text, dtype=np.str)
video_dirs = [os.path.join(config.root_dir, x) for x in seq_names]
tfconfig = tf.ConfigProto()
tfconfig.gpu_options.allow_growth = True # almost the same as tf.InteractiveSession
sess = tf.Session(config=tfconfig)
sess.run(tf.global_variables_initializer())
# restore_fn(sess)
if osp.isdir(config.model):
checkpoint = tf.train.latest_checkpoint(config.model)
else:
checkpoint = config.model
saver = tf.train.Saver(var_list)
saver.restore(sess, checkpoint)
tracker = Tracker(model, config=config)
for video_dir in video_dirs:
if not os.path.isdir(video_dir):
continue
video_name = os.path.basename(video_dir)
video_log_dir = os.path.join(log_dir, video_name)
mkdir_p(video_log_dir)
filenames = sort_nicely(glob.glob(video_dir + '/img/*.jpg'))
first_line = open(video_dir + '/groundtruth_rect.txt').readline()
bb = [int(v) for v in first_line.strip().split(',')]
init_bb = Rectangle(bb[0] - 1, bb[1] - 1, bb[2], bb[3]) # 0-index in python
trajectory = tracker.track(sess, init_bb, filenames, video_log_dir)
with open(osp.join(video_log_dir, 'track_rect.txt'), 'w') as f:
for region in trajectory:
rect_str = '{},{},{},{}\n'.format(region.x + 1, region.y + 1,
region.width, region.height)
f.write(rect_str)
def run_SA_Siam(seq, rp, bSaveImage, epoch=30):
iter_ckpt = epoch * 6650 - 1
checkpoint_appearance_path = CHECKPOINT_APPEARANCE.format(
iter_ckpt=iter_ckpt)
logging.info('Evaluating {}...'.format(checkpoint_appearance_path))
checkpoint_semantic_path = CHECKPOINT_SEMANTIC.format(iter_ckpt=iter_ckpt)
logging.info('Evaluating {}...'.format(checkpoint_semantic_path))
# Read configurations from json
model_config, _, track_config = load_cfgs(CHECKPOINT_SA_SIAM)
track_config['log_level'] = 0 # Skip verbose logging for speed
# Build the inference graph.
g = tf.Graph()
with g.as_default():
model = inference_wrapper.InferenceWrapper()
model.build_model(model_config, track_config)
saver_loader_semantic = get_saver('',
removes=[':0', '_semantic'],
excepts=['appearance', 'State'])
saver_loader_appearance = get_saver('',
removes=[':0', '_appearance'],
excepts=['semantic', 'State'])
g.finalize()
gpu_options = tf.GPUOptions(allow_growth=True)
sess_config = tf.ConfigProto(gpu_options=gpu_options)
with tf.Session(graph=g, config=sess_config) as sess:
# Load the model from checkpoint.
# restore_fn(sess)
saver_loader_semantic.restore(sess, checkpoint_semantic_path)
saver_loader_appearance.restore(sess, checkpoint_appearance_path)
tracker = Tracker(model, model_config, track_config)
tic = time.clock()
frames = seq.s_frames
init_rect = seq.init_rect
x, y, width, height = init_rect # OTB format
init_bb = Rectangle(x - 1, y - 1, width, height)
trajectory_py = tracker.track(sess, init_bb, frames)
trajectory = [
Rectangle(val.x + 1, val.y + 1, val.width, val.height)
for val in trajectory_py
] # x, y add one to match OTB format
duration = time.clock() - tic
result = dict()
result['res'] = trajectory
result['type'] = 'rect'
result['fps'] = round(seq.len / duration, 3)
return result
def main(checkpoint, input_files):
os.environ['CUDA_VISIBLE_DEVICES'] = auto_select_gpu()
model_config, _, track_config = load_cfgs(checkpoint)
track_config['log_level'] = 1
g = tf.Graph()
with g.as_default():
model = inference_wrapper.InferenceWrapper()
restore_fn = model.build_graph_from_config(model_config, track_config, checkpoint)
g.finalize()
if not osp.isdir(track_config['log_dir']):
logging.info('Creating inference directory: %s', track_config['log_dir'])
mkdir_p(track_config['log_dir'])
video_dirs = []
for file_pattern in input_files.split(","):
video_dirs.extend(glob(file_pattern))
logging.info("Running tracking on %d videos matching %s", len(video_dirs), input_files)
gpu_options = tf.GPUOptions(allow_growth=True)
sess_config = tf.ConfigProto(gpu_options=gpu_options)
with tf.Session(graph=g, config=sess_config) as sess:
restore_fn(sess)
tracker = Tracker(model, model_config=model_config, track_config=track_config)
for video_dir in video_dirs:
if not osp.isdir(video_dir):
logging.warning('{} is not a directory, skipping...'.format(video_dir))
continue
video_name = osp.basename(video_dir)
video_log_dir = osp.join(track_config['log_dir'], video_name)
mkdir_p(video_log_dir)
filenames = sort_nicely(glob(video_dir + '/img/*.jpg'))
first_line = open(video_dir + '/groundtruth_rect.txt').readline()
bb = [int(v) for v in first_line.strip().split(',')]
init_bb = Rectangle(bb[0] - 1, bb[1] - 1, bb[2], bb[3]) # 0-index in python
trajectory = tracker.track(sess, init_bb, filenames, video_log_dir)
with open(osp.join(video_log_dir, 'track_rect.txt'), 'w') as f:
for region in trajectory:
rect_str = '{},{},{},{}\n'.format(region.x + 1, region.y + 1,
region.width, region.height)
f.write(rect_str)
def run_MFST(seq, rp, bSaveImage):
checkpoint_path = CHECKPOINT
logging.info('Evaluating {}...'.format(checkpoint_path))
# Read configurations from json
model_config, _, track_config = load_cfgs(checkpoint_path)
