doggywastaken
commited on
Commit
•
70f7a9d
1
Parent(s):
d26715f
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# Leaky V-Net in Pytorch
|
2 |
|
3 |
This is a fork of @Dootmaan's VNet.PyTorch repo, who attempted a faithful recreation of the original V-Net: Fully Convolutional Neural Network for Volumetric Medical Image paper, with as little adaptations as possible.
|
@@ -6,4 +14,4 @@ This repo's model has some minor adaptations to fit it's designated application:
|
|
6 |
|
7 |
* ReLU layers is now the leaky version to allow for more consistent convergence on small training datasets
|
8 |
|
9 |
-
* Final Sigmoid layer has been removed from the network in favour of manual thresholding (for flexibility during testing)
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
datasets:
|
4 |
+
- doggywastaken/manual_breast_segs
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
pipeline_tag: image-segmentation
|
8 |
+
---
|
9 |
# Leaky V-Net in Pytorch
|
10 |
|
11 |
This is a fork of @Dootmaan's VNet.PyTorch repo, who attempted a faithful recreation of the original V-Net: Fully Convolutional Neural Network for Volumetric Medical Image paper, with as little adaptations as possible.
|
|
|
14 |
|
15 |
* ReLU layers is now the leaky version to allow for more consistent convergence on small training datasets
|
16 |
|
17 |
+
* Final Sigmoid layer has been removed from the network in favour of manual thresholding (for flexibility during testing)
|