Upload 40 files

configs/coco.yml

@@ -0,0 +1,82 @@
+# Classes
+names:
+  0: person
+  1: bicycle
+  2: car
+  3: motorcycle
+  4: airplane
+  5: bus
+  6: train
+  7: truck
+  8: boat
+  9: traffic light
+  10: fire hydrant
+  11: stop sign
+  12: parking meter
+  13: bench
+  14: bird
+  15: cat
+  16: dog
+  17: horse
+  18: sheep
+  19: cow
+  20: elephant
+  21: bear
+  22: zebra
+  23: giraffe
+  24: backpack
+  25: umbrella
+  26: handbag
+  27: tie
+  28: suitcase
+  29: frisbee
+  30: skis
+  31: snowboard
+  32: sports ball
+  33: kite
+  34: baseball bat
+  35: baseball glove
+  36: skateboard
+  37: surfboard
+  38: tennis racket
+  39: bottle
+  40: wine glass
+  41: cup
+  42: fork
+  43: knife
+  44: spoon
+  45: bowl
+  46: banana
+  47: apple
+  48: sandwich
+  49: orange
+  50: broccoli
+  51: carrot
+  52: hot dog
+  53: pizza
+  54: donut
+  55: cake
+  56: chair
+  57: couch
+  58: potted plant
+  59: bed
+  60: dining table
+  61: toilet
+  62: tv
+  63: laptop
+  64: mouse
+  65: remote
+  66: keyboard
+  67: cell phone
+  68: microwave
+  69: oven
+  70: toaster
+  71: sink
+  72: refrigerator
+  73: book
+  74: clock
+  75: vase
+  76: scissors
+  77: teddy bear
+  78: hair drier
+  79: toothbrush

configs/dataset/coco_detection.yml

@@ -0,0 +1,41 @@
+task: detection
+
+evaluator:
+  type: CocoEvaluator
+  iou_types: ['bbox', ]
+
+num_classes: 80
+remap_mscoco_category: True
+
+train_dataloader:
+  type: DataLoader
+  dataset:
+    type: CocoDetection
+    img_folder: /data/COCO2017/train2017/
+    ann_file: /data/COCO2017/annotations/instances_train2017.json
+    return_masks: False
+    transforms:
+      type: Compose
+      ops: ~
+  shuffle: True
+  num_workers: 4
+  drop_last: True
+  collate_fn:
+    type: BatchImageCollateFunction
+
+
+val_dataloader:
+  type: DataLoader
+  dataset:
+    type: CocoDetection
+    img_folder: /data/COCO2017/val2017/
+    ann_file: /data/COCO2017/annotations/instances_val2017.json
+    return_masks: False
+    transforms:
+      type: Compose
+      ops: ~
+  shuffle: False
+  num_workers: 4
+  drop_last: False
+  collate_fn:
+    type: BatchImageCollateFunction

configs/dataset/crowdhuman_detection.yml

@@ -0,0 +1,41 @@
+task: detection
+
+evaluator:
+  type: CocoEvaluator
+  iou_types: ['bbox', ]
+
+num_classes: 1 # your dataset classes
+remap_mscoco_category: False
+
+train_dataloader:
+  type: DataLoader
+  dataset:
+    type: CocoDetection
+    img_folder: /data/CrowdHuman/coco/CrowdHuman_train
+    ann_file: /data/CrowdHuman/coco/Chuman-train.json
+    return_masks: False
+    transforms:
+      type: Compose
+      ops: ~
+  shuffle: True
+  num_workers: 4
+  drop_last: True
+  collate_fn:
+    type: BatchImageCollateFunction
+
+
+val_dataloader:
+  type: DataLoader
+  dataset:
+    type: CocoDetection
+    img_folder: /data/CrowdHuman/coco/CrowdHuman_val
+    ann_file: /data/CrowdHuman/coco/Chuman-val.json
+    return_masks: False
+    transforms:
+      type: Compose
+      ops: ~
+  shuffle: False
+  num_workers: 4
+  drop_last: False
+  collate_fn:
+    type: BatchImageCollateFunction

configs/dataset/custom_detection.yml

@@ -0,0 +1,41 @@
+task: detection
+
+evaluator:
+  type: CocoEvaluator
+  iou_types: ['bbox', ]
+
+num_classes: 777 # your dataset classes
+remap_mscoco_category: False
+
+train_dataloader:
+  type: DataLoader
+  dataset:
+    type: CocoDetection
+    img_folder: /data/yourdataset/train
+    ann_file: /data/yourdataset/train/train.json
+    return_masks: False
+    transforms:
+      type: Compose
+      ops: ~
+  shuffle: True
+  num_workers: 4
+  drop_last: True
+  collate_fn:
+    type: BatchImageCollateFunction
+
+
+val_dataloader:
+  type: DataLoader
+  dataset:
+    type: CocoDetection
+    img_folder: /data/yourdataset/val
+    ann_file: /data/yourdataset/val/val.json
+    return_masks: False
+    transforms:
+      type: Compose
+      ops: ~
+  shuffle: False
+  num_workers: 4
+  drop_last: False
+  collate_fn:
+    type: BatchImageCollateFunction

