Commit
•
dca9d69
1
Parent(s):
6efaa31
add: README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
metrics:
|
| 3 |
+
- accuracy
|
| 4 |
+
- mean_iou
|
| 5 |
+
tags:
|
| 6 |
+
- segmentation
|
| 7 |
+
- keras
|
| 8 |
+
- tensorflow
|
| 9 |
+
- cityscapes
|
| 10 |
+
---
|
| 11 |
+
# DeepLabV3-Plus
|
| 12 |
+
|
| 13 |
+
Keras implementation of the DeepLabV3+ model as proposed by the paper [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://arxiv.org/abs/1802.02611)(ECCV 2018).
|
| 14 |
+
The models were trained on the fine-annotations set of the [Cityscapes dataset](cityscapes-dataset.com) for creating presets for [this PR](https://github.com/keras-team/keras-cv/pull/1831) on the `keras-cv` repository.
|
| 15 |
+
|
| 16 |
+
**Weights & Biases Dashboard:** https://wandb.ai/geekyrakshit/deeplabv3-keras-cv
|