Add more new configs (#10573)

open-mmlab · Jun 30, 2023 · b8e4573 · b8e4573
1 parent 8822264
commit b8e4573
Show file tree

Hide file tree

Showing 19 changed files with 1,482 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -121,6 +121,7 @@ We are excited to announce our latest work on real-time object recognition tasks
 **v3.1.0** was released in 30/6/2023:
 
 - Supports tracking algorithms including multi-object tracking (MOT) algorithms SORT, DeepSORT, StrongSORT, OCSORT, ByteTrack, QDTrack, and video instance segmentation (VIS) algorithm MaskTrackRCNN, Mask2Former-VIS.
+- Support [ViTDet](projects/ViTDet)
 - Supports inference and evaluation of multimodal algorithms [GLIP](configs/glip) and [XDecoder](projects/XDecoder), and also supports datasets such as COCO semantic segmentation, COCO Caption, ADE20k general segmentation, and RefCOCO. GLIP fine-tuning will be supported in the future.
 - Provides a [gradio demo](https://github.com/open-mmlab/mmdetection/blob/dev-3.x/projects/gradio_demo/README.md) for image type tasks of MMDetection, making it easy for users to experience.
 

diff --git a/README_zh-CN.md b/README_zh-CN.md
@@ -120,6 +120,7 @@ MMDetection 是一个基于 PyTorch 的目标检测开源工具箱。它是 [Ope
 **v3.1.0** 版本已经在 2023.6.30 发布：
 
 - 支持 Tracking 类算法，包括多目标跟踪 MOT 算法 SORT、DeepSORT、StrongSORT、OCSORT、ByteTrack、QDTrack 和视频实例分割 VIS 算法 MaskTrackRCNN、Mask2Former-VIS。
+- 支持 [ViTDet](projects/ViTDet)
 - 支持多模态开放检测算法 [GLIP](configs/glip) 和 [XDecoder](projects/XDecoder) 推理和评估，并同时支持了 COCO 语义分割、COCO Caption、ADE20k 通用分割、RefCOCO 等数据集。后续将支持 GLIP 微调
 - 提供了包括 MMDetection 图片任务的 [gradio demo](https://github.com/open-mmlab/mmdetection/blob/dev-3.x/projects/gradio_demo/README.md)，方便用户快速体验
 

diff --git a/docs/en/notes/changelog.md b/docs/en/notes/changelog.md
@@ -5,6 +5,7 @@
 ### Highlights
 
 - Supports tracking algorithms including multi-object tracking (MOT) algorithms SORT, DeepSORT, StrongSORT, OCSORT, ByteTrack, QDTrack, and video instance segmentation (VIS) algorithm MaskTrackRCNN, Mask2Former-VIS.
+- Support [ViTDet](../../../projects/ViTDet)
 - Supports inference and evaluation of multimodal algorithms [GLIP](../../../configs/glip) and [XDecoder](../../../projects/XDecoder), and also supports datasets such as COCO semantic segmentation, COCO Caption, ADE20k general segmentation, and RefCOCO. GLIP fine-tuning will be supported in the future.
 - Provides a [gradio demo](https://github.com/open-mmlab/mmdetection/blob/dev-3.x/projects/gradio_demo/README.md) for image type tasks of MMDetection, making it easy for users to experience.
 

diff --git a/docs/en/user_guides/tracking_inference.md b/docs/en/user_guides/tracking_inference.md
@@ -9,7 +9,7 @@ Note that if you use a folder as the input, the image names there must be  **sor
 This script can inference an input video / images with a multiple object tracking or video instance segmentation model.
 
 ```shell
-python demo/demo_mot.py \
+python demo/mot_demo.py \
     ${INPUTS}
     ${CONFIG_FILE} \
     [--checkpoint ${CHECKPOINT_FILE}] \
@@ -39,15 +39,15 @@ Optional arguments:
 
 ```shell
 # Example 1: do not specify --checkpoint to use --detector
-python demo/demo_mot.py \
+python demo/mot_demo.py \
     demo/demo_mot.mp4 \
     configs/sort/sort_faster-rcnn_r50_fpn_8xb2-4e_mot17halftrain_test-mot17halfval.py \
     --detector \
     https://download.openmmlab.com/mmtracking/mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-half-64ee2ed4.pth \
     --out mot.mp4
 
 # Example 2: use --checkpoint
-python demo/demo_mot.py \
+python demo/mot_demo.py \
     demo/demo_mot.mp4 \
     configs/qdtrack/qdtrack_faster-rcnn_r50_fpn_8xb2-4e_mot17halftrain_test-mot17halfval.py \
     --checkpoint https://download.openmmlab.com/mmtracking/mot/qdtrack/mot_dataset/qdtrack_faster-rcnn_r50_fpn_4e_mot17_20220315_145635-76f295ef.pth \

diff --git a/mmdet/configs/_base_/datasets/coco_instance.py b/mmdet/configs/_base_/datasets/coco_instance.py
@@ -0,0 +1,106 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from mmcv.transforms.loading import LoadImageFromFile
+from mmengine.dataset.sampler import DefaultSampler
+
+from mmdet.datasets.coco import CocoDataset
+from mmdet.datasets.samplers.batch_sampler import AspectRatioBatchSampler
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import LoadAnnotations
+from mmdet.datasets.transforms.transforms import RandomFlip, Resize
+from mmdet.evaluation.metrics.coco_metric import CocoMetric
+
+# dataset settings
+dataset_type = 'CocoDataset'
+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
+
+train_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(type=LoadAnnotations, with_bbox=True, with_mask=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, with_mask=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=CocoDataset,
+        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=CocoDataset,
+        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', 'segm'],
+    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=CocoDataset,
+#         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', 'segm'],
+#     format_only=True,
+#     ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#     outfile_prefix='./work_dirs/coco_instance/test')
diff --git a/mmdet/configs/_base_/datasets/coco_instance_semantic.py b/mmdet/configs/_base_/datasets/coco_instance_semantic.py
@@ -0,0 +1,87 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from mmcv.transforms.loading import LoadImageFromFile
+from mmengine.dataset.sampler import DefaultSampler
+
+from mmdet.datasets.coco import CocoDataset
+from mmdet.datasets.samplers.batch_sampler import AspectRatioBatchSampler
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import LoadAnnotations
+from mmdet.datasets.transforms.transforms import RandomFlip, Resize
+from mmdet.evaluation.metrics.coco_metric import CocoMetric
+
+# dataset settings
+dataset_type = 'CocoDataset'
+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
+
+train_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(type=LoadAnnotations, with_bbox=True, with_mask=True, with_seg=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, with_mask=True, with_seg=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=CocoDataset,
+        data_root=data_root,
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/', seg='stuffthingmaps/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=CocoDataset,
+        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', 'segm'],
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator
diff --git a/mmdet/configs/_base_/datasets/coco_panoptic.py b/mmdet/configs/_base_/datasets/coco_panoptic.py
@@ -0,0 +1,105 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from mmcv.transforms.loading import LoadImageFromFile
+from mmengine.dataset.sampler import DefaultSampler
+
+from mmdet.datasets.coco_panoptic import CocoPanopticDataset
+from mmdet.datasets.samplers.batch_sampler import AspectRatioBatchSampler
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import LoadPanopticAnnotations
+from mmdet.datasets.transforms.transforms import RandomFlip, Resize
+from mmdet.evaluation.metrics.coco_panoptic_metric import CocoPanopticMetric
+
+# dataset settings
+dataset_type = 'CocoPanopticDataset'
+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
+
+train_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(type=LoadPanopticAnnotations, backend_args=backend_args),
+    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),
+    dict(type=LoadPanopticAnnotations, backend_args=backend_args),
+    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=CocoPanopticDataset,
+        data_root=data_root,
+        ann_file='annotations/panoptic_train2017.json',
+        data_prefix=dict(
+            img='train2017/', seg='annotations/panoptic_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=CocoPanopticDataset,
+        data_root=data_root,
+        ann_file='annotations/panoptic_val2017.json',
+        data_prefix=dict(img='val2017/', seg='annotations/panoptic_val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type=CocoPanopticMetric,
+    ann_file=data_root + 'annotations/panoptic_val2017.json',
+    seg_prefix=data_root + 'annotations/panoptic_val2017/',
+    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=1,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type=DefaultSampler, shuffle=False),
+#     dataset=dict(
+#         type=CocoPanopticDataset,
+#         data_root=data_root,
+#         ann_file='annotations/panoptic_image_info_test-dev2017.json',
+#         data_prefix=dict(img='test2017/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type=CocoPanopticMetric,
+#     format_only=True,
+#     ann_file=data_root + 'annotations/panoptic_image_info_test-dev2017.json',
+#     outfile_prefix='./work_dirs/coco_panoptic/test')