add config

configs/tood/tood_r101_fpn_dconv_c3-c5_mstrain_2x_coco.py

@@ -0,0 +1,7 @@
+_base_ = './tood_r101_fpn_mstrain_2x_coco.py'
+
+model = dict(
+    backbone=dict(
+        dcn=dict(type='DCNv2', deformable_groups=1, fallback_on_stride=False),
+        stage_with_dcn=(False, True, True, True)),
+    bbox_head=dict(num_dcn_on_head=2))

configs/tood/tood_r101_fpn_mstrain_2x_coco.py

@@ -0,0 +1,7 @@
+_base_ = './tood_r50_fpn_mstrain_2x_coco.py'
+
+model = dict(
+    backbone=dict(
+        depth=101,
+        init_cfg=dict(type='Pretrained',
+                      checkpoint='torchvision://resnet101')))

configs/tood/tood_r50_fpn_mstrain_2x_coco.py

@@ -0,0 +1,22 @@
+_base_ = './tood_r50_fpn_1x_coco.py'
+# learning policy
+lr_config = dict(step=[16, 22])
+runner = dict(type='EpochBasedRunner', max_epochs=24)
+# multi-scale training
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='Resize',
+        img_scale=[(1333, 480), (1333, 800)],
+        multiscale_mode='range',
+        keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+data = dict(train=dict(pipeline=train_pipeline))

configs/tood/tood_x101_64x4d_fpn_dconv_c4-c5_mstrain_2x_coco.py

@@ -0,0 +1,7 @@
+_base_ = './tood_x101_64x4d_fpn_mstrain_2x_coco.py'
+model = dict(
+    backbone=dict(
+        dcn=dict(type='DCNv2', deformable_groups=1, fallback_on_stride=False),
+        stage_with_dcn=(False, False, True, True),
+    ),
+    bbox_head=dict(num_dcn_on_head=2))

configs/tood/tood_x101_64x4d_fpn_mstrain_2x_coco.py

@@ -0,0 +1,16 @@
+_base_ = './tood_r50_fpn_mstrain_2x_coco.py'
+
+model = dict(
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=64,
+        base_width=4,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(
+            type='Pretrained', checkpoint='open-mmlab://resnext101_64x4d')))