deeplab v3+: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Clone or download
Latest commit 8374b35 Dec 29, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
imgs keras-deeplab v3-plus Dec 30, 2018
.gitignore keras-deeplab v3-plus Dec 30, 2018
LICENSE keras-deeplab v3-plus Dec 30, 2018
README.md keras-deeplab v3-plus Dec 30, 2018
extract_weights.py keras-deeplab v3-plus Dec 30, 2018
load_weights.py keras-deeplab v3-plus Dec 30, 2018
model.py keras-deeplab v3-plus Dec 30, 2018

README.md

keras-deeplab-v3-plus

Keras implementation of Deeplab v.3 Model is based on the original TF frozen graph. It is possible to load pretrained weights into this model. Weights are directly imported from original TF checkpoint

Segmentation results of original TF model. Output Stride = 8




This result is obtained as an argmax applied to logits at exit layer
Segmentation results of this repo model with loaded weights and OS = 8
Results are identical to the TF model




Segmentation results of this repo model with loaded weights and OS = 16 Results are still good




How to use this model with custom input shape and custom number of classes:
from model import Deeplabv3
deeplab_model = Deeplabv3((512,512,3), num_classes=4, weighs = 'pascal_voc', OS=8)

After that you will get a usual Keras model which you can train using .fit and .fit_generator methods