Hi, Thank you for your works.
I trained your network on custom dataset (the training dataset is about 200, only one object per image with one category), and I found that all the test outputs are HBB, but the traing image and testing image have rotated object.
I checked the training dataset and it's annotation is correct.
In addtion, I observed that the main part of loss is the 'wh' loss, about 3~5.
Do you have any suggestions to fix the problem?
Some Info:
4 * GTX3080Ti
batch_size=20
epoch=200
image shape is (width:2446, height:2048, channel:3)
Hi, Thank you for your works. I trained your network on custom dataset (the training dataset is about 200, only one object per image with one category), and I found that all the test outputs are HBB, but the traing image and testing image have rotated object. I checked the training dataset and it's annotation is correct. In addtion, I observed that the main part of loss is the 'wh' loss, about 3~5. Do you have any suggestions to fix the problem?
Some Info: