diff --git a/CHANGELOG.md b/CHANGELOG.md index f775d1707e7..63011d14033 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -8,32 +8,31 @@ All notable changes to this project will be documented in this file. - Support encrypted dataset training () - Add custom max iou assigner to prevent CPU OOM when large annotations are used () -- Auto train type detection for Semi-SL, Self-SL and Incremental: "--train-type" now is optional (https://github.com/openvinotoolkit/training_extensions/pull/2195) -- Add per-class XAI saliency maps for Mask R-CNN model (https://github.com/openvinotoolkit/training_extensions/pull/2227) +- Auto train type detection for Semi-SL, Self-SL and Incremental: "--train-type" now is optional () +- Add per-class XAI saliency maps for Mask R-CNN model () - Add new object detector Deformable DETR () -- Add new object detector DINO() -- Add new visual prompting task: train/eval (https://github.com/openvinotoolkit/training_extensions/pull/2203) -- Add new visual prompting task: export (https://github.com/openvinotoolkit/training_extensions/pull/2274) -- Add new visual prompting task: deploy (https://github.com/openvinotoolkit/training_extensions/pull/2311) -- Add new visual prompting task: documentation (https://github.com/openvinotoolkit/training_extensions/pull/2354) -- Add new visual prompting task: optimize (PTQ) (https://github.com/openvinotoolkit/training_extensions/pull/2318) +- Add new object detector DINO () +- Add new visual prompting task (, , , , ) - Add new object detector ResNeXt101-ATSS () ### Enhancements - Introduce channel_last parameter to improve the performance () -- Decrease a time for making a workspace () +- Decrease time for making a workspace () - Set persistent_workers and pin_memory as True in detection task () -- New algorithm for Semi-SL semantic segmentation based on metric lerning via class prototypes (https://github.com/openvinotoolkit/training_extensions/pull/2156) -- Self-SL for classification now can recieve just folder with any images to start contrastive pretraining (https://github.com/openvinotoolkit/training_extensions/pull/2219) +- New algorithm for Semi-SL semantic segmentation based on metric learning via class prototypes () +- Self-SL for classification now can recieve just folder with any images to start contrastive pretraining () - Update OpenVINO version to 2023.0, and NNCF verion to 2.5 () -- Improve XAI saliency map generation for tiling detection and tiling instance segmentation (https://github.com/openvinotoolkit/training_extensions/pull/2240) +- Improve XAI saliency map generation for tiling detection and tiling instance segmentation () +- Remove CenterCrop from Classification test pipeline and editing missing docs link() ### Bug fixes - Fix the bug that auto adapt batch size is unavailable with IterBasedRunner () - Fix the bug that learning rate isn't scaled when multi-GPU trianing is enabled() - Fix the bug that label order is misaligned when model is deployed from Geti () +- Fix NNCF training on CPU () +- Fix H-label classification () ### Known issues diff --git a/docs/source/guide/release_notes/index.rst b/docs/source/guide/release_notes/index.rst index 616d98a1837..ef0c1f6d721 100644 --- a/docs/source/guide/release_notes/index.rst +++ b/docs/source/guide/release_notes/index.rst @@ -1,6 +1,19 @@ Releases ======== +*************** +[v1.4.0] (3Q23) +*************** + +- Support encrypted dataset training +- Add custom max iou assigner to prevent CPU OOM when large annotations are used +- Auto train type detection for Semi-SL, Self-SL and Incremental: "--train-type" now is optional +- Add per-class XAI saliency maps for Mask R-CNN model +- Add new object detector Deformable DETR +- Add new object detector DINO +- Add new visual prompting task +- Add new object detector ResNeXt101-ATSS + *************** [v1.3.0] (2Q23) *************** diff --git a/requirements/base.txt b/requirements/base.txt index 384031b53d2..a901eb88599 100644 --- a/requirements/base.txt +++ b/requirements/base.txt @@ -4,7 +4,7 @@ natsort>=6.0.0 prettytable protobuf>=3.20.0 pyyaml -datumaro==1.4.0rc3 +datumaro==1.4.0rc4 psutil scipy>=1.8 bayesian-optimization>=1.2.0 diff --git a/src/otx/__init__.py b/src/otx/__init__.py index 0656f85ae5c..1a39b601165 100644 --- a/src/otx/__init__.py +++ b/src/otx/__init__.py @@ -3,5 +3,5 @@ # Copyright (C) 2021-2023 Intel Corporation # SPDX-License-Identifier: Apache-2.0 -__version__ = "1.4.0rc2" +__version__ = "1.4.0rc3" # NOTE: Sync w/ src/otx/api/usecases/exportable_code/demo/requirements.txt on release diff --git a/src/otx/api/usecases/exportable_code/demo/requirements.txt b/src/otx/api/usecases/exportable_code/demo/requirements.txt index 5b4fe7a3779..040f57ee8b4 100644 --- a/src/otx/api/usecases/exportable_code/demo/requirements.txt +++ b/src/otx/api/usecases/exportable_code/demo/requirements.txt @@ -1,4 +1,4 @@ openvino==2023.0 openvino-model-api==0.1.3 -otx==1.4.0rc2 +otx==1.4.0rc3 numpy>=1.21.0,<=1.23.5 # np.bool was removed in 1.24.0 which was used in openvino runtime