[CodeCamp2023-xxx] Add new configs of RTMDet (#10840)

demo/inference_demo.ipynb

@@ -26,7 +26,7 @@
         "  </div>\n",
         "  <div>&nbsp;</div>\n",
         "\n",
-        "<a href=\"https://colab.research.google.com/github/open-mmlab/mmdetection/blob/dev-3.x/demo/MMDet_Tutorial.ipynb\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"></a>\n",
+        "<a href=\"https://colab.research.google.com/github/open-mmlab/mmdetection/blob/dev-3.x/demo/inference_demo.ipynb\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"></a>\n",
         "\n",
         "[![PyPI](https://img.shields.io/pypi/v/mmdet)](https://pypi.org/project/mmdet)\n",
         "[![docs](https://img.shields.io/badge/docs-latest-blue)](https://mmdetection.readthedocs.io/en/latest/)\n",

mmdet/apis/det_inferencer.py

@@ -2,12 +2,13 @@
 import copy
 import os.path as osp
 import warnings
-from typing import Dict, Iterable, List, Optional, Sequence, Union
+from typing import Dict, Iterable, List, Optional, Sequence, Tuple, Union
 
 import mmcv
 import mmengine
 import numpy as np
 import torch.nn as nn
+from mmcv.transforms import LoadImageFromFile
 from mmengine.dataset import Compose
 from mmengine.fileio import (get_file_backend, isdir, join_path,
                              list_dir_or_file)
@@ -165,21 +166,22 @@ def _init_pipeline(self, cfg: ConfigType) -> Compose:
                 meta_key for meta_key in pipeline_cfg[-1]['meta_keys']
                 if meta_key != 'img_id')
 
-        load_img_idx = self._get_transform_idx(pipeline_cfg,
-                                               'LoadImageFromFile')
+        load_img_idx = self._get_transform_idx(
+            pipeline_cfg, ('LoadImageFromFile', LoadImageFromFile))
         if load_img_idx == -1:
             raise ValueError(
                 'LoadImageFromFile is not found in the test pipeline')
         pipeline_cfg[load_img_idx]['type'] = 'mmdet.InferencerLoader'
         return Compose(pipeline_cfg)
 
-    def _get_transform_idx(self, pipeline_cfg: ConfigType, name: str) -> int:
+    def _get_transform_idx(self, pipeline_cfg: ConfigType,
+                           name: Union[str, Tuple[str, type]]) -> int:
         """Returns the index of the transform in a pipeline.
 
         If the transform is not found, returns -1.
         """
         for i, transform in enumerate(pipeline_cfg):
-            if transform['type'] == name:
+            if transform['type'] in name:
                 return i
         return -1
 

