def segmentation(model,config):
detection_graph = model.detection_graph
# fixed input sizes as model needs resize either way
vs = WebcamVideoStream(config.VIDEO_INPUT,640,480).start()
resize_ratio = 1.0 * 513 / max(vs.real_width,vs.real_height)
target_size = (int(resize_ratio * vs.real_width), int(resize_ratio * vs.real_height)) #(513, 384)
tf_config = model.tf_config
fps = FPS(config.FPS_INTERVAL).start()
print("> Starting Segmentaion")
with detection_graph.as_default():
with tf.Session(graph=detection_graph,config=tf_config) as sess:
while vs.isActive():
frame = vs.resized(target_size)
batch_seg_map = sess.run('SemanticPredictions:0',
feed_dict={'ImageTensor:0':
[cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)]})
seg_map = batch_seg_map[0]
#boxes = []
#labels = []
#ids = []
map_labeled = measure.label(seg_map, connectivity=1)
for region in measure.regionprops(map_labeled):
if region.area > config.MINAREA:
box = region.bbox
id = seg_map[tuple(region.coords[0])]
label = config.LABEL_NAMES[id]
#boxes.append(box)
#labels.append(label)
#ids.append(id)
if config.VISUALIZE:
draw_single_box_on_image(frame,box,label,id,config.DISCO_MODE)
vis = visualize_deeplab(frame,seg_map,fps._glob_numFrames,config.MAX_FRAMES,fps.fps_local(),
config.PRINT_INTERVAL,config.PRINT_TH,config.DL_DISPLAY_NAME,
config.VISUALIZE,config.VIS_FPS,config.DISCO_MODE,config.ALPHA)
if not vis:
break
fps.update()
fps.stop()
vs.stop()
def detection(model,config):
print("> Building Graph")
# tf Session Config
tf_config = tf.ConfigProto(allow_soft_placement=True)
tf_config.gpu_options.allow_growth=True
detection_graph = model.detection_graph
category_index = model.category_index
with detection_graph.as_default():
with tf.Session(graph=detection_graph,config=tf_config) as sess:
# start Videostream
vs = WebcamVideoStream(config.VIDEO_INPUT,config.WIDTH,config.HEIGHT).start()
# Define Input and Ouput tensors
tensor_dict = model.get_tensordict(['num_detections', 'detection_boxes', 'detection_scores','detection_classes', 'detection_masks'])
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Mask Transformations
fps = FPS(config.FPS_INTERVAL).start()
print('> Starting Detection')
while vs.isActive():
# Detection
if not (config.USE_TRACKER):
# default session
frame = vs.read()
output_dict = sess.run(tensor_dict, feed_dict={image_tensor: vs.expanded()})
num = output_dict['num_detections'][0]
classes = output_dict['detection_classes'][0]
boxes = output_dict['detection_boxes'][0]
scores = output_dict['detection_scores'][0]
if 'detection_masks' in output_dict:
masks = output_dict['detection_masks'][0]
else:
masks = None
# reformat detection
num = int(num)
boxes = np.squeeze(boxes)
classes = np.squeeze(classes).astype(np.uint8)
scores = np.squeeze(scores)
# Visualization
vis = vis_detection(frame, boxes, classes, scores, masks, category_index, fps.fps_local(),
config.VISUALIZE, config.DET_INTERVAL, config.DET_TH, config.MAX_FRAMES,
fps._glob_numFrames, config.OD_MODEL_NAME)
if not vis:
break
fps.update()
# End everything
vs.stop()
fps.stop()
def segmentation(model, config):
detection_graph = model.detection_graph
# fixed input sizes as model needs resize either way
vs = WebcamVideoStream(config.VIDEO_INPUT, 640, 480).start()
resize_ratio = 1.0 * 513 / max(vs.real_width, vs.real_height)
target_size = (int(resize_ratio * vs.real_width),
int(resize_ratio * vs.real_height)) #(513, 384)
tf_config = tf.ConfigProto(allow_soft_placement=True)
tf_config.gpu_options.allow_growth = True
fps = FPS(config.FPS_INTERVAL).start()
print("> Starting Segmentaion")
with detection_graph.as_default():
with tf.Session(graph=detection_graph, config=tf_config) as sess:
while vs.isActive():
frame = vs.resized(target_size)
batch_seg_map = sess.run(
'SemanticPredictions:0',
feed_dict={
'ImageTensor:0':
[cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)]
})
# visualization
if config.VISUALIZE:
seg_map = batch_seg_map[0]
seg_image = create_colormap(seg_map).astype(np.uint8)
cv2.addWeighted(seg_image, config.ALPHA, frame,
1 - config.ALPHA, 0, frame)
vis_text(frame, "fps: {}".format(fps.fps_local()),
(10, 30))
# boxes (ymin, xmin, ymax, xmax)
if config.BBOX:
map_labeled = measure.label(seg_map, connectivity=1)
for region in measure.regionprops(map_labeled):
if region.area > config.MINAREA:
box = region.bbox
p1 = (box[1], box[0])
p2 = (box[3], box[2])
cv2.rectangle(frame, p1, p2, (77, 255, 9), 2)
vis_text(
