update codes

.gitignore

+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/en/_build/
+docs/zh_cn/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+data/
+data
+.vscode
+.idea
+.DS_Store
+
+# custom
+*.pkl
+*.pkl.json
+*.log.json
+docs/modelzoo_statistics.md
+mmdet/.mim
+work_dirs/
+
+# Pytorch
+*.pth
+*.py~
+*.sh~

.owners.yml

+assign:
+  strategy:
+    # random
+    daily-shift-based
+  scedule:
+    '*/1 * * * *'
+  assignees:
+    - Czm369
+    - hhaAndroid
+    - jbwang1997
+    - RangiLyu
+    - BIGWangYuDong
+    - chhluo
+    - ZwwWayne

.pre-commit-config-zh-cn.yaml

+exclude: ^tests/data/
+repos:
+  - repo: https://gitee.com/openmmlab/mirrors-flake8
+    rev: 5.0.4
+    hooks:
+      - id: flake8
+  - repo: https://gitee.com/openmmlab/mirrors-isort
+    rev: 5.11.5
+    hooks:
+      - id: isort
+  - repo: https://gitee.com/openmmlab/mirrors-yapf
+    rev: v0.32.0
+    hooks:
+      - id: yapf
+  - repo: https://gitee.com/openmmlab/mirrors-pre-commit-hooks
+    rev: v4.3.0
+    hooks:
+      - id: trailing-whitespace
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: requirements-txt-fixer
+      - id: double-quote-string-fixer
+      - id: check-merge-conflict
+      - id: fix-encoding-pragma
+        args: ["--remove"]
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+  - repo: https://gitee.com/openmmlab/mirrors-mdformat
+    rev: 0.7.9
+    hooks:
+      - id: mdformat
+        args: ["--number"]
+        additional_dependencies:
+          - mdformat-openmmlab
+          - mdformat_frontmatter
+          - linkify-it-py
+  - repo: https://gitee.com/openmmlab/mirrors-codespell
+    rev: v2.2.1
+    hooks:
+      - id: codespell
+  - repo: https://gitee.com/openmmlab/mirrors-docformatter
+    rev: v1.3.1
+    hooks:
+      - id: docformatter
+        args: ["--in-place", "--wrap-descriptions", "79"]
+  - repo: https://gitee.com/openmmlab/mirrors-pyupgrade
+    rev: v3.0.0
+    hooks:
+      - id: pyupgrade
+        args: ["--py36-plus"]
+  - repo: https://gitee.com/open-mmlab/pre-commit-hooks
+    rev: v0.2.0
+    hooks:
+      - id: check-algo-readme
+      - id: check-copyright
+        args: ["mmdet"]
+#  - repo: https://gitee.com/openmmlab/mirrors-mypy
+#    rev: v0.812
+#    hooks:
+#      - id: mypy
+#        exclude: "docs"

.pre-commit-config.yaml

+repos:
+  - repo: https://github.com/PyCQA/flake8
+    rev: 5.0.4
+    hooks:
+      - id: flake8
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.11.5
+    hooks:
+      - id: isort
+  - repo: https://github.com/pre-commit/mirrors-yapf
+    rev: v0.32.0
+    hooks:
+      - id: yapf
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.3.0
+    hooks:
+      - id: trailing-whitespace
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: requirements-txt-fixer
+      - id: double-quote-string-fixer
+      - id: check-merge-conflict
+      - id: fix-encoding-pragma
+        args: ["--remove"]
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.2.1
+    hooks:
+      - id: codespell
+  - repo: https://github.com/executablebooks/mdformat
+    rev: 0.7.9
+    hooks:
+      - id: mdformat
+        args: ["--number"]
+        additional_dependencies:
+          - mdformat-openmmlab
+          - mdformat_frontmatter
+          - linkify-it-py
+  - repo: https://github.com/myint/docformatter
+    rev: v1.3.1
+    hooks:
+      - id: docformatter
+        args: ["--in-place", "--wrap-descriptions", "79"]
+  - repo: https://github.com/open-mmlab/pre-commit-hooks
+    rev: v0.2.0  # Use the ref you want to point at
+    hooks:
+      - id: check-algo-readme
+      - id: check-copyright
+        args: ["mmdet"]  # replace the dir_to_check with your expected directory to check

.readthedocs.yml

+version: 2
+
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.8"
+
+formats:
+  - epub
+
+python:
+  install:
+    - requirements: requirements/docs.txt
+    - requirements: requirements/readthedocs.txt