configs/dataset/obj365_detection.yml

@@ -0,0 +1,41 @@
+task: detection
+
+evaluator:
+  type: CocoEvaluator
+  iou_types: ['bbox', ]
+
+num_classes: 366
+remap_mscoco_category: False
+
+train_dataloader:
+  type: DataLoader
+  dataset:
+    type: CocoDetection
+    img_folder: /data/Objects365/data/train
+    ann_file: /data/Objects365/data/train/new_zhiyuan_objv2_train_resized.json
+    return_masks: False
+    transforms:
+      type: Compose
+      ops: ~
+  shuffle: True
+  num_workers: 4
+  drop_last: True
+  collate_fn:
+    type: BatchImageCollateFunction
+
+
+val_dataloader:
+  type: DataLoader
+  dataset:
+    type: CocoDetection
+    img_folder: /data/Objects365/data/val/
+    ann_file: /data/Objects365/data/val/new_zhiyuan_objv2_val_resized.json
+    return_masks: False
+    transforms:
+      type: Compose
+      ops: ~
+  shuffle: False
+  num_workers: 4
+  drop_last: False
+  collate_fn:
+    type: BatchImageCollateFunction

configs/dataset/voc_detection.yml

@@ -0,0 +1,40 @@
+task: detection
+
+evaluator:
+  type: CocoEvaluator
+  iou_types: ['bbox', ]
+
+num_classes: 20
+
+train_dataloader:
+  type: DataLoader
+  dataset:
+    type: VOCDetection
+    root: ./dataset/voc/
+    ann_file: trainval.txt
+    label_file: label_list.txt
+    transforms:
+      type: Compose
+      ops: ~
+  shuffle: True
+  num_workers: 4
+  drop_last: True
+  collate_fn:
+    type: BatchImageCollateFunction
+
+
+val_dataloader:
+  type: DataLoader
+  dataset:
+    type: VOCDetection
+    root: ./dataset/voc/
+    ann_file: test.txt
+    label_file: label_list.txt
+    transforms:
+      type: Compose
+      ops: ~
+  shuffle: False
+  num_workers: 4
+  drop_last: False
+  collate_fn:
+    type: BatchImageCollateFunction

configs/dfine/crowdhuman/dfine_hgnetv2_l_ch.yml

@@ -0,0 +1,44 @@
+__include__: [
+  '../../dataset/crowdhuman_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_l_crowdhuman
+
+
+HGNetv2:
+  name: 'B4'
+  return_idx: [1, 2, 3]
+  freeze_stem_only: True
+  freeze_at: 0
+  freeze_norm: True
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0000125
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+# Increase to search for the optimal ema
+epochs: 140
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 120
+  collate_fn:
+    stop_epoch: 120
+    ema_restart_decay: 0.9999
+    base_size_repeat: 4

configs/dfine/crowdhuman/dfine_hgnetv2_m_ch.yml

@@ -0,0 +1,60 @@
+__include__: [
+  '../../dataset/crowdhuman_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_m_crowdhuman
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B2'
+  return_idx: [1, 2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+DFINETransformer:
+  num_layers: 4  # 5 6
+  eval_idx: -1  # -2 -3
+
+HybridEncoder:
+  in_channels: [384, 768, 1536]
+  hidden_dim: 256
+  depth_mult: 0.67
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.000025
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.000025
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+# Increase to search for the optimal ema
+epochs: 220
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 200
+  collate_fn:
+    stop_epoch: 200
+    ema_restart_decay: 0.9999
+    base_size_repeat: 6

configs/dfine/crowdhuman/dfine_hgnetv2_n_ch.yml

@@ -0,0 +1,82 @@
+__include__: [
+  '../../dataset/crowdhuman_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_n_crowdhuman
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B0'
+  return_idx: [2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+
+HybridEncoder:
+  in_channels: [512, 1024]
+  feat_strides: [16, 32]
+
+  # intra
+  hidden_dim: 128
+  use_encoder_idx: [1]
+  dim_feedforward: 512
+
+  # cross
+  expansion: 0.34
+  depth_mult: 0.5
+
+
+DFINETransformer:
+  feat_channels: [128, 128]
+  feat_strides: [16, 32]
+  hidden_dim: 128
+  dim_feedforward: 512
+  num_levels: 2
+
+  num_layers: 3
+  eval_idx: -1
+
+  num_points: [6, 6]
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0004
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.0004
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.0008
+  betas: [0.9, 0.999]
+  weight_decay: 0.0001
+
+
+# Increase to search for the optimal ema
+epochs: 220
+train_dataloader:
+  total_batch_size: 128
+  dataset:
+    transforms:
+      policy:
+        epoch: 200
+  collate_fn:
+    stop_epoch: 200
+    ema_restart_decay: 0.9999
+    base_size_repeat: ~
+
+val_dataloader:
+  total_batch_size: 256

