problem when no detections about yolo_tracking HOT 6 CLOSED

ok so without thinking too hard:

Yolov5_DeepSort_Pytorch\deep_sort\deep_sort\sort\track.py
def increment_age(self):
self.age += 1
self.time_since_update += 1

def predict(self, kf):
"""Propagate the state distribution to the current time step using a
Kalman filter prediction step.

    Parameters
    ----------
    kf : kalman_filter.KalmanFilter
        The Kalman filter.

    """
    self.mean, self.covariance = kf.predict(self.mean, self.covariance)
    #self.age += 1
    self.increment_age()
   # self.time_since_update += 1

Yolov5_DeepSort_Pytorch\deep_sort\deep_sort\sort\tracker.py

def increment_ages(self):
for track in self.tracks:
track.increment_age()
track.mark_missed()

deepsort.py add

def increment_ages(self):
    self.tracker.increment_ages()

and in Yolov5_DeepSort_Pytorch\track.py

 else:
            p, s, im0 = path, '', im0s

        s += '%gx%g ' % img.shape[2:]  # print string

        if det is  None:
            deepsort.increment_ages()

        if det is not None and len(det):
            # Rescale boxes from img_size to im0 size
            det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()

from yolo_tracking.

This issue is now fixed and pushed to master @kanasite, @bryceburrows

from yolo_tracking.

Thank you for your feedback @bryceburrows!

You are totally right. I will try to fix this issue in the coming weeks

from yolo_tracking.

i have a fix that seems to work - don't to push the while thing as ive made a bunch of mod's for another use.

can send it to you if you like

from yolo_tracking.

Sure! Feel free to leave it here as a comment :)

from yolo_tracking.

bump, is this fixed?

from yolo_tracking.