CITATION.cff

+cff-version: 1.2.0
+message: "If you use this software, please cite it as below."
+authors:
+  - name: "MMDetection Contributors"
+title: "OpenMMLab Detection Toolbox and Benchmark"
+date-released: 2018-08-22
+url: "https://github.com/open-mmlab/mmdetection"
+license: Apache-2.0

LICENSE

+Copyright 2018-2023 OpenMMLab. All rights reserved.
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2018-2023 OpenMMLab.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

MANIFEST.in

+include requirements/*.txt
+include mmdet/VERSION
+include mmdet/.mim/model-index.yml
+include mmdet/.mim/dataset-index.yml
+include mmdet/.mim/demo/*/*
+recursive-include mmdet/.mim/configs *.py *.yml
+recursive-include mmdet/.mim/tools *.sh *.py

README.md

 # grounding_dino_mmcv
+## 论文
+`Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection`<br>
+[论文链接](https://arxiv.org/abs/2303.05499)<br>
+## 模型结构
+论文提出了一种名为Grounding DINO的开放集目标检测器。它将基于Transformer的DINO检测器与预训练相结合，能够通过人类输入如类别名称或指代表达式来检测任意对象.<br>
+- feature enhancer：text feature使用 self-attention, image features使用deformabel self-attention来减少计算量。
+- query初始化：feature enhancer输出的text features与image features,计算相似度，并求最大值后排序。
+- Cross-Modality Decoder：用第2步提取query做为输入，依次与image features，text features进行跨模态注意力计算，最终，获得更新后的decode输出。
+![model_framework.png](asserts%2Fmodel_framework.png)
+## 算法原理
+闭集检测器通常具有三个重要模块：特征提取的主干、用于特征增强的颈部和用于区域细化（或框预测）的头部<br>
+闭集检测器可以通过学习语言感知的区域嵌入来泛化以检测新对象，从而使每个区域可以在语言感知的语义空间中被分类为新类别。实现这一目标的关键是在颈部和/或头部输出处使用区域输出和语言特征之间的对比损失。 <br>
+![block.png](asserts%2Fblock.png)
+## 环境配置
+### Docker（方法一）
 