configs/dfine/crowdhuman/dfine_hgnetv2_s_ch.yml

@@ -0,0 +1,65 @@
+__include__: [
+  '../../dataset/crowdhuman_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_s_crowdhuman
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B0'
+  return_idx: [1, 2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+DFINETransformer:
+  num_layers: 3  # 4 5 6
+  eval_idx: -1  # -2 -3 -4
+
+HybridEncoder:
+  in_channels: [256, 512, 1024]
+  hidden_dim: 256
+  depth_mult: 0.34
+  expansion: 0.5
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0002
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.0002
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.0004
+  betas: [0.9, 0.999]
+  weight_decay: 0.0001
+
+
+# Increase to search for the optimal ema
+epochs: 220
+train_dataloader:
+  total_batch_size: 64
+  dataset:
+    transforms:
+      policy:
+        epoch: 200
+  collate_fn:
+    stop_epoch: 200
+    ema_restart_decay: 0.9999
+    base_size_repeat: 20
+
+val_dataloader:
+  total_batch_size: 128

configs/dfine/crowdhuman/dfine_hgnetv2_x_ch.yml

@@ -0,0 +1,55 @@
+__include__: [
+  '../../dataset/crowdhuman_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_x_crowdhuman
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B5'
+  return_idx: [1, 2, 3]
+  freeze_stem_only: True
+  freeze_at: 0
+  freeze_norm: True
+
+HybridEncoder:
+  hidden_dim: 384
+  dim_feedforward: 2048
+
+DFINETransformer:
+  feat_channels: [384, 384, 384]
+  reg_scale: 8
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0000025
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+# Increase to search for the optimal ema
+epochs: 140
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 120
+  collate_fn:
+    stop_epoch: 120
+    ema_restart_decay: 0.9998
+    base_size_repeat: 3

configs/dfine/custom/dfine_hgnetv2_l_custom.yml

@@ -0,0 +1,44 @@
+__include__: [
+  '../../dataset/custom_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_l_custom
+
+
+HGNetv2:
+  name: 'B4'
+  return_idx: [1, 2, 3]
+  freeze_stem_only: True
+  freeze_at: 0
+  freeze_norm: True
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0000125
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+# Increase to search for the optimal ema
+epochs: 80 # 72 + 2n
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 72
+  collate_fn:
+    stop_epoch: 72
+    ema_restart_decay: 0.9999
+    base_size_repeat: 4

configs/dfine/custom/dfine_hgnetv2_m_custom.yml

@@ -0,0 +1,60 @@
+__include__: [
+  '../../dataset/custom_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_m_custom
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B2'
+  return_idx: [1, 2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+DFINETransformer:
+  num_layers: 4  # 5 6
+  eval_idx: -1  # -2 -3
+
+HybridEncoder:
+  in_channels: [384, 768, 1536]
+  hidden_dim: 256
+  depth_mult: 0.67
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.000025
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.000025
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+# Increase to search for the optimal ema
+epochs: 132 # 120 + 4n
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 120
+  collate_fn:
+    stop_epoch: 120
+    ema_restart_decay: 0.9999
+    base_size_repeat: 6

configs/dfine/custom/dfine_hgnetv2_n_custom.yml

@@ -0,0 +1,82 @@
+__include__: [
+  '../../dataset/custom_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_n_custom
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B0'
+  return_idx: [2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+
+HybridEncoder:
+  in_channels: [512, 1024]
+  feat_strides: [16, 32]
+
+  # intra
+  hidden_dim: 128
+  use_encoder_idx: [1]
+  dim_feedforward: 512
+
+  # cross
+  expansion: 0.34
+  depth_mult: 0.5
+
+
+DFINETransformer:
+  feat_channels: [128, 128]
+  feat_strides: [16, 32]
+  hidden_dim: 128
+  dim_feedforward: 512
+  num_levels: 2
+
+  num_layers: 3
+  eval_idx: -1
+
+  num_points: [6, 6]
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0004
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.0004
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.0008
+  betas: [0.9, 0.999]
+  weight_decay: 0.0001
+
+
+# Increase to search for the optimal ema
+epochs: 220
+train_dataloader:
+  total_batch_size: 128
+  dataset:
+    transforms:
+      policy:
+        epoch: 200
+  collate_fn:
+    stop_epoch: 200
+    ema_restart_decay: 0.9999
+    base_size_repeat: ~
+
+val_dataloader:
+  total_batch_size: 256

configs/dfine/custom/dfine_hgnetv2_s_custom.yml

@@ -0,0 +1,65 @@
+__include__: [
+  '../../dataset/custom_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_s_custom
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B0'
+  return_idx: [1, 2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+DFINETransformer:
+  num_layers: 3  # 4 5 6
+  eval_idx: -1  # -2 -3 -4
+
+HybridEncoder:
+  in_channels: [256, 512, 1024]
+  hidden_dim: 256
+  depth_mult: 0.34
+  expansion: 0.5
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0002
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.0002
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.0004
+  betas: [0.9, 0.999]
+  weight_decay: 0.0001
+
+
+# Increase to search for the optimal ema
+epochs: 220
+train_dataloader:
+  total_batch_size: 64
+  dataset:
+    transforms:
+      policy:
+        epoch: 200
+  collate_fn:
+    stop_epoch: 200
+    ema_restart_decay: 0.9999
+    base_size_repeat: 20
+
+val_dataloader:
+  total_batch_size: 128