track_config['log_level'] = 0 # Skip verbose logging for speed
# Build the inference graph.
g = tf.Graph()
with g.as_default():
model = inference_wrapper.InferenceWrapper()
restore_fn = model.build_graph_from_config(model_config, track_config, checkpoint_path)
#g.finalize()
gpu_options = tf.GPUOptions(allow_growth=True)
sess_config = tf.ConfigProto(gpu_options=gpu_options)
with tf.Session(graph=g, config=sess_config) as sess:
## used for initializing alexnet parameters
init_global = tf.global_variables_initializer()
sess.run(init_global)
## global initalizer must be run before restore
# Load the model from checkpoint.
restore_fn(sess)
tracker = Tracker(model, model_config, track_config)
tic = time.clock()
frames = seq.s_frames
init_rect = seq.init_rect
x, y, width, height = init_rect # OTB format
init_bb = Rectangle(x - 1, y - 1, width, height)
trajectory_py = tracker.track(sess, init_bb, frames)
trajectory = [Rectangle(val.x + 1, val.y + 1, val.width, val.height) for val in
trajectory_py] # x, y add one to match OTB format
duration = time.clock() - tic
result = dict()
result['res'] = trajectory
result['type'] = 'rect'
result['fps'] = round(seq.len / duration, 3)
return result
def __init__(
self,
debug=0,
checkpoint='Logs/SiamFC/track_model_checkpoints/SiamFC-3s-color-pretrained'
):
os.environ['CUDA_VISIBLE_DEVICES'] = auto_select_gpu()
# run only on cpu
# os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
model_config, _, track_config = load_cfgs(checkpoint)
track_config['log_level'] = debug
g = tf.Graph()
with g.as_default():
model = inference_wrapper.InferenceWrapper()
restore_fn = model.build_graph_from_config(model_config,
track_config,
checkpoint)
g.finalize()
if not osp.isdir(track_config['log_dir']):
logging.info('Creating inference directory: %s',
track_config['log_dir'])
mkdir_p(track_config['log_dir'])
gpu_options = tf.GPUOptions(allow_growth=True)
sess_config = tf.ConfigProto(gpu_options=gpu_options)
sess = tf.Session(graph=g, config=sess_config)
# sess.run(tf.global_variables_initializer())
restore_fn(sess)
tracker = Tracker(model,
model_config=model_config,
track_config=track_config)
video_name = "demo"
video_log_dir = osp.join(track_config['log_dir'], video_name)
rmdir(video_log_dir)
mkdir_p(video_log_dir)
self.tracker = tracker
self.sess = sess
self.video_log_dir = video_log_dir
self.graph = g
def build_tracker(tracker_config):
# Build the inference graph.
g = tf.Graph()
with g.as_default():
model = inference_wrapper.InferenceWrapper()
restore_fn = model.build_graph_from_config(
tracker_config['model_config'], tracker_config['track_config'],
tracker_config['checkpoint_path'])
g.finalize()
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=tracker_config['gpu_fraction'])
sess_config = tf.ConfigProto(gpu_options=gpu_options)
sess = tf.Session(graph=g, config=sess_config)