+```
+docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk24.04-py310
+docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=80G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
+
+cd /your_code_path/grounding_dino_mmcv
+pip install mmdet -i https://mirrors.aliyun.com/pypi/simple/
+pip install -r requirements/multimodal.txt -i https://mirrors.aliyun.com/pypi/simple/
+export HF_ENDPOINT=https://hf-mirror.com
+```
+### Dockerfile（方法二）
+```
+cd ./docker
+docker build --no-cache -t mmdet:last .
+docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=80G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
+cd /your_code_path/grounding_dino_mmcv
+pip install mmdet -i https://mirrors.aliyun.com/pypi/simple/
+pip install -r requirements/multimodal.txt -i https://mirrors.aliyun.com/pypi/simple/
+export HF_ENDPOINT=https://hf-mirror.com
+```
+### Anaconda（方法三）
+1、关于本项目DCU显卡所需的特殊深度学习库可从光合开发者社区下载安装： https://developer.hpccube.com/tool/
+```
+DTK软件栈: dtk24.04
+python: python3.10
+torch: 2.1
+mmcv: 2.0.1
+```
+
+Tips：以上dtk软件栈、python、torch、mmcv等DCU相关工具版本需要严格一一对应
+
+2、其他非特殊库直接按照requirements.txt安装
+
+```
+cd /your_code_path/grounding_dino_mmcv
+pip install mmdet -i https://mirrors.aliyun.com/pypi/simple/
+pip install -r requirements/multimodal.txt -i https://mirrors.aliyun.com/pypi/simple/
+export HF_ENDPOINT=https://hf-mirror.com
+```
+
+## 数据集
+COCO2017（在网络良好的情况下，如果没有下载数据集，程序会默认在线下载数据集）
+
+[训练数据](http://images.cocodataset.org/zips/train2017.zip)
+
+[验证数据](http://images.cocodataset.org/zips/val2017.zip)
+
+[测试数据](http://images.cocodataset.org/zips/test2017.zip)
+
+[标签数据](https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017labels.zip)
+
+数据集的目录结构如下：
+
+```
+├── images 
+│   ├── train2017
+│   ├── val2017
+│   ├── test2017
+├── labels
+│   ├── train2017
+│   ├── val2017
+├── annotations
+│   ├── instances_val2017.json
+├── LICENSE
+├── README.txt 
+├── test-dev2017.txt
+├── train2017.txt
+├── val2017.txt
+
+```
+我们通过了mini数据集，供验证训练使用，如需正式使用，请下载完整COCO数据集或使用定制化数据集。
+```bash
+cd /your_code_path/grounding_dino_mmcv
+cd datasets/
+unzip  coco_mini.zip
+```
+## 训练
+- 数据集放置位置默认为当前目录下 datasets/
+- 如需要变更数据集目录 请修改 [coco_detection.py](configs%2F_base_%2Fdatasets%2Fcoco_detection.py)下的 data_root
+### 单机四卡
+```bash
+cd /your_code_path/grounding_dino_mmcv
+bash ./train_multi.sh
+```
+### 单机单卡
+```bash
+cd /your_code_path/grounding_dino_mmcv
+bash ./train.sh
+```
+## 推理
+- 可使用官方模型权重进行推理，也可使用自己训练模型权重进行推理
+- 这里以官方模型推理举例[[下载地址：groundingdino_swint_ogc_mmdet-822d7e9d.pth](https://download.openmmlab.com/mmdetection/v3.0/grounding_dino/groundingdino_swint_ogc_mmdet-822d7e9d.pth)]
+- 官方推理需要下载nltk的nltk_data中的 tokenizers/punkt和taggers/averaged_perceptron_tagger
+- 可在http://www.nltk.org/nltk_data/ 下载并放于/root/nltk_data下
+- nltk数据如下所示
+`
+├── nltk_data 
+│   ├── taggers
+│       ├── averaged_perceptron_tagger
+│          ├──averaged_perceptron_tagger.pickle
+│   ├── tokenizers
+│       ├──punkt
+│          ├──czech.pickle
+│          ├──anish.pickle
+│          ├──dutch.pickle
+│          ├── ......
+`
+```bash
+# 官方推理代码
+python demo/image_demo.py \
+	demo/demo.jpg \
+	configs/grounding_dino/grounding_dino_swin-t_pretrain_obj365_goldg_cap4m.py \
+	--weights groundingdino_swint_ogc_mmdet-822d7e9d.pth \
+	--texts 'bench . car .'
+```
+## result
+![result.png](asserts%2Fresult.png)
+### 精度
+|       模型名称       | Backbone |  Style  | amp混精 | Box AP@0.95 |
+|:----------------:|:---------:|:-------:|:-----:|:-----------:|
+| Mask R-CNN |    R50  | Scratch |  on   |    48.3     |
+
+## 应用场景
+### 算法类别
+`目标检测`
+### 热点应用行业
+`金融,交通,教育`
+## 源码仓库及问题反馈
+- https://developer.hpccube.com/codes/modelzoo/grounding_dino_mmcv
+## 参考资料
+- https://github.com/open-mmlab/mmdetection/tree/main

configs/_base_/datasets/ade20k_instance.py

+# dataset settings
+dataset_type = 'ADE20KInstanceDataset'
+data_root = 'data/ADEChallengeData2016/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/ADEChallengeData2016/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(2560, 640), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='ade20k_instance_val.json',
+        data_prefix=dict(img='images/validation'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'ade20k_instance_val.json',
+    metric=['bbox', 'segm'],
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator

configs/_base_/datasets/ade20k_panoptic.py

+# dataset settings
+dataset_type = 'ADE20KPanopticDataset'
+data_root = 'data/ADEChallengeData2016/'
+
+backend_args = None
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(2560, 640), keep_ratio=True),
+    dict(type='LoadPanopticAnnotations', backend_args=backend_args),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=0,
+    persistent_workers=False,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='ade20k_panoptic_val.json',
+        data_prefix=dict(img='images/validation/', seg='ade20k_panoptic_val/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoPanopticMetric',
+    ann_file=data_root + 'ade20k_panoptic_val.json',
+    seg_prefix=data_root + 'ade20k_panoptic_val/',
+    backend_args=backend_args)
+test_evaluator = val_evaluator

configs/_base_/datasets/ade20k_semantic.py

+dataset_type = 'ADE20KSegDataset'
+data_root = 'data/ADEChallengeData2016/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/ADEChallengeData2016/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(2048, 512), keep_ratio=True),
+    dict(
+        type='LoadAnnotations',
+        with_bbox=False,
+        with_mask=False,
+        with_seg=True,
+        reduce_zero_label=True),
+    dict(
+        type='PackDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape'))
+]
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/validation',
+            seg_map_path='annotations/validation'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='SemSegMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/cityscapes_detection.py

