Added Focal tversky loss #932
Conversation
There was a problem hiding this comment.
Hi @Aditi-Mhatre, thanks for adding a new loss function and thank you for adding a test!
I left some comments below, and can you please include the loss to the docs/? Thanks 🤗
| beta: float = 0.5, | ||
| gamma: float = 1.0, | ||
| ): | ||
| assert mode in {BINARY_MODE, MULTILABEL_MODE, MULTICLASS_MODE} |
There was a problem hiding this comment.
Please move the class docstring under __init__ similar to other losses
| output_sum = torch.sum(output, dim=dims) | ||
| target_sum = torch.sum(target, dim=dims) | ||
| difference = LA.vector_norm(output - target, ord=1, dim=dims) | ||
|
|
||
| intersection = (output_sum + target_sum - difference) / 2 # TP | ||
| fp = output_sum - intersection | ||
| fn = target_sum - intersection | ||
|
|
||
| tversky_score = (intersection + smooth) / ( | ||
| intersection + alpha * fp + beta * fn + smooth | ||
| ).clamp_min(eps) |
There was a problem hiding this comment.
As far as I understand we can just call soft_tversky_score here?
| [ | ||
| [[1, 1, 1, 1], [1, 1, 1, 1], 0.0, 1e-5, 0.5, 0.5, 1.0], | ||
| [[0, 1, 1, 0], [0, 1, 1, 0], 0.0, 1e-5, 0.5, 0.5, 1.0], | ||
| [[1, 1, 1, 1], [0, 0, 0, 0], 1.0, 1e-5, 0.5, 0.5, 1.0], | ||
| [[1, 0, 1, 0], [0, 1, 0, 0], 1.0, 1e-5, 0.5, 0.5, 1.0], |
There was a problem hiding this comment.
Can you please add a test case with gamma != 1?
There was a problem hiding this comment.
Hi @qubvel, thanks a lot for your comments ! Since @zifuwanggg mentioned that the loss function is already implemented I'll close this pull request
|
The focal Tversky loss has already been implemented. |
|
Indeed 😄 missed it, probably a documentation issue! Thanks for pointing it @zifuwanggg |
Hi,
Added:
Changed:
Maybe you can take a look at it.