erichhhhho
erichhhhho
@howard-mahe May I ask why > remains that the first layers modifications (three 3x3 conv in PSPNet instead of 7x7 conv in ResNet) What's the problem of using the 7x7?
check the target is between 0 - N-1 #154
@lfdeep Hi, I met the similar problem. I was wondering how you solved this. Thank you
> Hi, you can try `python main.py --train --dataset cityscapes --exp lr1e-2_crop769_batch20_lastmult10 --epochs 480 --base_lr 0.01 --crop_size 769 --batch_size 20 --last_mult 10`, which should get >76 mIOU, which is ~1...
@Ethanwl Also, I noticed that in [GCC_cl/config.py line 23](https://github.com/gjy3035/C-3-Framework/blob/python3.x/results_reports/VGG_decoder/GCC_cl/config.py#L23): `__C.NET = 'Res50' #` Which is mismatched from the txt result, and `__C.NET` should be `VGG_DECODER`. I doubted that the result...
@yuzehui1996 Hi, did you solve the pred problem for vgg-decoder in SHHB?
@chenyzh28 you can use the cityscapes colormap, this code uses a different color map. see get_palette()
Refer to [here](https://github.com/mcordts/cityscapesScripts/blob/master/cityscapesscripts/helpers/labels.py) Column Color
I was wondering if the multiplication of T square is really helpful? Because if T=20, the soft loss will dominate the total loss. And there is no need to add...
@HisiFish Have you solve this problem? Is it possible to compute the teacher output from the same input? --Updated-- Actually, it helps increasing the acc by 0.10-0.20%.