v0.5.0

[v0.5.0] - 2022-06-30

Added

• Merge dev to main. (#477)

• Docs 0.4.1 backup. (#462)

• Add CD back with semantic release. (#472)

Removed

Changed

• Refactor the guide for image to image search. (#458)

• Refactor the guide for text to image search. (#459)

• Refactor the default hyper-params and docstring format. (#465)

• Various updates on style, how-to and templates. (#462)

• Remove time column from Readme table. (#468)

• Change release trigger to push to main branch. (#478)

Fixed

• Use finetuner docs links in docs instead of netlify. (#475)

• Use twine pypi release . (#480)

💫 Patch v0.4.1

Release Note (0.4.1)

Release time: 2022-02-17 15:25:53

🙇 We'd like to thank all contributors for this new release! In particular,
Jie Fu, Michael Günther, Aziz Belaweid, CatStark, Wang Bo, Yanlong Wang, Tadej Svetina, Florian Hönicke, Jina Dev Bot, 🙇

🐞 Bug fixes

• [6314a0dd] - use small batch size by default (#366) (Wang Bo)
• [cb0e3d5e] - shuffle batches (#351) (Florian Hönicke)

🧼 Code Refactoring

• [fb0dc916] - add device option to tailor (Michael Günther)

📗 Documentation

• [f4807162] - fix code mesh tutorial (#372) (Aziz Belaweid)
• [9edcbe68] - fix typos in tll tutorial(#370) (CatStark)
• [ae655e9b] - use new docsqa server address (#364) (Yanlong Wang)
• [dc9d306f] - change ResNet18 to ResNet50 in README example (#362) (Michael Günther)

🏁 Unit Test and CICD

• [7aeb8861] - fix gpu (#365) (Tadej Svetina)

🍹 Other Improvements

• [adf7b2ee] - Docs onnx tutorial (#373) (Jie Fu)
• [40aa8087] - version: the next version will be 0.4.1 (Jina Dev Bot)

🎉 Release v0.4.0

Release Note (0.4.1)

Release time: 2022-01-27 15:16:47

🙇 We'd like to thank all contributors for this new release! In particular,
Wang Bo, George Mastrapas, Aziz Belaweid, Tadej Svetina, Yanlong Wang, Gregor von Dulong, Han Xiao, Nan Wang, Jina Dev Bot, 🙇

🆕 New Features

• [82238b14] - use da.evaluate in Evaluator + configurable metrics (#352) (George Mastrapas)
• [ffce20cd] - use docarray package and remove labeler (#338) (Tadej Svetina)
• [e3543f7b] - self supervised learning integration (#336) (Wang Bo)
• [fc326873] - tuner: onnx model dump load 280 (#308) (Gregor von Dulong)
• [b760da02] - add NTXent loss (#326) (Tadej Svetina)
• [554878ea] - tuner: add default projection head for ssl (#316) (Wang Bo)
• [bc25c379] - add default preprocess fn for ssl (#331) (Wang Bo)
• [2e1c5b7c] - evaluator integration (#284) (George Mastrapas)
• [4b245eb6] - add unlabeled data classes (#320) (Tadej Svetina)
• [fddf0bf7] - model checkpoint (#249) (Aziz Belaweid)
• [382ebd71] - early stop callback (#266) (Aziz Belaweid)

🐞 Bug fixes

• [36ad4a27] - module level PyTorch collate all function (#354) (George Mastrapas)
• [6ef74f13] - do not normalize float images (#342) (Wang Bo)
• [68f2ea2c] - use replace sort with sorted (#341) (Wang Bo)
• [ec28b04f] - add normalization to preprocessor (#340) (Wang Bo)
• [86c5f283] - remove double freeze from tutorial (#324) (Gregor von Dulong)
• [7d3c05a5] - cd tests (#318) (Tadej Svetina)
• [8ff56499] - docs: fix bottom github link (#310) (Yanlong Wang)
• [0eeb4b70] - tuner: logging (#303) (Tadej Svetina)
• [c75b6701] - make sure logging is correct (#296) (Aziz Belaweid)
• [d1b8bd91] - qa-bot: fix link reference and width style (#292) (Yanlong Wang)
• [9a51e1a1] - handle exceptions in callbacks (#286) (Tadej Svetina)

