Hi I am trying to train SSD -mobilenet in-order to detect 13 classes. I also trained a faster rcnn -resnet101 .
My training data images have resolution of 265 * 450 . (most of them) and each class had 400 images.
Then this weird thing happened faster rcnn converged faster with batch size of 1 .
But my SSD didn't . It's not converging at all . Here I will put the two graphs ,
Purple - Faster Rcnn | resnet101
Blue - SSD | mobilenet
I have seen some have trained this for few classes and obtained good results . If anyone have obtained good results please answer following .
You had only one class , so How fast it converged ?
What do you think , the network is suffering from vanishing gradents problem or local minima problem ?
Editing - Here I will update the mAp for each category plot .
See Question&Answers more detail:
os 与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…