Closed matln closed 3 years ago
Hi, in fact, the reported result is based on single GPU and augdropout is used, but runStandardXvector-voxceleb1.py is a baseline configuration with Softmax loss. For small dataset like voxceleb1, the regularizations (weight decay and dropout) are very useful to improve the generalization of model. Just forget the history results in runStandardXvector-voxceleb1.py and a much better result 2.6% is given in https://github.com/Snowdar/asv-subtools#1-voxceleb-recipe-speaker-recognition. Note that, there seems a bad problem/bug w.r.t my experiments between specaugment and multi-GPU. So suggest that do not use multi-GPU to run specaugment training for the time being.
Thanks for your advice! I will use specaugmnet
for further experiments.
Hi @Snowdar I cannot understand the relationship between specaugment and multi-GPU training. To my knowledge, the specaugment only happens in getitem of class ChunkEgs, which has nothing to do with smulti-GPU sampler...
Thanks for any help! Junjie
I guess the problem is utils.set_all_seed(1024)
since ddp will spawn processes independently. If you set random seed, all randomness in specaugment is the same for all processes.
Yeah, it is this problem about seed.
在 2021年8月2日,下午5:16,JUNJIE JIN @.***> 写道:
I guess the problem is utils.set_all_seed(1024) since ddp will spawn processes independently. If you set random seed, all randomness in specaugment is the same for all processes.
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.
I try to train the standard xvector model on VoxCeleb1 trainset using the script
runVoxceleb.sh
with 4 GPUs. And I completely use the default parameters inrunStandardXvector-voxceleb1.py
except for the weight decay changed to5e-1
(I also tried3e-1
), but the result EER is only3.531%
for 21 epoch far embedding with PLDA backend. Unable to achieve3.028%
reported at the bottom ofrunStandardXvector-voxceleb1.py
. Is there something I overlooked or what I need to modify?