[Feature] Support imagenet pre-training for RTMDet's backbone.

configs/rtmdet/cspnext_imagenet_pretrain/README.md

@@ -0,0 +1,11 @@
+# CSPNeXt ImageNet Pre-training
+
+In this folder, we provide the imagenet pre-training config of RTMDet's backbone CSPNeXt.
+To train with these configs, please install [MMClassification](https://github.com/open-mmlab/mmclassification) first.
+
+## Results and Models
+
+|    Model     | resolution | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) |                                                             Download                                                             |
+| :----------: | :--------: | :-------: | :------: | :-------: | :-------: | :------------------------------------------------------------------------------------------------------------------------------: |
+| CSPNeXt-tiny |  224x224   |   2.73    |  0.339   |   69.44   |   89.45   | [model](https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext_tiny/cspnext-tiny_imagenet_600e.pth) |
+|  CSPNeXt-s   |  224x224   |   4.89    |  0.664   |   74.41   |   92.23   |  [model](https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext_tiny/cspnext-s_imagenet_600e.pth)   |

configs/rtmdet/cspnext_imagenet_pretrain/cspnext-s_8xb256-rsb-a1-600e_in1k.py

@@ -0,0 +1,66 @@
+_base_ = [
+    'mmcls::_base_/datasets/imagenet_bs256_rsb_a12.py',
+    'mmcls::_base_/schedules/imagenet_bs2048_rsb.py',
+    'mmcls::_base_/default_runtime.py'
+]
+
+custom_imports = dict(imports=['mmdet.models'], allow_failed_imports=False)
+
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='mmdet.CSPNeXt',
+        arch='P5',
+        out_indices=(4, ),
+        expand_ratio=0.5,
+        deepen_factor=0.33,
+        widen_factor=0.5,
+        channel_attention=True,
+        norm_cfg=dict(type='BN'),
+        act_cfg=dict(type='mmdet.SiLU')),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=512,
+        loss=dict(
+            type='LabelSmoothLoss',
+            label_smooth_val=0.1,
+            mode='original',
+            loss_weight=1.0),
+        topk=(1, 5)),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.2, num_classes=1000),
+        dict(type='CutMix', alpha=1.0, num_classes=1000)
+    ]))
+
+# dataset settings
+train_dataloader = dict(sampler=dict(type='RepeatAugSampler', shuffle=True))
+
+# schedule settings
+optim_wrapper = dict(
+    optimizer=dict(weight_decay=0.01),
+    paramwise_cfg=dict(bias_decay_mult=0., norm_decay_mult=0.),
+)
+
+param_scheduler = [
+    # warm up learning rate scheduler
+    dict(
+        type='LinearLR',
+        start_factor=0.0001,
+        by_epoch=True,
+        begin=0,
+        end=5,
+        # update by iter
+        convert_to_iter_based=True),
+    # main learning rate scheduler
+    dict(
+        type='CosineAnnealingLR',
+        T_max=595,
+        eta_min=1.0e-6,
+        by_epoch=True,
+        begin=5,
+        end=600)
+]
+
+train_cfg = dict(by_epoch=True, max_epochs=600)

configs/rtmdet/cspnext_imagenet_pretrain/cspnext-tiny_8xb256-rsb-a1-600e_in1k.py

@@ -0,0 +1,5 @@
+_base_ = './cspnext-s_8xb256-rsb-a1-600e_in1k.py'
+
+model = dict(
+    backbone=dict(deepen_factor=0.167, widen_factor=0.375),
+    head=dict(in_channels=384))

configs/rtmdet/rtmdet_s_8xb32-300e_coco.py

@@ -1,5 +1,5 @@
 _base_ = './rtmdet_l_8xb32-300e_coco.py'
-checkpoint = 'TODO:imagenet_pretrain'  # noqa
+checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext_tiny/cspnext-s_imagenet_600e.pth'  # noqa
 model = dict(
     backbone=dict(
         deepen_factor=0.33,

configs/rtmdet/rtmdet_tiny_8xb32-300e_coco.py

@@ -1,6 +1,6 @@
 _base_ = './rtmdet_s_8xb32-300e_coco.py'
 
-checkpoint = 'TODO:imagenet_pretrain'  # noqa
+checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext_tiny/cspnext-tiny_imagenet_600e.pth'  # noqa
 
 model = dict(
     backbone=dict(