Too small loss on first epoch

[mlcoop]

I have tried to train on icdar 2015 dataset.
But loss is already 0.06 after firt epoch. Seems not all right @Vipermdl
Could you please help me out?

[novioleo]

I have tried to train on icdar 2015 dataset.
But loss is already 0.06 after firt epoch. Seems not all right @Vipermdl
Could you please help me out?

not enough,i can reach 0.0028

[mlcoop]

@novioleo could you please share your training config like?
-resnet50 or resnet34?
-batch size
-how many epochs did you train?
-didnt you overfit?
-which dataset are you using to train?

[novioleo]

1. not overfit at all.the val loss similar to train loss
2. bs=16
3. resnet50
4. icdar2015
   @AssylCooper

[mlcoop]

@novioleo Thanx
did it take you like weeks to get loss: 0.0028 ?
because it trains really slowly

[novioleo]

@AssylCooper change your learning rate~i don't think it slow.i spend few days to train.

[mlcoop]

@novioleo I'm trained it on icdar2017(7200 images) and now fine-tuning on icdar2015.
Could you please share your weights with 0.0028 loss?
Thanx

[novioleo]

sorry ,i can't
@AssylCooper