frame, config.LABEL_NAMES[seg_map[tuple(
region.coords[0])]],
(p1[0], p1[1] - 10))
cv2.imshow(config.DL_MODEL_NAME, frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
fps.update()
fps.stop()
vs.stop()
def segmentation(model, config):
detection_graph = model.detection_graph
# fixed input sizes as model needs resize either way
vs = WebcamVideoStream(config.VIDEO_INPUT, 640, 480).start()
resize_ratio = 1.0 * 513 / max(vs.real_width, vs.real_height)
target_size = (int(resize_ratio * vs.real_width),
int(resize_ratio * vs.real_height)) #(513, 384)
tf_config = model.tf_config
fps = FPS(config.FPS_INTERVAL).start()
print("> Starting Segmentaion")
with detection_graph.as_default():
with tf.Session(graph=detection_graph, config=tf_config) as sess:
while vs.isActive():
frame = vs.resized(target_size)
batch_seg_map = sess.run(
'SemanticPredictions:0',
feed_dict={
'ImageTensor:0':
[cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)]
})
seg_map = batch_seg_map[0]
#boxes = []
#labels = []
map_labeled = measure.label(seg_map, connectivity=1)
for region in measure.regionprops(map_labeled):
if region.area > config.MINAREA:
box = region.bbox
label = config.LABEL_NAMES[seg_map[tuple(
region.coords[0])]]
#boxes.append(box)
#labels.append(label)
if config.VISUALIZE:
draw_single_box_on_image(frame, box, label)
vis = visualize_deeplab(
frame, seg_map, fps._glob_numFrames, config.MAX_FRAMES,
fps.fps_local(), config.PRINT_INTERVAL, config.PRINT_TH,
config.OD_MODEL_NAME + config._DEV + config._OPT,
config.VISUALIZE)
if not vis:
break
fps.update()
fps.stop()
vs.stop()
def detection(model,config):
# Tracker
if config.USE_TRACKER:
import sys
sys.path.append(os.getcwd()+'/stuff/kcf')
import KCF
tracker = KCF.kcftracker(False, True, False, False)
tracker_counter = 0
track = False
print("> Building Graph")
# tf Session Config
tf_config = model.tf_config
detection_graph = model.detection_graph
category_index = model.category_index
with detection_graph.as_default():
with tf.Session(graph=detection_graph,config=tf_config) as sess:
# start Videostream
vs = WebcamVideoStream(config.VIDEO_INPUT,config.WIDTH,config.HEIGHT).start()
# Define Input and Ouput tensors
tensor_dict = model.get_tensordict(['num_detections', 'detection_boxes', 'detection_scores','detection_classes', 'detection_masks'])
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Mask Transformations
if 'detection_masks' in tensor_dict:
# Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0])
detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0])
real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32)
detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1])
detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1])
detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
detection_masks, detection_boxes, vs.real_height, vs.real_width)
detection_masks_reframed = tf.cast(tf.greater(detection_masks_reframed, 0.5), tf.uint8)
# Follow the convention by adding back the batch dimension
tensor_dict['detection_masks'] = tf.expand_dims(detection_masks_reframed, 0)
if config.SPLIT_MODEL:
score_out = detection_graph.get_tensor_by_name('Postprocessor/convert_scores:0')
expand_out = detection_graph.get_tensor_by_name('Postprocessor/ExpandDims_1:0')
score_in = detection_graph.get_tensor_by_name('Postprocessor/convert_scores_1:0')
expand_in = detection_graph.get_tensor_by_name('Postprocessor/ExpandDims_1_1:0')
# Threading
score = model.score
expand = model.expand
gpu_worker = SessionWorker("GPU",detection_graph,tf_config)
cpu_worker = SessionWorker("CPU",detection_graph,tf_config)
gpu_opts = [score_out, expand_out]
cpu_opts = [tensor_dict['detection_boxes'], tensor_dict['detection_scores'], tensor_dict['detection_classes'], tensor_dict['num_detections']]
gpu_counter = 0
cpu_counter = 0
fps = FPS(config.FPS_INTERVAL).start()
print('> Starting Detection')
while vs.isActive():
# Detection
if not (config.USE_TRACKER and track):
if config.SPLIT_MODEL:
# split model in seperate gpu and cpu session threads
masks = None # No Mask Detection possible yet
if gpu_worker.is_sess_empty():
# read video frame, expand dimensions and convert to rgb
frame = vs.read()
# put new queue
gpu_feeds = {image_tensor: vs.expanded()}
if config.VISUALIZE:
gpu_extras = frame # for visualization frame
else:
gpu_extras = None
gpu_worker.put_sess_queue(gpu_opts,gpu_feeds,gpu_extras)
g = gpu_worker.get_result_queue()
if g is None:
