DataBlock for segmentation

Part 1 (2020)
1

I am working on a segmentation task, where my original images and masked images are in separate folder namely images and segmentation. I tried to build the DataBlock with the code,

tree = DataBlock(blocks = (ImageBlock() , ImageBlock()), 
                 get_items = get_image_files , 
                 splitter = RandomSplitter(valid_pct= 0.2), 
                 item_tfms = Resize(224), 
                 get_x = get_img,
                 get_y = get_seg)

tree.summary('data/train')

This is how I built my learner and dls:

# Dataloaders 
dls = tree.dataloaders('data/train/' , bs=8)
dls.c = 1

# Learner 
learn = unet_learner(dls, resnet18 , n_out= dls.c , loss_func= nn.MSELoss() , metrics = dice)

The loss function I am using is Dice but when I fit the model, I am getting an assertion error.

Screenshot 2021-07-24 at 10.56.13 PM
Screenshot 2021-07-24 at 10.56.13 PM813×733 110 KB

I am not sure what I am doing wrong, can anyone help me with this?

2

If you’re doing segmentation, should you not use the MaskBlock? Why are you using the ImageBlock in this instance?

Some segmentation resources:

3

Because I have the segmented images in a separate folder itself. I can only use MaskBlock() if I have a mask function right?
I am not sure sorry!

6

Ok I think (not totally sure) that if your segmented images are in a separate folder, you need a label_func which can map from the input image path to the output image path.

def label_func(o):
     """ takes in a file as found from `get_image_files`
         and maps to the path name of the segmented image 
     """
     return Path("segmented_images") / o.name # or whatever is right for your directory setup. 

DataBlock(blocks=(ImageBlock, ImageBlock),
        splitter=RandomSplitter(0.2, seed=42),
        get_items=get_image_files,
        get_y=label_func,)
7

Hey @idraja yup I did that everything works fine, but I get an error when I use Dice metric.

Not sure how to solve this.

8

Hey @lukemshepherd yup it Dice is a metric sorry about that.

If I didnt use this metric my model runs smoothly, but using Dice as a metric bringing some assertion errors.

This is how I built my learner,

learn = unet_learner(dls= tree , arch = resnet18 , loss_func= loss_gen , norm_type= NormType.Weight , 
                     self_attention = True , y_range = y_range , metrics = [Dice)])
10

Tbh you were right, the assertion error was because I was using ImageBlock for my target block but the dice function expects a TensorMask (1D).

I got the metric from here Metrics | fastai

Trying out different things, but the pain point is I have my segmented images in a separate folder. Thanks for your answer, it really helps and now I was able to figure out where I was wrong.

12

There are several steps that need to be followed in order to create data blocks.

The steps are defined by the data block API. They can be asked in the form of questions while looking at the data:

  1. What is the types of your inputs/targets?
  2. Where is your data?
  3. Does something need to be applied to inputs?
  4. Does something need to be applied to the target?
  5. How to split the data?
  6. Do we need to apply something on formed items?
  7. Do we need to apply something on formed batches?
    This is it!!

dgcustomerfirst