Open ewrfcas opened 3 years ago
Here is the log
Hello, did you use bicubic downsampling kernel?
In addition, it seems that restoration_inference
did not normalize the images from [-1, 1] back to [0, 1]. As a workaround, you can normalize the output in your backbone by using output = (output + 1) / 2.0
and see how the results look. I will see how to modify restoration_inference
later.
Same issue here. In my case, the max value of output
exceeds 1 and the min value is greater than 0.
Hello, did you use bicubic downsampling kernel?
In addition, it seems that
restoration_inference
did not normalize the images from [-1, 1] back to [0, 1]. As a workaround, you can normalize the output in your backbone by usingoutput = (output + 1) / 2.0
and see how the results look. I will see how to modifyrestoration_inference
later.
I am sorry that it seems that this is not the problem. The code should have normalized it back to [0, 1].
I just tried two images in CelebA-HQ and they work fine. Could you please try the images in CelebA-HQ? Please note that MATLAB imresize
should be used for downsampling.
How about trying the images here? These two images work fine on my side.
How about trying the images here? These two images work fine on my side.
Hi, I have tried your images with command
python demo/restoration_demo.py configs/restorers/glean/glean_ffhq_16x.py \
pretrain/glean_ffhq_16x_20210527-61a3afad.pth \
00001.png \
results/00001.png \
--device 1
But the output is still poor.
Is it because of my wrong usage? Thank you
I used this command:
python demo/restoration_demo.py configs/restorers/glean/glean_ffhq_16x.py https://download.openmmlab.com/mmediting/restorers/glean/glean_ffhq_16x_20210527-61a3afad.pth ./00001.png outputs/00001.png
Did you modify the codes?
Here are my results: results.zip
Still fails with bicubic resizing and data rescaling to [0,1]. Here is the code in restoration_inference.py Failed results.
Still fails with bicubic resizing and data rescaling to [0,1]. Here is the code in restoration_inference.py Failed results.
How about removing data['lq'] = (data(['lq'] + 1) / 2)
. When adding this line, the input to the network would be [0, 1], which is incorrect.
I used the latest version of MMEditing codes without any modifications.
The output should be converted back to [-1,1]?
The output should be converted back to [-1,1]?
The code will handle the conversion itself. There is no need to modify the code. The original code will do.
Still fails with bicubic resizing and data rescaling to [0,1]. Here is the code in restoration_inference.py Failed results.
How about removing
data['lq'] = (data(['lq'] + 1) / 2)
. When adding this line, the input to the network would be [0, 1], which is incorrect.I used the latest version of MMEditing codes without any modifications.
Sorry, I am confused for the input range. Which is the correct value range, [0,1] or [-1,1]?
Still fails with bicubic resizing and data rescaling to [0,1]. Here is the code in restoration_inference.py Failed results.
How about removing
data['lq'] = (data(['lq'] + 1) / 2)
. When adding this line, the input to the network would be [0, 1], which is incorrect. I used the latest version of MMEditing codes without any modifications.Sorry, I am confused for the input range. Which is the correct value range, [0,1] or [-1,1]?
The inputs and outputs of GLEAN will be [-1, 1]. But you do not need to modify the code, as I have implemented the conversion.
Still fails with bicubic resizing and data rescaling to [0,1]. Here is the code in restoration_inference.py Failed results.
How about removing
data['lq'] = (data(['lq'] + 1) / 2)
. When adding this line, the input to the network would be [0, 1], which is incorrect. I used the latest version of MMEditing codes without any modifications.Sorry, I am confused for the input range. Which is the correct value range, [0,1] or [-1,1]?
The inputs and outputs of GLEAN will be [-1, 1]. But you do not need to modify the code, as I have implemented the conversion.
Thanks. I use the original codes to test the image given above, but the result is still failed.
I am able to reproduce your error just now. Please remove --device 1
. I will investigate why and please remove it for the moment.
Thanks, removing device
works! It seems that the data and the model are placed on different devices. If I set the CUDA_VISIBLE_DEVICES
in the very beginning, the demo can also work fine when --device
is set to other GPUs.
I am able to reproduce your error just now. Please remove
--device 1
. I will investigate why and please remove it for the moment.
Nice,it works. Maybe the model failed to load weights properly with --device?
It may be, thank you for letting me know :) I will look into the problem~
I will keep this issue open for the moment in case others encounter this problem. Thanks again.
Hi, I have tried GLEAN in mmediting for 64->1024 face SR. But the generated results are very poor. My command is python restoration_demo.py configs/restorers/glean/glean_ffhq_16x.py workdirs/glean_ffhq_16x_20210527-61a3afad.pth tests/data/1009.png preds/1009.png --device 2
My input is 64x64 face image and the output is