DSRL

DSRL copied to clipboard

feature viualization

1

Hi, nice to see that you have replicated the implementation. Have you done the visualization of features for the decoders of both branches? Maybe checking the feature map would help...

wl082013

SISR

2

Hello, maybe SISR is following "Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network" with Sub-Pixel convolution ?

XinruiYuan

Regarding your final experiment setting

1

Hi there, Thanks for sharing your codes. I wonder if the experience setting in your current train.py can achieve mIoU=0.6768 on Cityscapes. Like with deeplab v3 as SSSR backbone, init_lr=0.005...

SuperStacie

some questions about datasets

1

tks for ur work. i have git clone ur code, and got some trouble on the datasets. e.g: while i run the __main__ in 'cityscapes.py' it print the right picture,...

lions-heart

deeplab.py line 80

2

为什么返回时将x_sr_up重复了两次呢？

L1Uc

I can't find the test file or the code

wjxxyz

怎么在推理阶段把超分分支删除啊

2

可以给一个推理阶段的代码吗

rtrtfs

Some problem about Data processing during training with Cityscapes

3

I encountered the following issues during training： > Traceback (most recent call last): > File "/data2/zixuan/DSRL-subpixel/train.py", line 313, in > main() > File "/data2/zixuan/DSRL-subpixel/train.py", line 306, in main > trainer.training(epoch)...

ghost

PixelShuffle or ConvTransposed ?

1

请问您实测哪个性能更好呢？ 能否提供两个分支的实验结果呢？

kaigelee

How can I use pretrained weights uploaded on GoogleDrive?

5

Hi ! Thank you for sharing your DSRL codes. I wonder how I can use retrained weights uploaded on your GoogleDrive. Do I just download it and type train.py --resume...

KaSangeun