configs/dfine/custom/dfine_hgnetv2_x_custom.yml

@@ -0,0 +1,55 @@
+__include__: [
+  '../../dataset/custom_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_x_custom
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B5'
+  return_idx: [1, 2, 3]
+  freeze_stem_only: True
+  freeze_at: 0
+  freeze_norm: True
+
+HybridEncoder:
+  hidden_dim: 384
+  dim_feedforward: 2048
+
+DFINETransformer:
+  feat_channels: [384, 384, 384]
+  reg_scale: 8
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0000025
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+# Increase to search for the optimal ema
+epochs: 80 # 72 + 2n
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 72
+  collate_fn:
+    stop_epoch: 72
+    ema_restart_decay: 0.9998
+    base_size_repeat: 3

configs/dfine/custom/objects365/dfine_hgnetv2_l_obj2custom.yml

@@ -0,0 +1,53 @@
+__include__: [
+  '../../../dataset/custom_detection.yml',
+  '../../../runtime.yml',
+  '../../include/dataloader.yml',
+  '../../include/optimizer.yml',
+  '../../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_l_obj2custom
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B4'
+  return_idx: [1, 2, 3]
+  freeze_stem_only: True
+  freeze_at: 0
+  freeze_norm: True
+  pretrained: False
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0000125
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+epochs: 36 # Early stop
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 30
+  collate_fn:
+    stop_epoch: 30
+    ema_restart_decay: 0.9999
+    base_size_repeat: 4
+
+ema:
+  warmups: 0
+
+lr_warmup_scheduler:
+  warmup_duration: 0

configs/dfine/custom/objects365/dfine_hgnetv2_m_obj2custom.yml

@@ -0,0 +1,66 @@
+__include__: [
+  '../../../dataset/custom_detection.yml',
+  '../../../runtime.yml',
+  '../../include/dataloader.yml',
+  '../../include/optimizer.yml',
+  '../../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_m_obj2custom
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B2'
+  return_idx: [1, 2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+  pretrained: False
+
+DFINETransformer:
+  num_layers: 4  # 5 6
+  eval_idx: -1  # -2 -3
+
+HybridEncoder:
+  in_channels: [384, 768, 1536]
+  hidden_dim: 256
+  depth_mult: 0.67
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.000025
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.000025
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+epochs: 56 # Early stop
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 48
+  collate_fn:
+    stop_epoch: 48
+    ema_restart_decay: 0.9999
+    base_size_repeat: 6
+
+ema:
+  warmups: 0
+
+lr_warmup_scheduler:
+  warmup_duration: 0

configs/dfine/custom/objects365/dfine_hgnetv2_s_obj2custom.yml

@@ -0,0 +1,67 @@
+__include__: [
+  '../../../dataset/custom_detection.yml',
+  '../../../runtime.yml',
+  '../../include/dataloader.yml',
+  '../../include/optimizer.yml',
+  '../../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_s_obj2custom
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B0'
+  return_idx: [1, 2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+  pretrained: False
+
+DFINETransformer:
+  num_layers: 3  # 4 5 6
+  eval_idx: -1  # -2 -3 -4
+
+HybridEncoder:
+  in_channels: [256, 512, 1024]
+  hidden_dim: 256
+  depth_mult: 0.34
+  expansion: 0.5
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.000125
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.000125
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+epochs: 64 # Early stop
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 56
+  collate_fn:
+    stop_epoch: 56
+    ema_restart_decay: 0.9999
+    base_size_repeat: 10
+
+ema:
+  warmups: 0
+
+lr_warmup_scheduler:
+  warmup_duration: 0

configs/dfine/custom/objects365/dfine_hgnetv2_x_obj2custom.yml

@@ -0,0 +1,62 @@
+__include__: [
+  '../../../dataset/custom_detection.yml',
+  '../../../runtime.yml',
+  '../../include/dataloader.yml',
+  '../../include/optimizer.yml',
+  '../../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_x_obj2custom
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B5'
+  return_idx: [1, 2, 3]
+  freeze_stem_only: True
+  freeze_at: 0
+  freeze_norm: True
+  pretrained: False
+
+HybridEncoder:
+  # intra
+  hidden_dim: 384
+  dim_feedforward: 2048
+
+DFINETransformer:
+  feat_channels: [384, 384, 384]
+  reg_scale: 8
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0000025
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+epochs: 36 # Early stop
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 30
+  collate_fn:
+    stop_epoch: 30
+    ema_restart_decay: 0.9999
+    base_size_repeat: 3
+
+ema:
+  warmups: 0
+
+lr_warmup_scheduler:
+  warmup_duration: 0

