Different result in disjoint 15-5s setting.
kona419 opened this issue · comments
Hello,
I am trying to reproduce disjoint 15-5s setting.
But my result is very different from yours.
My command is :
/home/nayoung/nayoung/MiB/run.py --data_root '/home/nayoung/nayoung/' --batch_size 10 --dataset voc --name MIB --task 15-5s --step 0 --lr 0.01 --epochs 30 --method MiB
for step1~5 :
/home/nayoung/nayoung/MiB/run.py --data_root '/home/nayoung/nayoung/' --batch_size 10 --dataset voc --name MIB --task 15-5s --step 5 --lr 0.001 --epochs 30 --method MiB
I used batch size 10 becuz of cuda memory, and I didn't used the pretrained model.
Also I set the loss_kd=100.
background | aeroplane | bicycle | bird | boat | bottle | bus | car | cat | chair | cow | diningtable | dog | horse | motorbike | person | pottedplant | sheep | sofa | train | tvmonitor |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.857241 | 0.596404 | 0.249615 | 0.489829 | 0.336007 | 0.254114 | 0.694971 | 0.631736 | 0.539938 | 0.124421 | 0.380302 | 0.230107 | 0.470491 | 0.438303 | 0.5446194 | 0.615698 | |||||
0.822046 | 0.571647 | 0.246822 | 0.475479 | 0.322084 | 0.202237 | 0.607911 | 0.599167 | 0.515914 | 0.123029 | 0.300344 | 0.230606 | 0.447299 | 0.413728 | 0.5464546 | 0.603189 | 0.06315 | ||||
0.812532 | 0.53895 | 0.238265 | 0.418296 | 0.236745 | 0.17652 | 0.540683 | 0.536196 | 0.477998 | 0.089279 | 0.28096 | 0.100062 | 0.383524 | 0.36603 | 0.5146568 | 0.589685 | 0.056601 | 0.065537 | |||
0.523217 | 0.503853 | 0.216371 | 0.287688 | 0.198159 | 0.151194 | 0.494373 | 0.503627 | 0.455402 | 0.093359 | 0.119011 | 0.123516 | 0.33748 | 0.289346 | 0.5154741 | 0.565243 | 0.049754 | 0.061803 | 0.035291 | ||
0.424163 | 0.464728 | 0.215501 | 0.285088 | 0.162308 | 0.139302 | 0.465628 | 0.475487 | 0.407798 | 0.062629 | 0.131808 | 0.035045 | 0.331196 | 0.272611 | 0.4768657 | 0.551702 | 0.04413 | 0.06458 | 0.030589 | 0.110248 | |
0.303423 | 0.404756 | 0.196714 | 0.210973 | 0.101944 | 0.115709 | 0.366374 | 0.38747 | 0.39362 | 0.044943 | 0.073729 | 0.031481 | 0.310951 | 0.23618 | 0.4594278 | 0.545644 | 0.04088 | 0.061531 | 0.026771 | 0.092094 | 0.020551 |
class mIoU | 0.51339 | 0.227215 | 0.361226 | 0.226208 | 0.173179 | 0.528324 | 0.522281 | 0.465112 | 0.08961 | 0.214359 | 0.125136 | 0.380157 | 0.336033 | 0.5095831 | 0.578527 | 0.050903 | 0.063363 | 0.030884 | 0.101171 | 0.020551 |
1-15 : 0.350022
16-20 : 0.053374
all : 0.27586
Hey! Probably you get different results due to a different batch size...
This setting is particularly challenging due to the non-i.i.d. data, so probably decreasing the BS hampers the performances.
Hey! Probably you get different results due to a different batch size... This setting is particularly challenging due to the non-i.i.d. data, so probably decreasing the BS hampers the performances.
Thank you for the reply.
Because of my GPU memory, my batch size has a limit.
So could you recommend other hyperparameters(ex. learning rate, weight decay) for the low batch size to follow the paper's result?
I actually never tried with a lower batch size. The main issue is using a low batch size in the 15-1 increasing the non i.i.d.-ness of data (you may try to use Batch Renormalization in place of BN as in my https://arxiv.org/abs/2012.01415, but it may alter - in positive - the results).
As a rule of thumb, you may double the iteration and halve the learning rate but I won't guarantee it will work.
I actually never tried with a lower batch size. The main issue is using a low batch size in the 15-1 increasing the non i.i.d.-ness of data (you may try to use Batch Renormalization in place of BN as in my https://arxiv.org/abs/2012.01415, but it may alter - in positive - the results).
As a rule of thumb, you may double the iteration and halve the learning rate but I won't guarantee it will work.
Thank you for sharing~!
I will try with your recommendation.