gengz / siamesefc-pytorch-vot Goto Github PK

PyTorch implementation of 'Fully-convolutional Siamese networks for object tracking', slightly better results

License: Apache License 2.0

Python 97.06% Shell 0.38% MATLAB 2.56%

siamesefc-pytorch-vot's Issues

a small terminology query

I am little confused in tracking part where you make pyramid scales of crops?

Is there necessity of calculating "beta = 255 / min_scale_side" and first crop that region to make pyramid of crops out of that cropped region

I would be glad if you explain it bit more detail

Thanks in advance

EAO is lower than report

I follow the same data preparation procedure and run the code, but only get 0.1801 EAO on VOT17. So i'm wondering is there any other issues that i should notice

there something wrong in the code

  z = video_id_z[rand_z].copy()    # use copy() here to avoid changing dictionary
    x = video_id_z[rand_x].copy()

    # read z and x，--------here the path of z actually is search image----，
    #I think it should be 
    # l=len(z['instance_path'])
    #img_z = cv2.imread(os.path.join(self.data_dir, (z['instance_path'])[:l-5]+'z.jpg'))
    #img_z = self.__cvt_color(img_z)
    img_z = cv2.imread(os.path.join(self.data_dir, z['instance_path']))
    img_z = self.__cvt_color(img_z)

    img_x = cv2.imread(os.path.join(self.data_dir, x['instance_path']))
    img_x = self.__cvt_color(img_x)

Recommend Projects