Matt Pokorny
Matt Pokorny
@shalin51 Does that mean that new walk function should be: def walk(self, size): if self.eof: return None end_point = self.offset + 4 * (44948600- 44948596 ) assert end_point
File I/O with Colab is pretty brutal. Are you mounting your drive folder?
@aaobscure e.g. flow --lr 0.01
@aaobscure sorry if it wasn't clear. it should be something like this, if you're attempting to train custom weights: ``` !python flow --model cfg/tiny-yolo-voc-1c.cfg \ --load bin/tiny-yolo-voc.weights \ --train \...
Yeah cv2 won't throw an error when reading in an image even if an image actually isn't there. Probably why the error did appear once it went through cvtColor.
If it's only a few, I'd recommend writing a quick script to figure out which ones and remove them