configs/dfine/dfine_hgnetv2_l_coco.yml

@@ -0,0 +1,44 @@
+__include__: [
+  '../dataset/coco_detection.yml',
+  '../runtime.yml',
+  './include/dataloader.yml',
+  './include/optimizer.yml',
+  './include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_l_coco
+
+
+HGNetv2:
+  name: 'B4'
+  return_idx: [1, 2, 3]
+  freeze_stem_only: True
+  freeze_at: 0
+  freeze_norm: True
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0000125
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+# Increase to search for the optimal ema
+epochs: 80 # 72 + 2n
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 72
+  collate_fn:
+    stop_epoch: 72
+    ema_restart_decay: 0.9999
+    base_size_repeat: 4

configs/dfine/dfine_hgnetv2_m_coco.yml

@@ -0,0 +1,60 @@
+__include__: [
+  '../dataset/coco_detection.yml',
+  '../runtime.yml',
+  './include/dataloader.yml',
+  './include/optimizer.yml',
+  './include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_m_coco
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B2'
+  return_idx: [1, 2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+DFINETransformer:
+  num_layers: 4  # 5 6
+  eval_idx: -1  # -2 -3
+
+HybridEncoder:
+  in_channels: [384, 768, 1536]
+  hidden_dim: 256
+  depth_mult: 0.67
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.00002
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.00002
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.0002
+  betas: [0.9, 0.999]
+  weight_decay: 0.0001
+
+
+# Increase to search for the optimal ema
+epochs: 132 # 120 + 4n
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 120
+  collate_fn:
+    stop_epoch: 120
+    ema_restart_decay: 0.9999
+    base_size_repeat: 6

configs/dfine/dfine_hgnetv2_n_coco.yml

@@ -0,0 +1,82 @@
+__include__: [
+  '../dataset/coco_detection.yml',
+  '../runtime.yml',
+  './include/dataloader.yml',
+  './include/optimizer.yml',
+  './include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_n_coco
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B0'
+  return_idx: [2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+
+HybridEncoder:
+  in_channels: [512, 1024]
+  feat_strides: [16, 32]
+
+  # intra
+  hidden_dim: 128
+  use_encoder_idx: [1]
+  dim_feedforward: 512
+
+  # cross
+  expansion: 0.34
+  depth_mult: 0.5
+
+
+DFINETransformer:
+  feat_channels: [128, 128]
+  feat_strides: [16, 32]
+  hidden_dim: 128
+  dim_feedforward: 512
+  num_levels: 2
+
+  num_layers: 3
+  eval_idx: -1
+
+  num_points: [6, 6]
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0004
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.0004
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.0008
+  betas: [0.9, 0.999]
+  weight_decay: 0.0001
+
+
+# Increase to search for the optimal ema
+epochs: 160 # 148 + 4n
+train_dataloader:
+  total_batch_size: 128
+  dataset:
+    transforms:
+      policy:
+        epoch: 148
+  collate_fn:
+    stop_epoch: 148
+    ema_restart_decay: 0.9999
+    base_size_repeat: ~
+
+val_dataloader:
+  total_batch_size: 256

configs/dfine/dfine_hgnetv2_s_coco.yml

@@ -0,0 +1,61 @@
+__include__: [
+  '../dataset/coco_detection.yml',
+  '../runtime.yml',
+  './include/dataloader.yml',
+  './include/optimizer.yml',
+  './include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_s_coco
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B0'
+  return_idx: [1, 2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+DFINETransformer:
+  num_layers: 3  # 4 5 6
+  eval_idx: -1  # -2 -3 -4
+
+HybridEncoder:
+  in_channels: [256, 512, 1024]
+  hidden_dim: 256
+  depth_mult: 0.34
+  expansion: 0.5
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0001
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.0001
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.0002
+  betas: [0.9, 0.999]
+  weight_decay: 0.0001
+
+
+# Increase to search for the optimal ema
+epochs: 132 # 120 + 4n
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 120
+  collate_fn:
+    stop_epoch: 120
+    ema_restart_decay: 0.9999
+    base_size_repeat: 20

configs/dfine/dfine_hgnetv2_x_coco.yml

@@ -0,0 +1,56 @@
+__include__: [
+  '../dataset/coco_detection.yml',
+  '../runtime.yml',
+  './include/dataloader.yml',
+  './include/optimizer.yml',
+  './include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_x_coco
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B5'
+  return_idx: [1, 2, 3]
+  freeze_stem_only: True
+  freeze_at: 0
+  freeze_norm: True
+
+HybridEncoder:
+  # intra
+  hidden_dim: 384
+  dim_feedforward: 2048
+
+DFINETransformer:
+  feat_channels: [384, 384, 384]
+  reg_scale: 8
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0000025
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+# Increase to search for the optimal ema
+epochs: 80 # 72 + 2n
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 72
+  collate_fn:
+    stop_epoch: 72
+    ema_restart_decay: 0.9998
+    base_size_repeat: 3

