From 4c21f7ff199136350bdb15788d5a17a51a429e82 Mon Sep 17 00:00:00 2001 From: Kai Chen <chenkaidev@gmail.com> Date: Mon, 24 Feb 2020 16:07:58 +0800 Subject: [PATCH] Update version to 1.1 (#2144) * update version to 1.1 * fix typo * remove the version limit of ubelt --- README.md | 12 ++++++------ docs/CHANGELOG.md | 36 ++++++++++++++++++++++++++++++++++++ requirements/tests.txt | 2 +- setup.py | 2 +- 4 files changed, 44 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index 9c5ffe65..4a5c5d29 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,3 @@ - # MMDetection **News**: We released the technical report on [ArXiv](https://arxiv.org/abs/1906.07155). @@ -7,7 +6,7 @@ Documentation: https://mmdetection.readthedocs.io/ ## Introduction -The master branch works with **PyTorch 1.1** or higher. +The master branch works with **PyTorch 1.1 to 1.4**. mmdetection is an open source object detection toolbox based on PyTorch. It is a part of the open-mmlab project developed by [Multimedia Laboratory, CUHK](http://mmlab.ie.cuhk.edu.hk/). @@ -40,7 +39,7 @@ This project is released under the [Apache 2.0 license](LICENSE). ## Changelog -v1.0.0 was released in 30/1/2020, with more than 20 fixes and improvements. +v1.1.0 was released in 24/2/2020. Please refer to [CHANGELOG.md](docs/CHANGELOG.md) for details and release history. ## Benchmark and model zoo @@ -77,11 +76,11 @@ Other features - [x] [DCNv2](configs/dcn/README.md) - [x] [Group Normalization](configs/gn/README.md) - [x] [Weight Standardization](configs/gn+ws/README.md) -- [x] OHEM +- [x] [OHEM](configs/faster_rcnn_ohem_r50_fpn_1x.py) - [x] Soft-NMS - [x] [Generalized Attention](configs/empirical_attention/README.md) - [x] [GCNet](configs/gcnet/README.md) -- [x] [Mixed Precision (FP16) Training](https://github.com/open-mmlab/mmdetection/blob/master/configs/fp16) +- [x] [Mixed Precision (FP16) Training](configs/fp16) - [x] [InstaBoost](configs/instaboost/README.md) @@ -125,4 +124,5 @@ If you use this toolbox or benchmark in your research, please cite this project. ## Contact -This repo is currently maintained by Kai Chen ([@hellock](http://github.com/hellock)), Yuhang Cao ([@yhcao6](https://github.com/yhcao6)), Wenwei Zhang ([@ZwwWayne](https://github.com/ZwwWayne)), Jiangmiao Pang ([@OceanPang](https://github.com/OceanPang)) and Jiaqi Wang ([@myownskyW7](https://github.com/myownskyW7)). +This repo is currently maintained by Kai Chen ([@hellock](http://github.com/hellock)), Yuhang Cao ([@yhcao6](https://github.com/yhcao6)), Wenwei Zhang ([@ZwwWayne](https://github.com/ZwwWayne)), +Jiarui Xu ([@xvjiarui](https://github.com/xvjiarui)). Other core developers include Jiangmiao Pang ([@OceanPang](https://github.com/OceanPang)) and Jiaqi Wang ([@myownskyW7](https://github.com/myownskyW7)). diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md index f4221d23..632b97d7 100644 --- a/docs/CHANGELOG.md +++ b/docs/CHANGELOG.md @@ -1,5 +1,41 @@ ## Changelog +### v1.1.0 (24/2/2020) + +**Highlights** +- Dataset evaluation is rewritten with a unified api, which is used by both evaluation hooks and test scripts. +- Support new methods: [CARAFE](https://arxiv.org/abs/1905.02188). + +**Breaking Changes** +- The new MMDDP inherits from the official DDP, thus the `__init__` api is changed to be the same as official DDP. +- The `mask_head` field in HTC config files is modified. +- The evaluation and testing script is updated. +- In all transforms, instance masks are stored as a numpy array shaped (n, h, w) instead of a list of (h, w) arrays, where n is the number of instances. + +**Bug Fixes** +- Fix IOU assigners when ignore_iof_thr > 0 and there is no pred boxes. (#2135) +- Fix mAP evaluation when there are no ignored boxes. (#2116) +- Fix the empty RoI input for Deformable RoI Pooling. (#2099) +- Fix the dataset settings for multiple workflows. (#2103) +- Fix the warning related to `torch.uint8` in PyTorch 1.4. (#2105) +- Fix the inference demo on devices other than gpu:0. (#2098) +- Fix Dockerfile. (#2097) +- Fix the bug that `pad_val` is unused in Pad transform. (#2093) +- Fix the albumentation transform when there is no ground truth bbox. (#2032) + +**Improvements** +- Use torch instead of numpy for random sampling. (#2094) +- Migrate to the new MMDDP implementation in MMCV v0.3. (#2090) +- Add meta information in logs. (#2086) +- Rewrite Soft NMS with pytorch extension and remove cython as a dependency. (#2056) +- Rewrite dataset evaluation. (#2042, #2087, #2114, #2128) +- Use numpy array for masks in transforms. (#2030) + +**New Features** +- Implement "CARAFE: Content-Aware ReAssembly of FEatures". (#1583) +- Add `worker_init_fn()` in data_loader when seed is set. (#2066, #2111) +- Add logging utils. (#2035) + ### v1.0.0 (30/1/2020) This release mainly improves the code quality and add more docstrings. diff --git a/requirements/tests.txt b/requirements/tests.txt index 23009cad..c3e76b73 100644 --- a/requirements/tests.txt +++ b/requirements/tests.txt @@ -7,6 +7,6 @@ kwarray pytest pytest-cov pytest-runner -ubelt == 0.8.8 +ubelt xdoctest >= 0.10.0 yapf diff --git a/setup.py b/setup.py index 05f4f06f..89e79f95 100755 --- a/setup.py +++ b/setup.py @@ -16,7 +16,7 @@ def readme(): MAJOR = 1 -MINOR = 0 +MINOR = 1 PATCH = 0 SUFFIX = '' if PATCH != '': -- GitLab