Closed zhangyahu1 closed 3 years ago
Thanks for sharing your nice work!
I am trying to retrain your model on TED dataset, and run the command:
CUDA_VISIBLE_DEVICES=0,1 python run.py --config config/ted384.yaml --device_ids 0,1
With
Batch_size = 8, num_epochs: 100, num_repeats: 150, input: image with png format.
It seems the training process will take more than 7 days. May I know how long did you take? Thanks.
@AliaksandrSiarohin Is this the same setting reported in the paper? Otherwise it takes too long for training even with 2 GPUs.
Setting is the same, except the bs. We trained on 8 gpus, around 2-3 days.
Thanks!
Thanks for sharing your nice work!
I am trying to retrain your model on TED dataset, and run the command:
With
It seems the training process will take more than 7 days. May I know how long did you take? Thanks.