Closed rawalkhirodkar closed 3 years ago
@rawalkhirodkar I got 75.6, but the performance is still worse than the stated.
Besides, the reproduced result of DDRNet-23 is low.
@rawalkhirodkar @ShihuaHuang95 ,i just train with 2*3080 gpus with the config files. i use the official imagenet pretrained model. Nothing else has been changed.
I think this has to do with the learning rate updates. num_iters_per_epoch is a function of number of gpus which in turn controls the learning rate decay.
Training for longer (1500 epochs) with 8 GPUs reproduces the OWN performance with FLIP mentioned in the README.
Thanks.
I think this has to do with the learning rate updates. num_iters_per_epoch is a function of number of gpus which in turn controls the learning rate decay.
Training for longer (1500 epochs) with 8 GPUs reproduces the OWN performance with FLIP mentioned in the README.
Thanks.
Are you use the same config, when train 1500 epoch with 8 GPUs reproduces the OWN performance? or you have changed something? I would really appreciate your help. Thank you.
这是来自QQ邮箱的假期自动回复邮件。 您好,我最近正在休假中,无法亲自回复您的邮件。我将在假期结束后,尽快给您回复。
Hello, Thank you for the great work!
I am trying to reproduce the results of ddrnet-23_slim on Cityscapes val (77.83 mIoU) but could not do it.
Here are the training logs, 600epochs_5gpus_ddrnet23_slim_2021-06-02-20-21_train.txt 600epochs_8gpu_ddrnet23_slim_2021-06-03-09-32_train.txt 1500epochs_2gus_ddrnet23_slim_2021-06-04-18-36_train.txt
I would really appreciate your help. Thank you.