Wenyuan
Wenyuan
@tp227 Have you solve this problem? Can you give some guide for what should be change?
@endernewton Could you please give us an instruction about training on custom dataset? We met some errors, but still cannot figure them out. Thanks!
@paulcx I have change _pascal_voc.py_. It did not work.
In pascal_voc.py, I changed the original classes into my classes. Is there anything which should be modified? ``` self._classes = ('__background__', # always index 0 'aeroplane', 'bicycle', 'bird', 'boat', 'bottle',...
@endernewton @XiongweiWu Thanks. This work is a little difficult for me now. But I will try.
@tp227 @w39865008 I have successfully run this framework. I download the repository to make all files are updated. `tf-faster-rcnn/lib/datasets/pascal_voc.py` is the only file I modified. I replaced `self._classes` with the...
@Emma-uestc try to clear the file “default” and "cache".
> That's because they have added empty cells in the json file whereas in the chunk files only cells with content are present. I am facing the same problem too,...
I have the same problem, which are solved when I decrease learning rate to 0.00002.
@crazysal how about the score of task 6a