def display(self):
"""
display the processed images in a thread, for models expected output format see tf.image.combined_non_max_suppression
https://www.tensorflow.org/api_docs/python/tf/image/combined_non_max_suppression
"""
# init the starting variables to calculate FPS
try:
start = time.time()
l = 0
tick = 0
while (self._cap.isOpened() and self._running):
# if the display que is empty, nothing has been processed, just wait for an image to arrive
# do not timeout ever as too long does not garuntee an error
while self._display_que.empty() and self._running:
time.sleep(self._wait_time)
if not self._running:
return
if not self._running:
return
# get the images, the predictions placed on the que via the run function (the model)
image, boxes, classes, conf = self._display_que.get()
# there is potential for the images to be processed in batches, so for each image in the batch draw the boxes and the predictions and the confidence
for i in range(image.shape[0]):
if self._print_conf:
self._obj_detected = draw_box(image[i], boxes[i], classes[i],
conf[i], self._colors,
self._labels)
else:
self._obj_detected = draw_box(image[i], boxes[i], classes[i],
None, self._colors,
self._labels)
#display the frame then wait in case something else needs to catch up
cv2.imshow("frame", image[i])
time.sleep(self._wait_time)
#compute the display fps
l += 1
if time.time() - start - tick >= 1:
tick += 1
# store the fps to diplayed to the user
self._display_fps = l
l = 0
if cv2.waitKey(1) & 0xFF == ord('q') or not self._running:
break
except ValueError:
self._running = False
raise
except Exception as e:
#print ("display", e)
self._running = False
#time.sleep(10)
raise e
self._running = False
return
def video_processor(model, version , vidpath, device="/CPU:0"):
img_array = []
i = 0
t = 0
start = time.time()
tick = 0
e, f, a, b, c, d = 0, 0, 0, 0, 0, 0
if isinstance(model, str):
with tf.device(device):
model = build_model(name=model, model_version=version)
model.make_predict_function()
if hasattr(model, "predict"):
predfunc = model.predict
print("using pred function")
else:
predfunc = model
print("using call function")
colors = gen_colors(80)
label_names = get_coco_names(
path="yolo/dataloaders/dataset_specs/coco.names")
print(label_names)
# output_writer = cv2.VideoWriter('yolo_output.mp4', cv2.VideoWriter_fourcc(*'mp4v'), frame_count, (480, 640)) # change output file name if needed
pred = None
cap = cv2.VideoCapture(vidpath)
assert cap.isOpened()
width = int(cap.get(3))
height = int(cap.get(4))
print('width, height, fps:', width, height, int(cap.get(5)))
frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
while cap.isOpened():
success, image = cap.read()
#with tf.device(device):
e = datetime.datetime.now()
image = tf.cast(image, dtype=tf.float32)
image = image / 255
f = datetime.datetime.now()
if t % 1 == 0:
a = datetime.datetime.now()
#with tf.device(device):
pimage = tf.expand_dims(image, axis=0)
pimage = tf.image.resize(pimage, (416, 416))
pred = predfunc(pimage)
b = datetime.datetime.now()
image = image.numpy()
if pred != None:
c = datetime.datetime.now()
boxes, classes = int_scale_boxes(pred["bbox"], pred["classes"],
width, height)
draw = get_draw_fn(colors, label_names, 'YOLO')
draw_box(image, boxes[0].numpy(), classes[0].numpy(),
pred["confidence"][0], draw)
d = datetime.datetime.now()
cv2.imshow('frame', image)
i += 1
t += 1
if time.time() - start - tick >= 1:
tick += 1
print_opt((((f - e) + (b - a) + (d - c))), i)
i = 0
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
return