Shortcuts

Examples

Run all examples from this dir.


DL notebooks

  1. features – classification

    • cifar10 classification model

    • Runner usage example

  2. features – segmentation

    • segmentation with unet

    • model training and inference

    • predictions visialization

  3. tutorial – classification

    • dataset preparation (raw images -> train/valid/infer splits)

    • augmentations usage example

    • pretrained model finetuning

    • various classification metrics

    • metrics visualizaiton

    • FocalLoss and OneCycle usage examples

    • class imbalance handling

    • model inference


DL pipelines

  1. features – model training

    • configuration files usage example

    • local and docker runs

    • metrics visualization with tensorboard

  2. features – model training with stages

    • pipeline example with stages

  3. tutorial – classification pipeline

    • classification model training and inference

    • different augmentations and stages usage

    • knn index model example

    • embeddings projector

    • LrFinder usage

    • grid search metrics visualization

  4. tutorial – autolabel - WIP

    • pseudolabeling for your dataset

  5. tutorial – segmentation - WIP

  6. tutorial – autounet - WIP


RL pipelines

  1. features – OpenAI Gym LunarLander

    • off-policy RL for continuous action space environment

    • DDPG, SAC, TD3 benchmark

    • async multi-cpu, multi-gpu training

  2. features – Atari

    • off-policy RL for discrete action space environment

    • DQN

    • image-based environment with various wrappers

    • CNN-based agent with different distribution heads support


CI tests

  1. DL – Mnist with stages

  2. RL – OpenAI Gym MountainCarContinuous