Recent Releases of Zoobot

Zoobot - v2.9.0 - HuggingFace support, data rework

Key changes: - GalaxyDataModule replaced by CatalogDataModule - HuggingFaceDataModule added (HF support!) - Transform/augmentations totally reworked for speed and ease, includes prebuilt options - Preparation for v3 foundation models behind the scenes

What's Changed

  • Inigo dev by @inigoval in https://github.com/mwalmsley/zoobot/pull/118
  • Fix incorrect reference/link to CODEOFCONDUCT.md by @Logan-Locke in https://github.com/mwalmsley/zoobot/pull/121
  • Old updates direct to main copied into dev by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/122
  • New models, new data loading by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/123

New Contributors

  • @inigoval made their first contribution in https://github.com/mwalmsley/zoobot/pull/118
  • @Logan-Locke made their first contribution in https://github.com/mwalmsley/zoobot/pull/121

Full Changelog: https://github.com/mwalmsley/zoobot/compare/v2.0.1...v2.9.0

Scientific Software - Peer-reviewed - Jupyter Notebook
Published by mwalmsley 5 months ago

Zoobot - Add greyscale encoders

Zoobot now includes pretrained greyscale encoders. FinetuneableZoobot... classes can use these pretrained encoders.

This HuggingFace collection lists all current greyscale encoders.

Scientific Software - Peer-reviewed - Jupyter Notebook
Published by mwalmsley over 1 year ago

Zoobot - v2.0

What's Changed

  • New pretrained architectures: ConvNeXT, EfficientNetV2, MaxViT, and more. Each in several sizes. Available on HuggingFace.
  • Reworked finetuning procedure. All these architectures are finetuneable through a common method.
  • Reworked finetuning options. Batch norm finetuning removed. Cosine schedule option added.
  • Reworked finetuning saving/loading. Auto-downloads encoder from HuggingFace.
  • Now supports regression finetuning (as well as multi-class and binary). See pytorch/examples/finetuning
  • Updated timm to 0.9.10, allowing latest model architectures. Previously downloaded checkpoints may not load correctly!
  • (internal until published) GZ Evo v2 now includes Cosmic Dawn (HSC H2O). Significant performance improvement on HSC finetuning. Also now includes GZ UKIDSS (dragged from our archives).
  • Updated pytorch to 2.1.0
  • Added support for webdatasets (only recommended for large-scale distributed training)
  • Improved per-question logging when training from scratch
  • Added option to compile encoder for max speed (not recommended for finetuning, only for pretraining).
  • Deprecates TensorFlow. The CS research community focuses on PyTorch and new frameworks like JAX.

Full Changelog: https://github.com/mwalmsley/zoobot/compare/v1.0.5...v2.0

Scientific Software - Peer-reviewed - Jupyter Notebook
Published by mwalmsley almost 2 years ago

Zoobot - v1.0.5 - Finetuning Improvements, Max-ViT

What's Changed

Major improvements to finetuning. - Now supports finetuning resnet and maxvit-tiny! This previously only worked as static pretrained models. - Now specify numblocks instead of numlayers, reflecting the network structure (effnet, resnet50, maxvit) - Now you can optionally keep batchnorm layers always trainable

Small changes: Update dependency to use galaxy-datasets==0.15.0 Replace multi-class example with new galaxy-mnist dataset Fixes https://github.com/mwalmsley/zoobot/issues/108

The next release will update timm to 0.9ish Pytorch 2.1.0 already works, and the next release will also reflect that

Full Changelog: https://github.com/mwalmsley/zoobot/compare/v1.0.4...v1.0.5

Scientific Software - Peer-reviewed - Jupyter Notebook
Published by mwalmsley about 2 years ago

Zoobot - Color and multi-class support

This minor release adds pretrained color models (i.e. with 3 channels) and also adds support for multi-class finetuning.

What's Changed

  • sync by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/92
  • 1.0.3 version bump by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/99
  • Rebuild docs by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/103
  • Add color weights, trivial QoL changes by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/104
  • Add multiclass example by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/105
  • Add multiclass support by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/106

Full Changelog: https://github.com/mwalmsley/zoobot/compare/v1.0.3...v1.0.4

Scientific Software - Peer-reviewed - Jupyter Notebook
Published by mwalmsley over 2 years ago

Zoobot - JOSS paper release

Minor release marking Zoobot's state on acceptance of the JOSS paper.

What's Changed

  • Finetune v1 onto docs by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/85
  • Dev by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/87
  • sync by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/93
  • Delete requirements.txt by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/96
  • Bring paper fix from docs to main by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/97
  • Highlight Colab notebook by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/98

Full Changelog: https://github.com/mwalmsley/zoobot/compare/1.0.2...v1.0.3

Scientific Software - Peer-reviewed - Jupyter Notebook
Published by mwalmsley over 2 years ago

Zoobot - v1.0.2 - Lighning v2 and galaxy-datasets updates

  • Lightning v2 now correctly uses early stopping
  • galaxy-datasets version bumped to correctly ignore alpha channel of png images

What's Changed

  • Hotfix - add early stopping back, update docs by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/91

Full Changelog: https://github.com/mwalmsley/zoobot/compare/v1.0.1...1.0.2

Scientific Software - Peer-reviewed - Jupyter Notebook
Published by mwalmsley almost 3 years ago

Zoobot - v1.0.1 - Lightning v2.0 support

Small incremental release adjusting the LightningModule hooks used in order to support Lightning v2. Lightning v2.0.0 (currently latest) is now the minimum required version.

