@longcw @cory8249 @crazylyf I am planing to train the YOLO2 on the SynthText dataset, so when I prepare the dataset, I need to resize the image into 416416 and rearrange the channel to make sure the shape of the image is 3416*416, right? Besides these work, are there any other work I need to do?
@longcw @cory8249 @crazylyf I am planing to train the YOLO2 on the SynthText dataset, so when I prepare the dataset, I need to resize the image into 416416 and rearrange the channel to make sure the shape of the image is 3416*416, right? Besides these work, are there any other work I need to do?