Shenghao.Yu

@MStumpp do you want to set the temporal stride like 16, 8 ? you can look into slowfastnet.py/class slowfast / forward find code like this slow = self.SlowPath(input[:, :, ::16,...

@tomanick The top 1 accuracy became about 94% is the train accuracy for training from scratch ? And since you use ReduceLROnPlateau as your lr_schedular, how did you get the...

window10 1 install Visual Studio 2019 or higher version 2 git clone https://github.com/gen-ko/lanms-neo.git 3 python setup.py install

@yhjo09 Sorry to interrupt, but the original model link is no longer valid （https://www.dropbox.com/s/5r6cy0x72s8x9yf/latest_net_G.pth?dl=0） i got a 404 error，can you share this file to me emali: [email protected] ? thank you...

@Wolfybox can you show some train detail? like init learning optimizer totoal_epoch? i am re-implement this paper in this week. since the author write code : gt_labels[8:-7] i suppose he...