What's Changed

  • Update with Maja's changes by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/89
  • Support Lightning v2.0.0 by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/90

Full Changelog: https://github.com/mwalmsley/zoobot/compare/v1.0.0...v1.0.1

Scientific Software - Peer-reviewed - Jupyter Notebook
Published by mwalmsley almost 3 years ago

Zoobot - v1 release

This release completely rewrites the API and documentation based on user feedback during the one-year beta period.

Major changes include: - New API for finetuning - Shift to PyTorch/Lightning - Support for all timm models - Docs refocused on finetuning - Pretrained model library added - Data loading refactored to albumentations and mwalmsley/galaxy-datasets

Documentation is here. Installation and quickstart are on the README.

Thank you all for the help!

What's Changed

  • Update refactor with latest changes by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/15
  • Dockerize zoobot for pytorch and tensorflow versions by @camallen in https://github.com/mwalmsley/zoobot/pull/14
  • Refactor pytorch datasets by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/16
  • missed a rename, thanks cam by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/17
  • allow multiple catalog paths to be passed by @camallen in https://github.com/mwalmsley/zoobot/pull/19
  • allow install of git based packages (pytorchgalaxydatasets) by @camallen in https://github.com/mwalmsley/zoobot/pull/20
  • Bring old dev branch up-to-date by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/23
  • Update finetuning_advanced example by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/24
  • PL logging by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/22
  • Improve data files for docker by @camallen in https://github.com/mwalmsley/zoobot/pull/21
  • allow checkpointing setup to be customized by @camallen in https://github.com/mwalmsley/zoobot/pull/26
  • Include Cam's latest features on generic dev by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/27
  • improve docker setup by @camallen in https://github.com/mwalmsley/zoobot/pull/28
  • Trivial updates by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/29
  • Refactor PyTorch for explicit Lighnting/Wandb hyperparameters by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/30
  • Adding Zoobot to pypi by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/31
  • add gh action CI system by @camallen in https://github.com/mwalmsley/zoobot/pull/34
  • add gh action to publish package to pypi by @camallen in https://github.com/mwalmsley/zoobot/pull/33
  • remove travis CI integration by @camallen in https://github.com/mwalmsley/zoobot/pull/35
  • Deprecate TFRecords by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/32
  • Fix doc build, tweak readme by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/40
  • Trivial typing change left behind by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/55
  • Create CODEOFCONDUCT.md by @camallen in https://github.com/mwalmsley/zoobot/pull/46
  • Add PyTorch Finetuning Capability, Examples by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/59
  • Benchmarks by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/58
  • remove extra _non-star label for artifact task by @camallen in https://github.com/mwalmsley/zoobot/pull/60
  • allow more params to finetuning via config object by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/63
  • add wandb logging, freeze batchnorm by default by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/62
  • Make sure TF and Torch versions have similar performance by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/64
  • Big messy PR of misc. improvements by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/65
  • use correct torchvision 0.13.1 package by @camallen in https://github.com/mwalmsley/zoobot/pull/69
  • Update with previous commits by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/72
  • use latest galaxy-datasets package by @camallen in https://github.com/mwalmsley/zoobot/pull/75
  • add timm package for pytoch cuda by @camallen in https://github.com/mwalmsley/zoobot/pull/77
  • Docs by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/78
  • Merge pull request #78 from mwalmsley/docs by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/79
  • Finetune v1 by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/80
  • Joss by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/81
  • Syncing branches by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/83
  • Update finetune-v1 with docs changes by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/84
  • Finetune v1 onto dev by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/86
  • Add tensorboard writer callback to pytorch by @maja-jablonska in https://github.com/mwalmsley/zoobot/pull/54
  • V1 release by @mwalmsley in https://github.com/mwalmsley/zoobot/pull/88

New Contributors

  • @maja-jablonska made their first contribution in https://github.com/mwalmsley/zoobot/pull/54

Full Changelog: https://github.com/mwalmsley/zoobot/compare/v0.0.3...v1.0.0

Scientific Software - Peer-reviewed - Jupyter Notebook
Published by mwalmsley almost 3 years ago

Zoobot - Docs pre-release

Improved documentation and refactored train API (pytorch).

Awaiting results from several segmentation experiments ahead of public release (inc pytorch version).

Scientific Software - Peer-reviewed - Jupyter Notebook
Published by mwalmsley over 3 years ago

Zoobot - v0.0.2

Polish throughout and add new features. See #2 for a full description.

Scientific Software - Peer-reviewed - Jupyter Notebook
Published by mwalmsley over 4 years ago

Zoobot - v0.0.1

Initial release.

This had enough documentation and code to replicate the DECaLS model and make predictions. There are a few minor missing arguments and similar typos that you might have stumbled into, because I made some last minute changes without updating the docs, but everything worked with a little stack tracing.

Scientific Software - Peer-reviewed - Jupyter Notebook
Published by mwalmsley over 4 years ago