Darknet: I train the network for 9000 iterations, If I add in more images, should I re-train from scratch or continue?
I trained the network using a dataset after 9,000 iterations. I collected more images and added them into my dataset, should I re-train the network from scratch? or can I just keep training using the weight from 9000th iteration?
sensationTI
All 4 comments
If the classes were not changed, keep training with the saved weights. Your initial mAP differs from the previous dataset but it will be adjusting after some epochs with the new samples.
Yogerlan
on 4 Aug 2020
If the classes were not changed, keep training with the saved weights. Your initial mAP differs from the previous dataset but it will be adjusting after some epochs with the new samples.
If some objects in my newly collected images are not labeled, and I feed it into the network. Will it make any effect on the training result?
sensationTI
on 4 Aug 2020
Yes. Images with no labels negative samples.
AnchorAnalytics
on 5 Aug 2020
@sensationTI Note that images with desired objects without labels are not negative samples. They would impact your training and could confuse your model.
Mahdi89
on 9 Sep 2020
Related issues
qianyunw
路
3Comments
Mididou
路
3Comments
Jacky3213
路
3Comments
Cipusha
路
3Comments
bit-scientist
路
3Comments
Most helpful comment
If the classes were not changed, keep training with the saved weights. Your initial mAP differs from the previous dataset but it will be adjusting after some epochs with the new samples.