Xception pretrained

[haibochina]

Thank you for your great job! Is there any pretrained model for DFANet?

[LikeLy-Journey]

i have not trained this model

[haibochina]

i have not trained this model

I am training now!

[linbaiwpi]

i have not trained this model

I am training now!

How is your training right now? Using the pre-trained Xception or training from scratch?

[haibochina]

It is still training now！ The result without pretrained model is 59 miou 

发自我的iPhone

------------------ Original ------------------ From: Lin Bai <[email protected]> Date: Sat,Mar 14,2020 9:57 AM To: LikeLy-Journey/SegmenTron <[email protected]> Cc: haibo <[email protected]>, Author <[email protected]> Subject: Re: [LikeLy-Journey/SegmenTron] Xception pretrained (#23)

i have not trained this model

I am training now!

How is your training right now? Using the pre-trained Xception or training from scratch?

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

[haliphinx]

@haibochina Hey, are you training the DFANet on the cityscape dataset? What's your final accuracy and what's the number of epoch in total to achieve that? I trained it from scratch, but it stuck into around 30 miou from epoch 100. Thanks!!

[haibochina]

@haliphinx I just trained XceptionA the way that shufflenet use. and just trained 30000 iterarion, then I trainied DFANet on cityscape, the mIOU is 68.9. https://github.com/megvii-model/ShuffleNet-Series

[haliphinx]

@haibochina Thanks for your reply. The accuracy sounds great! I'm wondering if it's possible to share your pretrained XceptionA model please.