search

ShaohuaDong2021 / DPLNet

6 stars 0 forks source link

Effect of the number of learnable token and their dimension #9

Open bqm1111 opened 3 months ago

bqm1111 commented 3 months ago

Do you use the same dimension and number of learnable tokens in every stage? Did conduct any ablation study on how the variation of these hyperparameters affects overall performance?

ShaohuaDong2021 commented 3 months ago

Yes, we used the same dimension and number of learnable tokens in every stage, we conducted the ablation studies for dimension and number of learnable tokens, as shown in Table 6. We did not use the different dimension or number of learnable tokens for different stages.

bqm1111 commented 3 months ago

I dont see you mention about learning rate scheduler. Did you fix the learning rate for the training process? Could you elaborate more on your training process? How did you initialize the learnable token?

ShaohuaDong2021 commented 3 months ago

Yes, we fixed the learning rate and we initialized the learnable token randomly.