configs/dfine/include/dataloader.yml

@@ -0,0 +1,39 @@
+
+train_dataloader:
+  dataset:
+    transforms:
+      ops:
+        - {type: RandomPhotometricDistort, p: 0.5}
+        - {type: RandomZoomOut, fill: 0}
+        - {type: RandomIoUCrop, p: 0.8}
+        - {type: SanitizeBoundingBoxes, min_size: 1}
+        - {type: RandomHorizontalFlip}
+        - {type: Resize, size: [640, 640], }
+        - {type: SanitizeBoundingBoxes, min_size: 1}
+        - {type: ConvertPILImage, dtype: 'float32', scale: True}
+        - {type: ConvertBoxes, fmt: 'cxcywh', normalize: True}
+      policy:
+        name: stop_epoch
+        epoch: 72 # epoch in [71, ~) stop `ops`
+        ops: ['RandomPhotometricDistort', 'RandomZoomOut', 'RandomIoUCrop']
+
+  collate_fn:
+    type: BatchImageCollateFunction
+    base_size: 640
+    base_size_repeat: 3
+    stop_epoch: 72 # epoch in [72, ~) stop `multiscales`
+
+  shuffle: True
+  total_batch_size: 32 # total batch size equals to 32 (4 * 8)
+  num_workers: 4
+
+
+val_dataloader:
+  dataset:
+    transforms:
+      ops:
+        - {type: Resize, size: [640, 640], }
+        - {type: ConvertPILImage, dtype: 'float32', scale: True}
+  shuffle: False
+  total_batch_size: 64
+  num_workers: 4

configs/dfine/include/dfine_hgnetv2.yml

@@ -0,0 +1,82 @@
+task: detection
+
+model: DFINE
+criterion: DFINECriterion
+postprocessor: DFINEPostProcessor
+
+use_focal_loss: True
+eval_spatial_size: [640, 640] # h w
+
+DFINE:
+  backbone: HGNetv2
+  encoder: HybridEncoder
+  decoder: DFINETransformer
+
+HGNetv2:
+  pretrained: True
+  local_model_dir: weight/hgnetv2/
+
+HybridEncoder:
+  in_channels: [512, 1024, 2048]
+  feat_strides: [8, 16, 32]
+
+  # intra
+  hidden_dim: 256
+  use_encoder_idx: [2]
+  num_encoder_layers: 1
+  nhead: 8
+  dim_feedforward: 1024
+  dropout: 0.
+  enc_act: 'gelu'
+
+  # cross
+  expansion: 1.0
+  depth_mult: 1
+  act: 'silu'
+
+
+DFINETransformer:
+  feat_channels: [256, 256, 256]
+  feat_strides: [8, 16, 32]
+  hidden_dim: 256
+  num_levels: 3
+
+  num_layers: 6
+  eval_idx: -1
+  num_queries: 300
+
+  num_denoising: 100
+  label_noise_ratio: 0.5
+  box_noise_scale: 1.0
+
+  # NEW
+  reg_max: 32
+  reg_scale: 4
+
+  # Auxiliary decoder layers dimension scaling
+  # "eg. If num_layers: 6 eval_idx: -4,
+  # then layer 3, 4, 5 are auxiliary decoder layers."
+  layer_scale: 1  # 2
+
+
+  num_points: [3, 6, 3] # [4, 4, 4] [3, 6, 3]
+  cross_attn_method: default # default, discrete
+  query_select_method: default # default, agnostic
+
+
+DFINEPostProcessor:
+  num_top_queries: 300
+
+
+DFINECriterion:
+  weight_dict: {loss_vfl: 1, loss_bbox: 5, loss_giou: 2, loss_fgl: 0.15, loss_ddf: 1.5}
+  losses: ['vfl', 'boxes', 'local']
+  alpha: 0.75
+  gamma: 2.0
+  reg_max: 32
+
+  matcher:
+    type: HungarianMatcher
+    weight_dict: {cost_class: 2, cost_bbox: 5, cost_giou: 2}
+    alpha: 0.25
+    gamma: 2.0

configs/dfine/include/optimizer.yml

@@ -0,0 +1,36 @@
+use_amp: True
+use_ema: True
+ema:
+  type: ModelEMA
+  decay: 0.9999
+  warmups: 1000
+  start: 0
+
+
+epochs: 72
+clip_max_norm: 0.1
+
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm).*$'
+      lr: 0.0000125
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+lr_scheduler:
+  type: MultiStepLR
+  milestones: [500]
+  gamma: 0.1
+
+lr_warmup_scheduler:
+  type: LinearWarmup
+  warmup_duration: 500

configs/dfine/objects365/dfine_hgnetv2_l_obj2coco.yml

@@ -0,0 +1,52 @@
+__include__: [
+  '../../dataset/coco_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_l_obj2coco
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B4'
+  return_idx: [1, 2, 3]
+  freeze_stem_only: True
+  freeze_at: 0
+  freeze_norm: True
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0000125
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+epochs: 36 # Early stop
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 30
+  collate_fn:
+    stop_epoch: 30
+    ema_restart_decay: 0.9999
+    base_size_repeat: 4
+
+ema:
+  warmups: 0
+
+lr_warmup_scheduler:
+  warmup_duration: 0