mmdet/configs/rtmdet/rtmdet_ins_l_8xb32_300e_coco.py

@@ -0,0 +1,134 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .rtmdet_l_8xb32_300e_coco import *
+
+from mmcv.transforms.loading import LoadImageFromFile
+from mmcv.transforms.processing import RandomResize
+from mmengine.hooks.ema_hook import EMAHook
+from torch.nn.modules.activation import SiLU
+
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import (FilterAnnotations,
+                                               LoadAnnotations)
+from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
+                                                  Pad, RandomCrop, RandomFlip,
+                                                  Resize, YOLOXHSVRandomAug)
+from mmdet.engine.hooks.pipeline_switch_hook import PipelineSwitchHook
+from mmdet.models.dense_heads.rtmdet_ins_head import RTMDetInsSepBNHead
+from mmdet.models.layers.ema import ExpMomentumEMA
+from mmdet.models.losses.dice_loss import DiceLoss
+from mmdet.models.losses.gfocal_loss import QualityFocalLoss
+from mmdet.models.losses.iou_loss import GIoULoss
+from mmdet.models.task_modules.coders.distance_point_bbox_coder import \
+    DistancePointBBoxCoder
+from mmdet.models.task_modules.prior_generators.point_generator import \
+    MlvlPointGenerator
+
+model.merge(
+    dict(
+        bbox_head=dict(
+            _delete_=True,
+            type=RTMDetInsSepBNHead,
+            num_classes=80,
+            in_channels=256,
+            stacked_convs=2,
+            share_conv=True,
+            pred_kernel_size=1,
+            feat_channels=256,
+            act_cfg=dict(type=SiLU, inplace=True),
+            norm_cfg=dict(type='SyncBN', requires_grad=True),
+            anchor_generator=dict(
+                type=MlvlPointGenerator, offset=0, strides=[8, 16, 32]),
+            bbox_coder=dict(type=DistancePointBBoxCoder),
+            loss_cls=dict(
+                type=QualityFocalLoss,
+                use_sigmoid=True,
+                beta=2.0,
+                loss_weight=1.0),
+            loss_bbox=dict(type=GIoULoss, loss_weight=2.0),
+            loss_mask=dict(
+                type=DiceLoss, loss_weight=2.0, eps=5e-6, reduction='mean')),
+        test_cfg=dict(
+            nms_pre=1000,
+            min_bbox_size=0,
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.6),
+            max_per_img=100,
+            mask_thr_binary=0.5),
+    ))
+
+train_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(
+        type=LoadAnnotations, with_bbox=True, with_mask=True, poly2mask=False),
+    dict(type=CachedMosaic, img_scale=(640, 640), pad_val=114.0),
+    dict(
+        type=RandomResize,
+        scale=(1280, 1280),
+        ratio_range=(0.1, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(
+        type=RandomCrop,
+        crop_size=(640, 640),
+        recompute_bbox=True,
+        allow_negative_crop=True),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type=CachedMixUp,
+        img_scale=(640, 640),
+        ratio_range=(1.0, 1.0),
+        max_cached_images=20,
+        pad_val=(114, 114, 114)),
+    dict(type=FilterAnnotations, min_gt_bbox_wh=(1, 1)),
+    dict(type=PackDetInputs)
+]
+
+train_dataloader.update(
+    dict(pin_memory=True, dataset=dict(pipeline=train_pipeline)))
+
+train_pipeline_stage2 = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(
+        type=LoadAnnotations, with_bbox=True, with_mask=True, poly2mask=False),
+    dict(
+        type=RandomResize,
+        scale=(640, 640),
+        ratio_range=(0.1, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(
+        type=RandomCrop,
+        crop_size=(640, 640),
+        recompute_bbox=True,
+        allow_negative_crop=True),
+    dict(type=FilterAnnotations, min_gt_bbox_wh=(1, 1)),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(type=PackDetInputs)
+]
+custom_hooks = [
+    dict(
+        type=EMAHook,
+        ema_type=ExpMomentumEMA,
+        momentum=0.0002,
+        update_buffers=True,
+        priority=49),
+    dict(
+        type=PipelineSwitchHook,
+        switch_epoch=280,
+        switch_pipeline=train_pipeline_stage2)
+]
+
+val_evaluator.update(dict(metric=['bbox', 'segm']))
+test_evaluator = val_evaluator

mmdet/configs/rtmdet/rtmdet_ins_m_8xb32_300e_coco.py

@@ -0,0 +1,17 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .rtmdet_ins_l_8xb32_300e_coco import *
+
+model.update(
+    dict(
+        backbone=dict(deepen_factor=0.67, widen_factor=0.75),
+        neck=dict(
+            in_channels=[192, 384, 768], out_channels=192, num_csp_blocks=2),
+        bbox_head=dict(in_channels=192, feat_channels=192)))