# Load the model from checkpoint.
restore_fn(sess)
tracker = Tracker(model,
model_config=tracker_config['model_config'],
track_config=tracker_config['track_config'])
return sess, tracker
selection = handle.region()
# PROCESS INIT FRAME #
imgfile = handle.frame()
if not imgfile:
sys.exit(0)
logger.info(imgfile)
init_left, init_top, init_w, init_h = selection[:]
# Feed minx, miny, maxx, maxy #
init_bbox = [init_left, init_top, init_left + init_w, init_top + init_h]
init_im = io.imread(imgfile)
tracker = Tracker(model, init_im, init_bbox, TRACK_CONFIG['use_gpu'])
while True:
imgfile = handle.frame()
logger.info(imgfile)
if not imgfile:
handle.quit()
break
im = io.imread(imgfile)
est_bbox = tracker.track(im)
#logger.info("est_bbox: ", est_bbox)
w, h = est_bbox[2] - est_bbox[0], est_bbox[3] - est_bbox[1]
minx, miny = est_bbox[0], est_bbox[1]
selection = vot.Rectangle(minx, miny, w, h)
#logger.info(selection)
handle.report(selection)
with g.as_default():
model = inference_wrapper.InferenceWrapper()
restore_fn = model.build_graph_from_config(model_config, track_config,
checkpoint_path)
#g.finalize()
gpu_options = tf.GPUOptions(allow_growth=True)
sess_config = tf.ConfigProto(gpu_options=gpu_options)
with tf.Session(graph=g, config=sess_config) as sess:
## used for initializing alexnet parameters
init_global = tf.global_variables_initializer()
sess.run(init_global)
## global initalizer must be run before restore
# Load the model from checkpoint.
restore_fn(sess)
tracker = Tracker(model, model_config, track_config)
handle = vot.VOT("rectangle")
selection = handle.region()
imagefile = handle.frame()
tracker.track_vot_init(sess, selection, imagefile)
while True:
imagefile = handle.frame()
if not imagefile:
break
region = tracker.track_vot(sess, imagefile)
handle.report(region)
def main(_):
# load model
model_config, _, track_config = load_cfgs(CHECKPOINT)
track_config["log_level"] = 0
track_config["is_video"] = True
g = tf.Graph()
with g.as_default():
model = inference_wrapper.InferenceWrapper()
restore_fn = model.build_graph_from_config(model_config, track_config,
CHECKPOINT)
g.finalize()
if not os.path.isdir(track_config['log_dir']):
tf.logging.info('Creating inference directory: %s',
track_config['log_dir'])
mkdir_p(track_config['log_dir'])
gpu_options = tf.GPUOptions(allow_growth=True)
sess_config = tf.ConfigProto(gpu_options=gpu_options)
with tf.Session(graph=g, config=sess_config) as sess:
restore_fn(sess)
tracker = Tracker(model,
model_config=model_config,
track_config=track_config)
video_name = os.path.basename(FLAGS.video_path)
video_log_dir = os.path.join(track_config["log_dir"], video_name)
mkdir_p(video_log_dir)
if str(FLAGS.video_path) in ["0", "1"]:
# read from camera
video_path = int(FLAGS.video_path)
with_camera = True
else:
# read from video
video_path = glob(os.path.join(FLAGS.video_path, "*.mp4"))[0]
with_camera = False
video_capture = cv2.VideoCapture(video_path)
bb = [-1, -1, -1, -1]
cv2.namedWindow("template")
cv2.setMouseCallback("template", draw_init_box, bb)
trajectory = []
f_count = 0
f_rate = 0
start_time = time.time()
while True:
# capture frame by frame
ret_, frame = video_capture.read()
if ret_ == False:
continue
f_width, f_height = [
int(a) for a in FLAGS.video_resolution.split("*")
]
try:
o_frame = cv2.resize(frame, (f_width, f_height),
interpolation=cv2.INTER_CUBIC)
except:
break
i_frame = cv2.cvtColor(o_frame, cv2.COLOR_BGR2RGB)
# cv2.imwrite("test.jpg",o_frame)
# pdb.set_trace()
if f_count == 0: # initialize the tracker
# wait for drawing init box
while True:
init_frame = o_frame.copy()
cv2.imshow("template", init_frame)
k = cv2.waitKey(0)
if k == 32: # space
cx = int((bb[0] + bb[2]) / 2)
cy = int((bb[1] + bb[3]) / 2)
w = int(bb[2] - bb[0])
h = int(bb[3] - bb[1])
# Rectangle: [x,y,width,height]
init_bb = Rectangle(cx - 1, cy - 1, w,
h) # 0-index in python
draw_box(init_frame, init_bb, "exemplar")
break
first_box = convert_bbox_format(init_bb, "center-based")
bbox_feed = [
first_box.y, first_box.x, first_box.height, first_box.width
]
input_feed = [i_frame, bbox_feed]
frame2crop_scale = tracker.siamese_model.initialize(
sess, input_feed)
# Storing target state
original_target_height = first_box.height