# gpu thread has no output queue. ok skip, let's check cpu thread.
gpu_counter += 1
else:
# gpu thread has output queue.
gpu_counter = 0
score,expand,frame = g["results"][0],g["results"][1],g["extras"]
if cpu_worker.is_sess_empty():
# When cpu thread has no next queue, put new queue.
# else, drop gpu queue.
cpu_feeds = {score_in: score, expand_in: expand}
cpu_extras = frame
cpu_worker.put_sess_queue(cpu_opts,cpu_feeds,cpu_extras)
c = cpu_worker.get_result_queue()
if c is None:
# cpu thread has no output queue. ok, nothing to do. continue
cpu_counter += 1
continue # If CPU RESULT has not been set yet, no fps update
else:
cpu_counter = 0
boxes, scores, classes, num, frame = c["results"][0],c["results"][1],c["results"][2],c["results"][3],c["extras"]
else:
# default session
frame = vs.read()
output_dict = sess.run(tensor_dict, feed_dict={image_tensor: vs.expanded()})
num = output_dict['num_detections'][0]
classes = output_dict['detection_classes'][0]
boxes = output_dict['detection_boxes'][0]
scores = output_dict['detection_scores'][0]
if 'detection_masks' in output_dict:
masks = output_dict['detection_masks'][0]
else:
masks = None
# reformat detection
num = int(num)
boxes = np.squeeze(boxes)
classes = np.squeeze(classes).astype(np.uint8)
scores = np.squeeze(scores)
# Visualization
vis = vis_detection(frame, boxes, classes, scores, masks, category_index, fps.fps_local(),
config.VISUALIZE, config.DET_INTERVAL, config.DET_TH, config.MAX_FRAMES,
fps._glob_numFrames, config.OD_MODEL_NAME)
if not vis:
break
# Activate Tracker
if config.USE_TRACKER and num <= config.NUM_TRACKERS:
tracker_frame = frame
track = True
first_track = True
# Tracking
else:
frame = vs.read()
if first_track:
trackers = []
tracker_boxes = boxes
for box in boxes[~np.all(boxes == 0, axis=1)]:
tracker.init(conv_detect2track(box,vs.real_width, vs.real_height), tracker_frame)
trackers.append(tracker)
first_track = False
for idx,tracker in enumerate(trackers):
tracker_box = tracker.update(frame)
tracker_boxes[idx,:] = conv_track2detect(tracker_box, vs.real_width, vs.real_height)
vis = vis_detection(frame, tracker_boxes, classes, scores, masks, category_index, fps.fps_local(),
config.VISUALIZE, config.DET_INTERVAL, config.DET_TH, config.MAX_FRAMES,
fps._glob_numFrames, config.OD_MODEL_NAME)
if not vis:
break
tracker_counter += 1
#tracker_frame = frame
if tracker_counter >= config.TRACKER_FRAMES:
track = False
tracker_counter = 0
fps.update()
# End everything
vs.stop()
fps.stop()
if config.SPLIT_MODEL:
gpu_worker.stop()
cpu_worker.stop()
def detection(model,config):
# Tracker
if config.USE_TRACKER:
import sys
sys.path.append(os.getcwd()+'/rod/kcf')
import KCF
tracker = KCF.kcftracker(False, True, False, False)
tracker_counter = 0
track = False
print("> Building Graph")
# tf Session Config
tf_config = model.tf_config
detection_graph = model.detection_graph
category_index = model.category_index
with detection_graph.as_default():
with tf.Session(graph=detection_graph,config=tf_config) as sess:
# start Videostream
vs = WebcamVideoStream(config.VIDEO_INPUT,config.WIDTH,config.HEIGHT).start()
# Define Input and Ouput tensors
tensor_dict = model.get_tensordict(['num_detections', 'detection_boxes', 'detection_scores','detection_classes', 'detection_masks'])
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Mask Transformations
if 'detection_masks' in tensor_dict:
# Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0])
detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0])
real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32)
detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1])
detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1])
detection_masks_reframed = reframe_box_masks_to_image_masks(
detection_masks, detection_boxes, vs.real_height, vs.real_width)
detection_masks_reframed = tf.cast(tf.greater(detection_masks_reframed, 0.5), tf.uint8)