configs/dfine/objects365/dfine_hgnetv2_l_obj365.yml

@@ -0,0 +1,49 @@
+__include__: [
+  '../../dataset/obj365_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_l_obj365
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B4'
+  return_idx: [1, 2, 3]
+  freeze_stem_only: True
+  freeze_at: 0
+  freeze_norm: True
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0000125
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+#   weight_decay: 0.00005  # Faster convergence (optional)
+
+
+epochs: 24 # Early stop
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 500
+  collate_fn:
+    stop_epoch: 500
+    base_size_repeat: 4
+
+checkpoint_freq: 1
+print_freq: 1000

configs/dfine/objects365/dfine_hgnetv2_m_obj2coco.yml

@@ -0,0 +1,65 @@
+__include__: [
+  '../../dataset/coco_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_m_obj2coco
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B2'
+  return_idx: [1, 2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+DFINETransformer:
+  num_layers: 4  # 5 6
+  eval_idx: -1  # -2 -3
+
+HybridEncoder:
+  in_channels: [384, 768, 1536]
+  hidden_dim: 256
+  depth_mult: 0.67
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.000025
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.000025
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+epochs: 56 # Early stop
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 48
+  collate_fn:
+    stop_epoch: 48
+    ema_restart_decay: 0.9999
+    base_size_repeat: 6
+
+ema:
+  warmups: 0
+
+lr_warmup_scheduler:
+  warmup_duration: 0

configs/dfine/objects365/dfine_hgnetv2_m_obj365.yml

@@ -0,0 +1,62 @@
+__include__: [
+  '../../dataset/obj365_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: .output/dfine_hgnetv2_s_obj365
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B2'
+  return_idx: [1, 2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+DFINETransformer:
+  num_layers: 4  # 5 6
+  eval_idx: -1  # -2 -3
+
+HybridEncoder:
+  in_channels: [384, 768, 1536]
+  hidden_dim: 256
+  depth_mult: 0.67
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.000025
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.000025
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+#   weight_decay: 0.00005  # Faster convergence (optional)
+
+
+epochs: 36 # Early stop
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 500
+  collate_fn:
+    stop_epoch: 500
+    base_size_repeat: 6
+
+checkpoint_freq: 1
+print_freq: 1000

configs/dfine/objects365/dfine_hgnetv2_n_obj2coco.yml

@@ -0,0 +1,88 @@
+__include__: [
+  '../../dataset/coco_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_n_obj2coco
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B0'
+  return_idx: [2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+
+HybridEncoder:
+  in_channels: [512, 1024]
+  feat_strides: [16, 32]
+
+  # intra
+  hidden_dim: 128
+  use_encoder_idx: [1]
+  dim_feedforward: 512
+
+  # cross
+  expansion: 0.34
+  depth_mult: 0.5
+
+
+DFINETransformer:
+  feat_channels: [128, 128]
+  feat_strides: [16, 32]
+  hidden_dim: 128
+  dim_feedforward: 512
+  num_levels: 2
+
+  num_layers: 3
+  eval_idx: -1
+
+  num_points: [6, 6]
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0004
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.0004
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.0008
+  betas: [0.9, 0.999]
+  weight_decay: 0.0001
+
+
+
+epochs: 64 # Early stop
+train_dataloader:
+  total_batch_size: 128
+  dataset:
+    transforms:
+      policy:
+        epoch: 56
+  collate_fn:
+    stop_epoch: 56
+    ema_restart_decay: 0.9999
+    base_size_repeat: ~
+
+ema:
+  warmups: 0
+
+lr_warmup_scheduler:
+  warmup_duration: 0
+
+val_dataloader:
+  total_batch_size: 256

configs/dfine/objects365/dfine_hgnetv2_n_obj365.yml

@@ -0,0 +1,84 @@
+__include__: [
+  '../../dataset/obj365_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_n_obj365
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B0'
+  return_idx: [2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+
+HybridEncoder:
+  in_channels: [512, 1024]
+  feat_strides: [16, 32]
+
+  # intra
+  hidden_dim: 128
+  use_encoder_idx: [1]
+  dim_feedforward: 512
+
+  # cross
+  expansion: 0.34
+  depth_mult: 0.5
+
+
+DFINETransformer:
+  feat_channels: [128, 128]
+  feat_strides: [16, 32]
+  hidden_dim: 128
+  dim_feedforward: 512
+  num_levels: 2
+
+  num_layers: 3
+  eval_idx: -1
+
+  num_points: [6, 6]
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0004
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.0004
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.0008
+  betas: [0.9, 0.999]
+  weight_decay: 0.0001
+
+
+
+epochs: 48 # Early stop
+train_dataloader:
+  total_batch_size: 128
+  dataset:
+    transforms:
+      policy:
+        epoch: 500
+  collate_fn:
+    stop_epoch: 500
+    base_size_repeat: ~
+
+checkpoint_freq: 1
+print_freq: 500
+
+val_dataloader:
+  total_batch_size: 256

