Understanding how to label/target tensors for 3D volumes

Thanks for the explanation.

Do you mean I need to threshold the prediction (i.e the probabilities after the activation function (sigmod/softmax)) so as to be one-hot encoded like the target?

Sample code:

def dice_single_channel(probability, truth, activation, eps = 1e-7, squared_pred = False):
    if activation:
        probability = nn.Softmax2d()(probability)

    p = (probability >= .5).float()
    t = (truth).float()

    intersection = (p * t).sum()

    if squared_pred:
        p = p**2
        t = t**2
    return 1-(2.0 * intersection + eps)/ (p.sum() + t.sum() + eps)

batchsize = 2
channel_num = 5
probability = torch.rand(batchsize,channel_num,10,10)

truth = torch.randint(low = 0, high=2, size=(batchsize,channel_num,10,10))
print(probability.sum(), truth.sum())

dice = dice_single_channel(probability, truth, activation=True) 



I’m not sure which implementation I was referring to, but would recommend to take a look at this feature request or this implementation, which don’t use a threshold.