Fast_SCNN based on the original config yaml cannot reproduce the mIoU?

[nemonameless]

Without any change, I train with 8 gpus but only get 59.0 mIoU on cityscapes. But using your trained fast_scnn_segmentron.pth can reproduce 68.9
Did you change something later about the config yaml?

Thanks for your nice work!

[LikeLy-Journey]

so your batch size is 12 * 8? I only use batch 12 with 1 gpus which is consistent with paper.

[pawopawo]

so your batch size is 32? I only use batch 12 with 3 gpus which is consistent with paper.

The BATCH_SIZE in the config file refers to the total batch_size or the batch_size on each gpu? My understanding is that this parameter is the batch_size on each gpu

[LikeLy-Journey]

so your batch size is 32? I only use batch 12 with 3 gpus which is consistent with paper.

The BATCH_SIZE in the config file refers to the total batch_size or the batch_size on each gpu? My understanding is that this parameter is the batch_size on each gpu

you are right, it is the batch_size on each gpu, i updated my reply. so only need 1 gpus to make total batch size be 12.

[pawopawo]

so your batch size is 32? I only use batch 12 with 3 gpus which is consistent with paper.

The BATCH_SIZE in the config file refers to the total batch_size or the batch_size on each gpu? My understanding is that this parameter is the batch_size on each gpu

you are right, it is the batch_size on each gpu, i updated my reply. so only need 1 gpus to make total batch size be 12.

Thank you for your reply. Are all the parameters in the configs file trained by 1 gpu by default?

[nemonameless]

so your batch size is 32? I only use batch 12 with 3 gpus which is consistent with paper.

The BATCH_SIZE in the config file refers to the total batch_size or the batch_size on each gpu? My understanding is that this parameter is the batch_size on each gpu

you are right, it is the batch_size on each gpu, i updated my reply. so only need 1 gpus to make total batch size be 12.

Only one GPU training and bs=12 is so slow, If I train with 4 GPUs and thus the batchsize=48? Any else should I change to reproduce 68.9 by training with 4gpus and bs=48 ?

[LikeLy-Journey]

so your batch size is 32? I only use batch 12 with 3 gpus which is consistent with paper.

The BATCH_SIZE in the config file refers to the total batch_size or the batch_size on each gpu? My understanding is that this parameter is the batch_size on each gpu

you are right, it is the batch_size on each gpu, i updated my reply. so only need 1 gpus to make total batch size be 12.

Only one GPU training and bs=12 is so slow, If I train with 4 GPUs and thus the batchsize=48? Any else should I change to reproduce 68.9 by training with 4gpus and bs=48 ?

you can set batch_size=3 in config file, and use 4gpu to keep total batch size=12

[LikeLy-Journey]

so your batch size is 32? I only use batch 12 with 3 gpus which is consistent with paper.

The BATCH_SIZE in the config file refers to the total batch_size or the batch_size on each gpu? My understanding is that this parameter is the batch_size on each gpu

you are right, it is the batch_size on each gpu, i updated my reply. so only need 1 gpus to make total batch size be 12.

Thank you for your reply. Are all the parameters in the configs file trained by 1 gpu by default?

no, i only trained 3 or 4 models. i think keep total batch size=12~16 will be ok.

[nemonameless]

so your batch size is 32? I only use batch 12 with 3 gpus which is consistent with paper.

The BATCH_SIZE in the config file refers to the total batch_size or the batch_size on each gpu? My understanding is that this parameter is the batch_size on each gpu

you are right, it is the batch_size on each gpu, i updated my reply. so only need 1 gpus to make total batch size be 12.

Only one GPU training and bs=12 is so slow, If I train with 4 GPUs and thus the batchsize=48? Any else should I change to reproduce 68.9 by training with 4gpus and bs=48 ?

you can set batch_size=3 in config file, and use 4gpu to keep total batch size=12

I mean bs=12 training is so slow, I just want train with larger batchsize . If I use bs=48 (12*4) and change lr=0.045x4 , can I reproduce 68.9?

[LikeLy-Journey]

so your batch size is 32? I only use batch 12 with 3 gpus which is consistent with paper.

The BATCH_SIZE in the config file refers to the total batch_size or the batch_size on each gpu? My understanding is that this parameter is the batch_size on each gpu

you are right, it is the batch_size on each gpu, i updated my reply. so only need 1 gpus to make total batch size be 12.

Only one GPU training and bs=12 is so slow, If I train with 4 GPUs and thus the batchsize=48? Any else should I change to reproduce 68.9 by training with 4gpus and bs=48 ?

you can set batch_size=3 in config file, and use 4gpu to keep total batch size=12

I mean bs=12 training is so slow, I just want train with larger batchsize . If I use bs=48 (12*4) and change lr=0.045x4 , can I reproduce 68.9?

i have not tried this hyper parameters.

[y-kl8]

hi, I see you get the trained model, dou you know where can i obtain the trained cityscapes_deeplabv3_plus_mobilenet model?

[LikeLy-Journey]

hi, I see you get the trained model, dou you know where can i obtain the trained cityscapes_deeplabv3_plus_mobilenet model?

https://github.com/LikeLy-Journey/SegmenTron#real-time-models
https://github.com/LikeLy-Journey/SegmenTron/releases