Surayuth

If you use Dataloader, the simplest way is to change the _batch_size_ to the size of your dataset. Be sure that you have enough memory to do that.

The coordinates of all centers are a constraint, by default, within [-1, 1]. This means the length of the side of each grid is [1 - (-1)]/N = 2/N where...

Those values are used to normalize the inputs, which are ground truths(gt) and low-resolution images(inp), of the model(feature extracter)​. As you can see, inp: {sub:[0.5], div: [0.5]} means the low-resolution...

Edit ResidualBlock in basic_layers.py by replacing all / with //. For example, in line 16, you should write as ``` self.conv1 = nn.Conv2d(input_channels, output_channels//4, 1, 1, bias = False) ```

@makseq Hello! Sorry for the late reply. Below is an example. I need to label each button. All of them have the same size. So, I want to know if...

I think you are doing it the right way. That line exists to prepare to input tensor for RAP where its size depends on the number of classes.

Is the code working correctly? I want to use it in my code.

@andreped Thanks for a quick reply and your improvement. I want to use this method in my project too but I also need the whole process to be differentiable which...

Yes. I would like to use this to extract a saliency map instead of using existing CNN (i.e., UNet, ...) because I don't have many images for training my model.

Thanks for pointing it out. I just want to extract the stained area unsupervised but I don't have enough images to train the model. The stain variation is too much...