🧼 Code Refactoring

• [0fd54bf0] - adjust readme after remove labeler (#350) (Wang Bo)
• [a3b0a1db] - doc-bot: migrate to <jina-qa-bot> (#283) (Yanlong Wang)

📗 Documentation

• [bb8e974c] - clean up readme and ndcg (#359) (Wang Bo)
• [79581b47] - add text tutorial (#357) (George Mastrapas)
• [7c6a9f51] - fix labeler docs adjust quick start (#358) (Wang Bo)
• [e8058192] - 3d mesh finetuning tutorial (#345) (Aziz Belaweid)
• [4f9f4a32] - rename bottleneck to projection head (#356) (Wang Bo)
• [ec170afe] - clean up docs (#355) (Wang Bo)
• [42ca1498] - bump qabot (#330) (Yanlong Wang)
• [0eae3206] - add checkpoints to documentation (#312) (Tadej Svetina)
• [7fef9df6] - fix section title in docs (Han Xiao)
• [a5f956ad] - adjust readme based on new release (#302) (Wang Bo)
• [7cc242f4] - add tll tutorial (#285) (Wang Bo)

🍹 Other Improvements

• [b86c0e64] - cd: fix cd if condition (Han Xiao)
• [49813c95] - docs: add docarray link to sidebar (Han Xiao)
• [b4a10f7e] - remove doc building from CD (#317) (Tadej Svetina)
• [954acce7] - CI improvements (#305) (Tadej Svetina)
• [c796bdd4] - fix typos in covid-qa (#294) (Nan Wang)
• [c51b044a] - adapt to the latest changes (#267) (Nan Wang)
• [61e99141] - version: the next version will be 0.3.1 (Jina Dev Bot)

🎉 0.3.0

Minor release 0.3.0

New features

1. Tailor now allows you to freeze weights by layer names freeze=['layer1', 'layer2'] and attach a customised bottleneck net module bottleneck_net=MLP() on top of your embedding model #230, #238.
2. Finetuner now support callbacks. Callbacks can be triggered on model training process, and we've implemented several built-in callbacks such as WandBLogger which could log your tranining progress with Weights and Biases #231, #237.
3. Built-in different mining strategy, such as hard negative mining, can be plug-into loss fucntions, such as TripletLoss(miner=TripletEasyHardMiner(neg_strategy='semihard') ) #236.
4. Learning rate scheduler support on batch or epoch level using scheduler_step #248.
5. Multiprocess data loading now supports with Pytorch and PaddlePaddle backend with num_workers #263.
6. Built-in Evaluator support with different metrics supported, such as precision, recall, mAP, nDCG etc #223, #224.

Bug fixes & Refactoring & Testing

1. Make blob property writable with Pytorch backend #244.
2. Now the reserved tag for finetuner change to finetuner_label #251.
3. Code consistency improvement in embed and preprocessing #256, #255.
4. Minor bug fixed includs type casting #268, unit/integration test improvement #264, #253, DocArray import refactoring after we split docarray as a seperate project #277, #275.

🙇 We'd like to thank all contributors for this new release! In particular,
Tadej Svetina, Wang Bo, George Mastrapas, Gregor von Dulong, Aziz Belaweid, Han Xiao, Mohammad Kalim Akram, Deepankar Mahapatro, Nan Wang, Maximilian Werk, Roshan Jossy, Jina Dev Bot, 🙇

💫 Patch v0.2.4

Release Note (0.2.4)

Release time: 2021-11-24 16:13:58

🙇 We'd like to thank all contributors for this new release! In particular,
Han Xiao, Jina Dev Bot, 🙇

📗 Documentation

• [b7ff2920] - fix doc gen (Han Xiao)

🍹 Other Improvements

• [67c66fe4] - bump jina min req. version (Han Xiao)
• [c39f2a2b] - version: the next version will be 0.2.4 (Jina Dev Bot)

💫 Patch v0.2.3

Release Note (0.2.3)

Release time: 2021-11-24 14:08:12

🙇 We'd like to thank all contributors for this new release! In particular,
Han Xiao, Deepankar Mahapatro, Yanlong Wang, Tadej Svetina, Jina Dev Bot, 🙇

