Add mask loss graph

zimmerrol · Apr 13, 2019 · 85fa970 · 85fa970
1 parent eea0373
commit 85fa970
Show file tree

Hide file tree

Showing 3 changed files with 7 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -5,7 +5,13 @@
 This is an implementation of the improved training scheme [Faster Training of Mask R-CNN by Focusing on Instance Boundaries](https://arxiv.org/abs/1809.07069) on Python 3, Keras, and TensorFlow. The code is an extension of the existing implementation of [Mask R-CNN by Matterport](https://github.com/matterport/Mask_RCNN). It can be seen as a fork of the original repository based on [commit cbff80f](https://github.com/matterport/Mask_RCNN/commit/cbff80f3e3f653a9eeee43d0d383a0385aba546b). The model generates bounding boxes and segmentation masks for each instance of an object in the image. It's based on Feature Pyramid Network (FPN) and a ResNet101 backbone. The training speed has been increased by introducing an auxiliary objective.
 
 
-![Instance Mask Visualizations](edge_agreement_head.png)
+![Instance Mask Visualizations](edge_agreement_head_small.png)
+
+
+![Instance Mask Visualizations](mask_loss.jpg)
+
+
+
 
 
 If you like this work and want to use this in your work or research, please cite:

diff --git a/edge_agreement_head_small.png b/edge_agreement_head_small.png
diff --git a/mask_loss.jpg b/mask_loss.jpg