the error during training

Question

the error during training

Re3write opened this issue 5 years ago · 6 comments

File "/home/SiamRPN-PyTorch/train/data.py", line 136, in open
img_mean_d )
File "/home/SiamRPN-PyTorch/train/data.py", line 192, in get_instance_image
instance_img, scale_x = self.crop_and_pad(img, cx, cy, size_x, s_x, img_mean)
File "/home/SiamRPN-PyTorch/train/data.py", line 215, in crop_and_pad
xmin = int(self.round_up(xmin + left))
ValueError: cannot convert float NaN to integer

how can i fix it？

Answer 1 · 2019-04-20T04:21:11.000Z

You need delete "cache" folder and try again

Answer 2 · 2019-04-20T04:28:27.000Z

@arbitularov thanks a lot ，by the way have you finished the train code？i see you just update 17 hours ago

Answer 3 · 2019-04-20T04:31:08.000Z

You are welcome, now I'am not finished

Answer 4 · 2019-04-20T04:34:01.000Z

Okay，thanks

Answer 5 · 2019-04-20T09:41:08.000Z

@arbitularov
if index == 8627 or index == 8629 or index == 9057 or index == 9058:
index += 1

the index shound not add 1,when the index=9057, it will be 9058 and get error

Answer 6 · 2019-04-20T18:45:02.000Z

yes, you are right.
index += 3 it is ok