🐞 Bug fixes

• [88f37a29] - docbot: feedback tooltip ui style (#222) (Yanlong Wang)

🧼 Code Refactoring

• [2d9e9d72] - dataset: make preprocess_fn return any (#217) (Han Xiao)

📗 Documentation

• [62214aa2] - fix css layout of versions (Han Xiao)
• [08336e87] - dataset: restructure docs on datasets (#226) (Han Xiao)
• [6e5934ba] - versioning (#225) (Deepankar Mahapatro)
• [97639dac] - improve docstring for preprocess_fn (#221) (Tadej Svetina)

🍹 Other Improvements

• [670adbe0] - version: the next version will be 0.2.3 (Jina Dev Bot)

💫 Patch v0.2.2

Release Note (0.2.2)

Release time: 2021-11-21 21:14:37

🙇 We'd like to thank all contributors for this new release! In particular,
Yanlong Wang, Han Xiao, Jina Dev Bot, 🙇

🐞 Bug fixes

• [89511dc9] - docbot overflow and scrolling (#216) (Yanlong Wang)

🧼 Code Refactoring

• [7778855e] - dataset: make preprocess_fn work on document (#215) (Han Xiao)

🍹 Other Improvements

• [55e0888e] - fix readme (Han Xiao)
• [dc526452] - version: the next version will be 0.2.2 (Jina Dev Bot)

💫 Patch v0.2.1

Release Note (0.2.1)

Release time: 2021-11-20 19:39:37

🙇 We'd like to thank all contributors for this new release! In particular,
Han Xiao, Tadej Svetina, Jina Dev Bot, 🙇

🧼 Code Refactoring

• [d70546ac] - sampling: make num_items_per_class optional (#214) (Han Xiao)

📗 Documentation

• [acc6e388] - tutorial: add swiss roll tutorial (Han Xiao)
• [8748e9ee] - labeler: fix docstring (#213) (Tadej Svetina)

🍹 Other Improvements

• [23d8ca80] - remove notebook from static (Han Xiao)
• [5b0b9a1d] - version: the next version will be 0.2.1 (Jina Dev Bot)

💫 Patch v0.2.0

Release Note (0.2.0)

Release time: 2021-11-19 14:22:57

🙇 We'd like to thank all contributors for this new release! In particular,
Han Xiao, Yanlong Wang, Tadej Svetina, Wang Bo, Jina Dev Bot, 🙇

🆕 New Features

• [f920fe25] - reformat pipeline (#192) (Tadej Svetina)

🐞 Bug fixes

• [fe67bb92] - docs celeba (#211) (Tadej Svetina)
• [e0f81474] - make get_framework robust (#207) (Tadej Svetina)
• [376f4028] - tailor: fix to emebdding model (#196) (Wang Bo)

📗 Documentation

• [0a67481d] - fix doc-bot style during load (#212) (Yanlong Wang)

🍹 Other Improvements

• [c6041fde] - version: set next version to 0.2.0 (Han Xiao)
• [20eb41c2] - style: fix coding style optimize imports (Han Xiao)
• [6539237b] - version: the next version will be 0.1.6 (Jina Dev Bot)

💫 Patch v0.1.5

Release Note (0.1.5)

Release time: 2021-11-08 10:20:47

🙇 We'd like to thank all contributors for this new release! In particular,
Roshan Jossy, Han Xiao, Wang Bo, Tadej Svetina, Jina Dev Bot, 🙇

🆕 New Features

• [531d9052] - tuner: add miner for session dataset (#184) (Wang Bo)
• [77df7676] - reformat data loading (#181) (Tadej Svetina)

🐞 Bug fixes

• [3d5fc769] - embedding: fix embedding train/eval time behavior (#190) (Han Xiao)

🏁 Unit Test and CICD

• [d80a4d0f] - embedding: add test for #190 (Han Xiao)
• [fd1fe384] - upgrade tf version (#189) (Wang Bo)
• [5059e202] - pin framework version (#188) (Wang Bo)

🍹 Other Improvements

• [e1a73434] - labeler: add component for audio matches (#185) (Roshan Jossy)
• [717f06a0] - version: the next version will be 0.1.5 (Jina Dev Bot)