Hi,
I would like to know whether or not it is possible to train the retinanet model without an FPN? How would I achieve this? I thought about changing the retinanet function in retinanet.py line 257 but it is listed there that this is the minimum model necessary for training.
Thanks in advance!
Hi, I would like to know whether or not it is possible to train the retinanet model without an FPN? How would I achieve this? I thought about changing the retinanet function in retinanet.py line 257 but it is listed there that this is the minimum model necessary for training. Thanks in advance!