When set num_heads = 1, doesnt train

[abeyang00]

First of all, thank you for the wonderful work. I have a quick question though.

I see you have set num_head = 6, meaning you iteratively update bounding box results 6 times before getting final output.

I wanted to see if i can just use 1 iteration so i set cfg.model.sparsercnn.num_heads = 1

But training does not go well and i get following result

AP only goes upto 3%...

Any suggestion to what i'm doing wrong? should i also set cfg.model.sparsercnn.deep_supervision = false? even though this is same as setting num_heads = 1?

Thank you!

[PeizeSun]

Hi~ Do you change any other codes?

[abeyang00]

@PeizeSun no i didnt change anything else. when i set num_heads=6, it trains well.

Its only when i set num_heads=1, it doesnt train well

[PeizeSun]

when you set num_heads=6, is the final performance the same as our reported performance?

[abeyang00]

In the paper AP is 42.3 but i reproduced 38%. Not the same but close enough.

[PeizeSun]

Do you train on 8GPUs?

[abeyang00]

No, just 1 gpu.

[PeizeSun]

I guess only 1 gpu is the reason for 1 head not working.
The first head of proposal box and features is not dependent on input image, later heads are dependent. So only one head needs large batch size to provide statistic information. Usually training is on 8 gpus and batch size 16. If training on 1 gpu, small batch size can't provide effective statistic information.

[abeyang00]

so if i only have 1 gpu and using 1 iteration head, i can't train the network??

[PeizeSun]

Maybe reducing learning rate could help.

[abeyang00]

thank you, i'll try it.

[QinghangHong1]

First of all, thank you for the wonderful work. I have a quick question though.

I see you have set num_head = 6, meaning you iteratively update bounding box results 6 times before getting final output.

I wanted to see if i can just use 1 iteration so i set cfg.model.sparsercnn.num_heads = 1

But training does not go well and i get following result

AP only goes upto 3%...

Any suggestion to what i'm doing wrong? should i also set cfg.model.sparsercnn.deep_supervision = false? even though this is same as setting num_heads = 1?

Thank you!

Hi,

Your plots look really nice and clean. Could you share how you plot the mAP trend from the log, please? Thank you a lot!