Introduction
Requirements
sudo apt-get install libsm6 libxext6 libxrender-dev libyaml-dev libpython3-dev
Tensorflow (2.x) & Tensorflow Addons (optional)
pip install tensorflow-gpu==2.4.0 --upgrade
pip install tensorflow-addons==0.12.0 --upgrade
Installation
pip install tf-semantic-segmentation
Features
- Fast and easy training/prediction on multiple datasets
- Distributed Training on Multiple GPUs
- Hyper Parameter Optimization using WandB
- WandB Integration
- Easily create TFRecord from Directory
- Tensorboard visualizations
- Ensemble inference
Datasets
- Ade20k
- Camvid
- Cityscapes
- MappingChallenge
- MotsChallenge
- Coco
- PascalVoc2012
- Taco
- Shapes (randomly creating triangles, rectangles and circles)
- Toy (Overlaying TinyImageNet with MNIST)
- ISIC2018
- CVC-ClinicDB
Models
- U2Net / U2NetP
- Unet
- PSP
- FCN
- Erfnet
- MultiResUnet
- NestedUnet (Unet++)
- SatelliteUnet
- MobilenetUnet (unet with mobilenet encoder pre-trained on imagenet)
- InceptionResnetV2Unet (unet with inception-resnet v2 encoder pre-trained on imagenet)
- ResnetUnet (unet with resnet50 encoder pre-trained on imagenet)
- AttentionUnet
Losses
- Catagorical Crossentropy
- Binary Crossentropy
- Crossentropy + SSIM
- Dice
- Crossentropy + Dice
- Tversky
- Focal
- Focal + Tversky
Metrics
- f1
- f2
- iou
- precision
- recall
- psnr
- ssim
Activations:
Optimizers:
Normalization
Augmentations
- flip left/right
- flip up/down
- rot 180
- color