CornerNet
CornerNet copied to clipboard
training on my own pictures
If I want to train the model with my own images,how can I get the json file of annotations,such as instances_minival2014.json,instances_testval2014.json and instances_trainval2014.json?
There's an alternative to preparing JSON files.
You can change the _load_data
function in db/coco.py
to read your own dataset. self._image_ids
is a list of image names, while self._detections
is a dictionary where the keys are the image names and the values are the bounding boxes and category ids.
how to change the _load_data function in db/coco.py? just need to save your image file names to the _image_ids variable and just set _detections to be an empty list. i can not understand.
e
do you know how to change the function _load_data?i am in the same case as you.thank you!
How to display the test result of single picture?