I am trying to train a deep learning model to identify weeds from images. When I try to train the model using the Image Chips I got from exporting the training data, I get "Error: division by zero. Training was not successful." I found on Arc's site that the solution was making sure my input data has more than one unique value and has JSON file type. It has both, I am not sure where to go from here.
@MathewMyroniuk I see you're using a batch size of 64 and validation % - 10. Can you share a screenshot of the stats.txt file from your training data?.. Here is an example of my stats.txt file
Hello, please I am having a similar issue here, I am using CPU and not GPU for this processing. I am aware the CPU can be used. I have reduced batch sizes from 16-12-8-4-2 yet unsuccessful. I will appreciate solutions achieved by anyone who has encountered this before. Thank you
@Omoige23 I have posted on your other post. BTW, this thread and your issue seem different. Not guaranteed but creating a new post might have gotten attention sooner.