Closed aelnouby closed 6 years ago
I got the same problem
Try
im_data = np.expand_dims(
yolo_utils.preprocess_test((image, None, cfg.inp_size), 0)[0], 0)
Then comment this line in preprocess_test
#inp_size = inp_size[size_index]
@CompilerBian thank you very much ,this problem had solved
@CompilerBian I did it.(editing demo.py and utils/yolo.py) But I get this error.
TypeError: 'numpy.int64' object is not iterable
Same error occurs when removing comment sign on the line you mentioned
Sorry for introduced this bug in the last PR. I just fixed this in the master branch: https://github.com/longcw/yolo2-pytorch/commit/dfdd82270cc946a8e9dcb5f99b5c9958bf05b0bd
When trying the demo, I found that
preprocess_test
has two arguments(data, size_index)
while in the demo.py file, only one argument is passedyolo_utils.preprocess_test((image, None, cfg.inp_size))[0]
, how to fix this ?Thanks.