v0.3.0

fastai based Learner with callbacks enabling

• unified training and inference with tensordict
• tracking of activations and weights
• learning rate search
• hyperparamter scheduling (e.g. one cycle)

tabular models

• supervised (classification / regression) for numerical & categorical features, including handling of missing values
• unsupervised (variational auto encoder) also for numerical & categorical features, including handling of missing values

v0.2.0

Added mingpt (source: https://github.com/karpathy/minGPT/tree/master), including the three projects (adder, sort, char) with dedicated notebooks.

v0.1.6

added Diffuser UNet based on https://github.com/fastai/course22p2/blob/master/nbs/26_diffusion_unet.ipynb

v0.1.5

refactored unet implementation in unet.py to improve readability

v0.1.4

• new unet.py contains modified version of fastai 2022 unet implementation
• added unet_fastai2022.ipynb to apply implemented unet to mnist

v0.1.3

• added fastai 2022 course like resnet implementation in resnet.py
• applied resnet to mnist in resnet_fastai2022.ipynb

v0.1.2

• refactored telemetry
• added tests for telemetry

v0.1.1

• pypi setup