+# dataset settings
+dataset_type = 'CityscapesDataset'
+data_root = 'data/cityscapes/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/segmentation/cityscapes/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/segmentation/',
+#          'data/': 's3://openmmlab/datasets/segmentation/'
+#      }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='RandomResize',
+        scale=[(2048, 800), (2048, 1024)],
+        keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type='RepeatDataset',
+        times=8,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='annotations/instancesonly_filtered_gtFine_train.json',
+            data_prefix=dict(img='leftImg8bit/train/'),
+            filter_cfg=dict(filter_empty_gt=True, min_size=32),
+            pipeline=train_pipeline,
+            backend_args=backend_args)))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instancesonly_filtered_gtFine_val.json',
+        data_prefix=dict(img='leftImg8bit/val/'),
+        test_mode=True,
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instancesonly_filtered_gtFine_val.json',
+    metric='bbox',
+    backend_args=backend_args)
+
+test_evaluator = val_evaluator

configs/_base_/datasets/cityscapes_instance.py

+# dataset settings
+dataset_type = 'CityscapesDataset'
+data_root = 'data/cityscapes/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/segmentation/cityscapes/'
+
+# Method 2: Use backend_args, file_client_args in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/segmentation/',
+#          'data/': 's3://openmmlab/datasets/segmentation/'
+#      }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='RandomResize',
+        scale=[(2048, 800), (2048, 1024)],
+        keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type='RepeatDataset',
+        times=8,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='annotations/instancesonly_filtered_gtFine_train.json',
+            data_prefix=dict(img='leftImg8bit/train/'),
+            filter_cfg=dict(filter_empty_gt=True, min_size=32),
+            pipeline=train_pipeline,
+            backend_args=backend_args)))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instancesonly_filtered_gtFine_val.json',
+        data_prefix=dict(img='leftImg8bit/val/'),
+        test_mode=True,
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+
+test_dataloader = val_dataloader
+
+val_evaluator = [
+    dict(
+        type='CocoMetric',
+        ann_file=data_root +
+        'annotations/instancesonly_filtered_gtFine_val.json',
+        metric=['bbox', 'segm'],
+        backend_args=backend_args),
+    dict(
+        type='CityScapesMetric',
+        seg_prefix=data_root + 'gtFine/val',
+        outfile_prefix='./work_dirs/cityscapes_metric/instance',
+        backend_args=backend_args)
+]
+
+test_evaluator = val_evaluator
+
+# inference on test dataset and
+# format the output results for submission.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         ann_file='annotations/instancesonly_filtered_gtFine_test.json',
+#         data_prefix=dict(img='leftImg8bit/test/'),
+#         test_mode=True,
+#         filter_cfg=dict(filter_empty_gt=True, min_size=32),
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#         type='CityScapesMetric',
+#         format_only=True,
+#         outfile_prefix='./work_dirs/cityscapes_metric/test')

configs/_base_/datasets/coco_caption.py

+# data settings
+
+dataset_type = 'CocoCaptionDataset'
+data_root = 'data/coco/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+test_pipeline = [
+    dict(
+        type='LoadImageFromFile',
+        imdecode_backend='pillow',
+        backend_args=backend_args),
+    dict(
+        type='Resize',
+        scale=(224, 224),
+        interpolation='bicubic',
+        backend='pillow'),
+    dict(type='PackInputs', meta_keys=['image_id']),
+]
+
+# ann_file download from
+# train dataset: https://storage.googleapis.com/sfr-vision-language-research/datasets/coco_karpathy_train.json # noqa
+# val dataset: https://storage.googleapis.com/sfr-vision-language-research/datasets/coco_karpathy_val.json # noqa
+# test dataset: https://storage.googleapis.com/sfr-vision-language-research/datasets/coco_karpathy_test.json # noqa
+# val evaluator: https://storage.googleapis.com/sfr-vision-language-research/datasets/coco_karpathy_val_gt.json # noqa
+# test evaluator: https://storage.googleapis.com/sfr-vision-language-research/datasets/coco_karpathy_test_gt.json # noqa
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/coco_karpathy_val.json',
+        pipeline=test_pipeline,
+    ))
+
+val_evaluator = dict(
+    type='COCOCaptionMetric',
+    ann_file=data_root + 'annotations/coco_karpathy_val_gt.json',
+)
+
+# # If you want standard test, please manually configure the test dataset
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator

configs/_base_/datasets/coco_detection.py

+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'datasets/coco_mini/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instances_val2017.json',
+    metric='bbox',
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator
+
+# inference on test dataset and
+# format the output results for submission.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#         data_prefix=dict(img='test2017/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='CocoMetric',
+#     metric='bbox',
+#     format_only=True,
+#     ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#     outfile_prefix='./work_dirs/coco_detection/test')