# Follow the convention by adding back the batch dimension
tensor_dict['detection_masks'] = tf.expand_dims(detection_masks_reframed, 0)
if config.SPLIT_MODEL:
score_out = detection_graph.get_tensor_by_name('Postprocessor/convert_scores:0')
expand_out = detection_graph.get_tensor_by_name('Postprocessor/ExpandDims_1:0')
score_in = detection_graph.get_tensor_by_name('Postprocessor/convert_scores_1:0')
expand_in = detection_graph.get_tensor_by_name('Postprocessor/ExpandDims_1_1:0')
# Threading
score = model.score
expand = model.expand
gpu_worker = SessionWorker("GPU",detection_graph,tf_config)
cpu_worker = SessionWorker("CPU",detection_graph,tf_config)
gpu_opts = [score_out, expand_out]
cpu_opts = [tensor_dict['detection_boxes'], tensor_dict['detection_scores'], tensor_dict['detection_classes'], tensor_dict['num_detections']]
fps = FPS(config.FPS_INTERVAL).start()
masks = None
print('> Starting Detection')
while vs.isActive():
# Detection
if not (config.USE_TRACKER and track):
if config.SPLIT_MODEL:
# split model in seperate gpu and cpu session threads
if gpu_worker.is_sess_empty():
# read video frame, expand dimensions and convert to rgb
frame = vs.read()
# put new queue
gpu_feeds = {image_tensor: vs.expanded()}
if config.VISUALIZE:
gpu_extras = frame # for visualization frame
else:
gpu_extras = None
gpu_worker.put_sess_queue(gpu_opts,gpu_feeds,gpu_extras)
g = gpu_worker.get_result_queue()
if g is None:
# gpu thread has no output queue. ok skip, let's check cpu thread.
pass
else:
# gpu thread has output queue.
score,expand,frame = g["results"][0],g["results"][1],g["extras"]
if cpu_worker.is_sess_empty():
# When cpu thread has no next queue, put new queue.
# else, drop gpu queue.
cpu_feeds = {score_in: score, expand_in: expand}
cpu_extras = frame
cpu_worker.put_sess_queue(cpu_opts,cpu_feeds,cpu_extras)
c = cpu_worker.get_result_queue()
if c is None:
# cpu thread has no output queue. ok, nothing to do. continue
continue # If CPU RESULT has not been set yet, no fps update
else:
boxes, scores, classes, num, frame = c["results"][0],c["results"][1],c["results"][2],c["results"][3],c["extras"]
else:
# default session
frame = vs.read()
output_dict = sess.run(tensor_dict, feed_dict={image_tensor: vs.expanded()})
num = output_dict['num_detections'][0]
classes = output_dict['detection_classes'][0]
boxes = output_dict['detection_boxes'][0]
scores = output_dict['detection_scores'][0]
if 'detection_masks' in output_dict:
masks = output_dict['detection_masks'][0]
# reformat detection
num = int(num)
boxes = np.squeeze(boxes)
classes = np.squeeze(classes).astype(np.uint8)
scores = np.squeeze(scores)
# Visualization
vis = visualize_objectdetection(frame,boxes,classes,scores,masks,category_index,fps._glob_numFrames,
config.MAX_FRAMES,fps.fps_local(),config.PRINT_INTERVAL,config.PRINT_TH,
config.OD_DISPLAY_NAME,config.VISUALIZE,config.VIS_FPS,config.DISCO_MODE,config.ALPHA)
if not vis:
break
# Activate Tracker
if config.USE_TRACKER and num <= config.NUM_TRACKERS:
tracker_frame = frame
track = True
first_track = True
# Tracking
else:
frame = vs.read()
if first_track:
trackers = []
tracker_boxes = boxes
for box in boxes[~np.all(boxes == 0, axis=1)]:
tracker.init(conv_detect2track(box,vs.real_width, vs.real_height), tracker_frame)
trackers.append(tracker)
first_track = False
for idx,tracker in enumerate(trackers):
tracker_box = tracker.update(frame)
tracker_boxes[idx,:] = conv_track2detect(tracker_box, vs.real_width, vs.real_height)
vis = visualize_objectdetection(frame,tracker_boxes,classes,scores,masks,category_index,fps._glob_numFrames,
config.MAX_FRAMES,fps.fps_local(),config.PRINT_INTERVAL,config.PRINT_TH,
config.OD_DISPLAY_NAME,config.VISUALIZE,config.VIS_FPS,config.DISCO_MODE,config.ALPHA)
if not vis:
break
tracker_counter += 1
#tracker_frame = frame
if tracker_counter >= config.TRACKER_FRAMES:
track = False
tracker_counter = 0
fps.update()
# End everything
vs.stop()
fps.stop()
if config.SPLIT_MODEL:
gpu_worker.stop()
cpu_worker.stop()