[FEATURE] Support YOLOv6 3.0 inference

configs/yolov6/yolov6v3_l_syncbn_fast_8xb32-300e_coco.py

@@ -0,0 +1,28 @@
+_base_ = './yolov6v3_m_syncbn_fast_8xb32-300e_coco.py'
+
+# ======================= Possible modified parameters =======================
+# -----model related-----
+# The scaling factor that controls the depth of the network structure
+deepen_factor = 1
+# The scaling factor that controls the width of the network structure
+widen_factor = 1
+
+# ============================== Unmodified in most cases ===================
+model = dict(
+    backbone=dict(
+        deepen_factor=deepen_factor,
+        widen_factor=widen_factor,
+        hidden_ratio=1. / 2,
+        block_cfg=dict(
+            type='ConvWrapper',
+            norm_cfg=dict(type='BN', momentum=0.03, eps=0.001)),
+        act_cfg=dict(type='SiLU', inplace=True)),
+    neck=dict(
+        deepen_factor=deepen_factor,
+        widen_factor=widen_factor,
+        hidden_ratio=1. / 2,
+        block_cfg=dict(
+            type='ConvWrapper',
+            norm_cfg=dict(type='BN', momentum=0.03, eps=0.001)),
+        block_act_cfg=dict(type='SiLU', inplace=True)),
+    bbox_head=dict(head_module=dict(widen_factor=widen_factor)))

configs/yolov6/yolov6v3_m_syncbn_fast_8xb32-300e_coco.py

@@ -0,0 +1,63 @@
+_base_ = './yolov6v3_s_syncbn_fast_8xb32-300e_coco.py'
+
+# ======================= Possible modified parameters =======================
+# -----model related-----
+# The scaling factor that controls the depth of the network structure
+deepen_factor = 0.6
+# The scaling factor that controls the width of the network structure
+widen_factor = 0.75
+
+# -----train val related-----
+affine_scale = 0.9  # YOLOv5RandomAffine scaling ratio
+
+# ============================== Unmodified in most cases ===================
+model = dict(
+    backbone=dict(
+        type='YOLOv6CSPBep',
+        deepen_factor=deepen_factor,
+        widen_factor=widen_factor,
+        hidden_ratio=2. / 3,
+        block_cfg=dict(type='RepVGGBlock'),
+        act_cfg=dict(type='ReLU', inplace=True)),
+    neck=dict(
+        type='YOLOv6CSPRepBiPAFPN',
+        deepen_factor=deepen_factor,
+        widen_factor=widen_factor,
+        block_cfg=dict(type='RepVGGBlock'),
+        hidden_ratio=2. / 3,
+        block_act_cfg=dict(type='ReLU', inplace=True)),
+    bbox_head=dict(
+        type='YOLOv6Head',
+        head_module=dict(reg_max=16, widen_factor=widen_factor)))
+
+mosaic_affine_pipeline = [
+    dict(
+        type='Mosaic',
+        img_scale=_base_.img_scale,
+        pad_val=114.0,
+        pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - affine_scale, 1 + affine_scale),
+        # img_scale is (width, height)
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114))
+]
+
+train_pipeline = [
+    *_base_.pre_transform, *mosaic_affine_pipeline,
+    dict(
+        type='YOLOv5MixUp',
+        prob=0.1,
+        pre_transform=[*_base_.pre_transform, *mosaic_affine_pipeline]),
+    dict(type='YOLOv5HSVRandomAug'),
+    dict(type='mmdet.RandomFlip', prob=0.5),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                   'flip_direction'))
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))

configs/yolov6/yolov6v3_n_syncbn_fast_8xb32-400e_coco.py

@@ -0,0 +1,21 @@
+_base_ = './yolov6v3_s_syncbn_fast_8xb32-400e_coco.py'
+
+# ======================= Possible modified parameters =======================
+# -----model related-----
+# The scaling factor that controls the depth of the network structure
+deepen_factor = 0.33
+# The scaling factor that controls the width of the network structure
+widen_factor = 0.25
+
+# -----train val related-----
+lr_factor = 0.02  # Learning rate scaling factor
+
+# ============================== Unmodified in most cases ===================
+model = dict(
+    backbone=dict(deepen_factor=deepen_factor, widen_factor=widen_factor),
+    neck=dict(deepen_factor=deepen_factor, widen_factor=widen_factor),
+    bbox_head=dict(
+        head_module=dict(widen_factor=widen_factor),
+        loss_bbox=dict(iou_mode='siou')))
+
+default_hooks = dict(param_scheduler=dict(lr_factor=lr_factor))

configs/yolov6/yolov6v3_s_syncbn_fast_8xb32-300e_coco.py

@@ -0,0 +1,33 @@
+_base_ = './yolov6v3_s_syncbn_fast_8xb32-400e_coco.py'
+
+# ======================= Frequently modified parameters =====================
+# -----train val related-----
+# Base learning rate for optim_wrapper
+max_epochs = 300  # Maximum training epochs
+num_last_epochs = 15  # Last epoch number to switch training pipeline
+
+# ============================== Unmodified in most cases ===================
+default_hooks = dict(
+    param_scheduler=dict(
+        type='YOLOv5ParamSchedulerHook',
+        scheduler_type='cosine',
+        lr_factor=0.01,
+        max_epochs=max_epochs))
+
+custom_hooks = [
+    dict(
+        type='EMAHook',
+        ema_type='ExpMomentumEMA',
+        momentum=0.0001,
+        update_buffers=True,
+        strict_load=False,
+        priority=49),
+    dict(
+        type='mmdet.PipelineSwitchHook',
+        switch_epoch=max_epochs - num_last_epochs,
+        switch_pipeline=_base_.train_pipeline_stage2)
+]
+
+train_cfg = dict(
+    max_epochs=max_epochs,
+    dynamic_intervals=[(max_epochs - num_last_epochs, 1)])