mmdet/configs/rtmdet/rtmdet_ins_s_8xb32_300e_coco.py

@@ -0,0 +1,101 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .rtmdet_ins_l_8xb32_300e_coco import *
+
+from mmcv.transforms.loading import LoadImageFromFile
+from mmcv.transforms.processing import RandomResize
+from mmengine.hooks.ema_hook import EMAHook
+
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import (FilterAnnotations,
+                                               LoadAnnotations)
+from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
+                                                  Pad, RandomCrop, RandomFlip,
+                                                  Resize, YOLOXHSVRandomAug)
+from mmdet.engine.hooks.pipeline_switch_hook import PipelineSwitchHook
+from mmdet.models.layers.ema import ExpMomentumEMA
+
+checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-s_imagenet_600e.pth'  # noqa
+model.update(
+    dict(
+        backbone=dict(
+            deepen_factor=0.33,
+            widen_factor=0.5,
+            init_cfg=dict(
+                type='Pretrained', prefix='backbone.', checkpoint=checkpoint)),
+        neck=dict(
+            in_channels=[128, 256, 512], out_channels=128, num_csp_blocks=1),
+        bbox_head=dict(in_channels=128, feat_channels=128)))
+
+train_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(
+        type=LoadAnnotations, with_bbox=True, with_mask=True, poly2mask=False),
+    dict(type=CachedMosaic, img_scale=(640, 640), pad_val=114.0),
+    dict(
+        type=RandomResize,
+        scale=(1280, 1280),
+        ratio_range=(0.5, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(
+        type=RandomCrop,
+        crop_size=(640, 640),
+        recompute_bbox=True,
+        allow_negative_crop=True),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type=CachedMixUp,
+        img_scale=(640, 640),
+        ratio_range=(1.0, 1.0),
+        max_cached_images=20,
+        pad_val=(114, 114, 114)),
+    dict(type=FilterAnnotations, min_gt_bbox_wh=(1, 1)),
+    dict(type=PackDetInputs)
+]
+
+train_pipeline_stage2 = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(
+        type=LoadAnnotations, with_bbox=True, with_mask=True, poly2mask=False),
+    dict(
+        type=RandomResize,
+        scale=(640, 640),
+        ratio_range=(0.5, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(
+        type=RandomCrop,
+        crop_size=(640, 640),
+        recompute_bbox=True,
+        allow_negative_crop=True),
+    dict(type=FilterAnnotations, min_gt_bbox_wh=(1, 1)),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(type=PackDetInputs)
+]
+
+train_dataloader.update(dict(dataset=dict(pipeline=train_pipeline)))
+
+custom_hooks = [
+    dict(
+        type=EMAHook,
+        ema_type=ExpMomentumEMA,
+        momentum=0.0002,
+        update_buffers=True,
+        priority=49),
+    dict(
+        type=PipelineSwitchHook,
+        switch_epoch=280,
+        switch_pipeline=train_pipeline_stage2)
+]

mmdet/configs/rtmdet/rtmdet_ins_tiny_8xb32_300e_coco.py

@@ -0,0 +1,67 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+
+# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
+# mmcv >= 2.0.1
+# mmengine >= 0.8.0
+
+from mmengine.config import read_base
+
+with read_base():
+    from .rtmdet_ins_s_8xb32_300e_coco import *
+
+from mmcv.transforms.loading import LoadImageFromFile
+from mmcv.transforms.processing import RandomResize
+
+from mmdet.datasets.transforms.formatting import PackDetInputs
+from mmdet.datasets.transforms.loading import (FilterAnnotations,
+                                               LoadAnnotations)
+from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
+                                                  Pad, RandomCrop, RandomFlip,
+                                                  Resize, YOLOXHSVRandomAug)
+
+checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-tiny_imagenet_600e.pth'  # noqa
+
+model.update(
+    dict(
+        backbone=dict(
+            deepen_factor=0.167,
+            widen_factor=0.375,
+            init_cfg=dict(
+                type='Pretrained', prefix='backbone.', checkpoint=checkpoint)),
+        neck=dict(
+            in_channels=[96, 192, 384], out_channels=96, num_csp_blocks=1),
+        bbox_head=dict(in_channels=96, feat_channels=96)))
+
+train_pipeline = [
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(
+        type=LoadAnnotations, with_bbox=True, with_mask=True, poly2mask=False),
+    dict(
+        type=CachedMosaic,
+        img_scale=(640, 640),
+        pad_val=114.0,
+        max_cached_images=20,
+        random_pop=False),
+    dict(
+        type=RandomResize,
+        scale=(1280, 1280),
+        ratio_range=(0.5, 2.0),
+        resize_type=Resize,
+        keep_ratio=True),
+    dict(type=RandomCrop, crop_size=(640, 640)),
+    dict(type=YOLOXHSVRandomAug),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=Pad, size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type=CachedMixUp,
+        img_scale=(640, 640),
+        ratio_range=(1.0, 1.0),
+        max_cached_images=10,
+        random_pop=False,
+        pad_val=(114, 114, 114),
+        prob=0.5),
+    dict(type=FilterAnnotations, min_gt_bbox_wh=(1, 1)),
+    dict(type=PackDetInputs)
+]
+
+train_dataloader.update(dict(dataset=dict(pipeline=train_pipeline)))