original_target_width = first_box.width
search_center = np.array([
get_center(tracker.x_image_size),
get_center(tracker.x_image_size)
])
current_target_state = TargetState(
bbox=first_box,
search_pos=search_center,
scale_idx=int(get_center(tracker.num_scales)))
# setup initialized params
current_param = {
"original_target_width": original_target_width,
"original_target_height": original_target_height,
"search_center": search_center,
"current_target_state": current_target_state
}
bbox, current_param = tracker.track_frame(sess, i_frame,
current_param,
video_log_dir)
# add overlays
end_time = time.time()
f_rate = int(1 / (end_time - start_time))
start_time = time.time()
draw_box(o_frame, bbox)
cv2.putText(o_frame,
str(f_rate) + "fps", (10, 30),
cv2.FONT_HERSHEY_SIMPLEX,
1, (0, 0, 255),
thickness=2,
lineType=2)
trajectory.append(bbox)
f_count += 1
cv2.imshow("Real-time Ouput", o_frame)
cv2.imshow("template", init_frame)
# if f_count > 30:
# cv2.imwrite("test.jpg",o_frame)
# pdb.set_trace()
if cv2.waitKey(1) & 0xFF == ord("q"):
cv2.imwrite("./assets/instance.jpg", o_frame)
cv2.imwrite("./assets/exemplar.jpg", init_frame)
break
video_capture.release()
cv2.destroyAllWindows()
# save track results
# pdb.set_trace()
with open(os.path.join(video_log_dir, "track_rect.txt"), "w") as f:
for region in trajectory:
rect_str = "{},{},{},{}\n".format(region.x + 1, region.y + 1,
region.width, region.height)
f.write(rect_str)
def main(checkpoint, input_files):
os.environ['CUDA_VISIBLE_DEVICES'] = auto_select_gpu()
model_config, _, track_config = load_cfgs(checkpoint)
track_config['log_level'] = 1
g = tf.Graph()
with g.as_default():
model = inference_wrapper.InferenceWrapper()
restore_fn = model.build_graph_from_config(model_config, track_config,
checkpoint)
g.finalize()
if not osp.isdir(track_config['log_dir']):
logging.info('Creating inference directory: %s',
track_config['log_dir'])
mkdir_p(track_config['log_dir'])
video_dirs = []
for file_pattern in input_files.split(","):
video_dirs.extend(glob(file_pattern))
logging.info("Running tracking on %d videos matching %s", len(video_dirs),
input_files)
gpu_options = tf.GPUOptions(allow_growth=True)
sess_config = tf.ConfigProto(gpu_options=gpu_options)
with tf.Session(graph=g, config=sess_config) as sess:
restore_fn(sess)
tracker = Tracker(model,
model_config=model_config,
track_config=track_config)
for video_dir in video_dirs:
if not osp.isdir(video_dir):
logging.warning(
'{} is not a directory, skipping...'.format(video_dir))
continue
video_name = osp.basename(video_dir)
video_log_dir = osp.join(track_config['log_dir'], video_name)
mkdir_p(video_log_dir)
filenames = sort_nicely(
glob(video_dir + '/img/*.jpg') +
glob(video_dir + '/img/*.png'))
first_line = open(video_dir + '/groundtruth_rect.txt').readline()
bb = [int(v) for v in first_line.strip().split(',')]
init_bb = Rectangle(bb[0] - 1, bb[1] - 1, bb[2],
bb[3]) # 0-index in python
trajectory = tracker.track(sess, init_bb, filenames, video_log_dir)
with open(osp.join(video_log_dir, 'track_rect.txt'), 'w') as f:
for region in trajectory:
rect_str = '{},{},{},{}\n'.format(region.x + 1,
region.y + 1,
region.width,
region.height)
f.write(rect_str)
with open(osp.join(video_log_dir, 'bboxes.json'), 'r') as f:
data = json.load(f)
final_output = {}
for i, fname in enumerate(data.keys()):
img = np.array(Image.open(fname).convert('RGB'))
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
#print(img,img.shape)
bboxes = data[fname]
bboxes = list(
map(
lambda x: list(
map(lambda y: float(y),
x.strip().split(','))), bboxes))
arr = []
for x, y, w, h in bboxes:
ymin, xmin, ymax, xmax = int(y), int(x), int(y +
h), int(x + w)
img = cv2.rectangle(img, (xmin, ymin), (xmax, ymax),
(0, 255, 0, 255), 2)
arr.append([ymin, xmin, ymax, xmax])
final_output[fname] = arr
name = osp.basename(fname)
name = osp.splitext(name)[0]
W, H, _ = img.shape
cv2.imshow("Pic", cv2.resize(img, (W // 2, H // 2)))
cv2.waitKey(0)
out_folder = osp.join(video_log_dir, "Outputs")
mkdir_p(out_folder)
cv2.imwrite(osp.join(out_folder, f"{name}_bbox.png"), img)
with open(osp.join(out_folder, "output.json"), "w") as f:
json.dump(final_output, f, indent=4)
cv2.destroyAllWindows()