DeepLabV3-Plus

Keras implementation of the DeepLabV3+ model as proposed by the paper Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation(ECCV 2018). The models were trained on the fine-annotations set of the Cityscapes dataset for creating presets for this PR on the keras-cv repository.

Weights & Biases Dashboard: https://wandb.ai/geekyrakshit/deeplabv3-keras-cv