star4s

I would like to run the super resolution program, matlab code, in c++. Is it possible?

2

Hello. I am training by 16, 32, 64 batchSize for the big size image super resolution. Ihave one more question about c++ generating from a matlab code. How to generate...

I have a question again about Dual GPU for your Program.

2

I have a question again about Dual GPU for your Program. I alreay set Dual GPU, two Geforce 1080 ti. Can I use the Dual GPU on your program, Super...

Hello. Long time no see. I tried using the 1080TI(11GB) for the Super Resolution.

2

Hello. Long time no see. I tried using the 1080TI(11GB) for the Super Resolution. Size of my Images is 1120 * 1450 and the number of Images is 457. After...

Hello. I got some problem when I run the Cuda_SRCNN for big size images.

4

Hello. I got some problem when I run the Cuda_SRCNN for big size images. When I try running the Cuda_SRCNN for 654 * 664 size image, the neural network for...

How are you? I am still running your program. I got a problem.

2

How are you? I am still running your program. I got a problem. Every time I should run "gpu_compile.m" before I start "testSRnet_result.m". When I start Matlab, I need to...

I have one more question about "train objective" and "val objective" in result after training by running "train_SRnet.m"

1

I have one more question about "train objective" and "val objective" in result after training by running "train_SRnet.m" After I take training by running "train_SRnet.m", I got a bottom graph...

I have one more question about stride.

3

I have one more question about stride. When I read the reference paper, "Image Super-Resolution Using Deep Convolutional Networks" on 6 page, it mentioned about 24,800 sub-images, which are extracted...

What are the stride and the padding in options of SRnet.m ? ==================================================== conv2_1Block = dagnn.Conv('size',[9 9 3 64],'hasBias',true,'stride',[1,1],'pad',[0,0,0,0]); net.addLayer('conv2_1',conv2_1Block,{'input'},{'conv2_1'},{'c2_1f','c2_1b'}); net.addLayer('relu2_1',reluBlock,{'conv2_1'},{'conv2_1x'},{}); conv2_2Block = dagnn.Conv('size',[5 5 64 32],'hasBias',true,'stride',[1,1],'pad',[0,0,0,0]); net.addLayer('conv2_2',conv2_2Block,{'conv2_1x'},{'conv2_2'},{'c2_2f','c2_2b'}); net.addLayer('relu2_2',reluBlock,{'conv2_2'},{'conv2_3x'},{}); conv2_3Block...

If I would like to set up the filter size, 9-5-5, should I change on "SRnet.m"?

1

conv2_1Block = dagnn.Conv('size',[9 9 3 64],'hasBias',true,'stride',[1,1],'pad',[0,0,0,0]); net.addLayer('conv2_1',conv2_1Block,{'input'},{'conv2_1'},{'c2_1f','c2_1b'}); net.addLayer('relu2_1',reluBlock,{'conv2_1'},{'conv2_1x'},{}); conv2_2Block = dagnn.Conv('size',[1 1 64 32],'hasBias',true,'stride',[1,1],'pad',[0,0,0,0]); net.addLayer('conv2_2',conv2_2Block,{'conv2_1x'},{'conv2_2'},{'c2_2f','c2_2b'}); net.addLayer('relu2_2',reluBlock,{'conv2_2'},{'conv2_2x'},{}); conv2_3Block = dagnn.Conv('size',[5 5 32 3],'hasBias',true,'stride',[1,1],'pad',[0,0,0,0]); net.addLayer('conv2_3',conv2_3Block,{'conv2_2x'},{'prediction'},{'c2_3f','c2_3b'}); ================================================================== Top is your code in "SRnet.m"....

I have one more question about upscaling factors when I take image training.

1

I have one more question about upscaling factors when I take image training. I cannnot find upscaling factors. How can I tuning upscaling factors in the program? What do you...