configs/dfine/objects365/dfine_hgnetv2_s_obj2coco.yml

@@ -0,0 +1,66 @@
+__include__: [
+  '../../dataset/coco_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_s_obj2coco
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B0'
+  return_idx: [1, 2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+DFINETransformer:
+  num_layers: 3  # 4 5 6
+  eval_idx: -1  # -2 -3 -4
+
+HybridEncoder:
+  in_channels: [256, 512, 1024]
+  hidden_dim: 256
+  depth_mult: 0.34
+  expansion: 0.5
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.000125
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.000125
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+epochs: 64 # Early stop
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 56
+  collate_fn:
+    stop_epoch: 56
+    ema_restart_decay: 0.9999
+    base_size_repeat: 10
+
+ema:
+  warmups: 0
+
+lr_warmup_scheduler:
+  warmup_duration: 0

configs/dfine/objects365/dfine_hgnetv2_s_obj365.yml

@@ -0,0 +1,63 @@
+__include__: [
+  '../../dataset/obj365_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_s_obj365
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B0'
+  return_idx: [1, 2, 3]
+  freeze_at: -1
+  freeze_norm: False
+  use_lab: True
+
+DFINETransformer:
+  num_layers: 3  # 4 5 6
+  eval_idx: -1  # -2 -3 -4
+
+HybridEncoder:
+  in_channels: [256, 512, 1024]
+  hidden_dim: 256
+  depth_mult: 0.34
+  expansion: 0.5
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.000125
+    -
+      params: '^(?=.*backbone)(?=.*norm|bn).*$'
+      lr: 0.000125
+      weight_decay: 0.
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+#   weight_decay: 0.00005  # Faster convergence (optional)
+
+
+epochs: 36 # Early stop
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 500
+  collate_fn:
+    stop_epoch: 500
+    base_size_repeat: 20
+
+checkpoint_freq: 1
+print_freq: 1000

configs/dfine/objects365/dfine_hgnetv2_x_obj2coco.yml

@@ -0,0 +1,61 @@
+__include__: [
+  '../../dataset/coco_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_x_obj2coco
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B5'
+  return_idx: [1, 2, 3]
+  freeze_stem_only: True
+  freeze_at: 0
+  freeze_norm: True
+
+HybridEncoder:
+  # intra
+  hidden_dim: 384
+  dim_feedforward: 2048
+
+DFINETransformer:
+  feat_channels: [384, 384, 384]
+  reg_scale: 8
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0000025
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+
+
+epochs: 36 # Early stop
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 30
+  collate_fn:
+    stop_epoch: 30
+    ema_restart_decay: 0.9999
+    base_size_repeat: 3
+
+ema:
+  warmups: 0
+
+lr_warmup_scheduler:
+  warmup_duration: 0

configs/dfine/objects365/dfine_hgnetv2_x_obj365.yml

@@ -0,0 +1,58 @@
+__include__: [
+  '../../dataset/obj365_detection.yml',
+  '../../runtime.yml',
+  '../include/dataloader.yml',
+  '../include/optimizer.yml',
+  '../include/dfine_hgnetv2.yml',
+]
+
+output_dir: ./output/dfine_hgnetv2_x_obj365
+
+
+DFINE:
+  backbone: HGNetv2
+
+HGNetv2:
+  name: 'B5'
+  return_idx: [1, 2, 3]
+  freeze_stem_only: True
+  freeze_at: 0
+  freeze_norm: True
+
+HybridEncoder:
+  # intra
+  hidden_dim: 384
+  dim_feedforward: 2048
+
+DFINETransformer:
+  feat_channels: [384, 384, 384]
+  reg_scale: 8
+
+optimizer:
+  type: AdamW
+  params:
+    -
+      params: '^(?=.*backbone)(?!.*norm|bn).*$'
+      lr: 0.0000025
+    -
+      params: '^(?=.*(?:encoder|decoder))(?=.*(?:norm|bn)).*$'
+      weight_decay: 0.
+
+  lr: 0.00025
+  betas: [0.9, 0.999]
+  weight_decay: 0.000125
+#   weight_decay: 0.00005  # Faster convergence (optional)
+
+
+epochs: 24 # Early stop
+train_dataloader:
+  dataset:
+    transforms:
+      policy:
+        epoch: 500
+  collate_fn:
+    stop_epoch: 500
+    base_size_repeat: 3
+
+checkpoint_freq: 1
+print_freq: 1000

configs/obj365.yml

@@ -0,0 +1,367 @@
+# Classes
+names:
+  0: Person
+  1: Sneakers
+  2: Chair
+  3: Other Shoes
+  4: Hat
+  5: Car
+  6: Lamp
+  7: Glasses
+  8: Bottle
+  9: Desk
+  10: Cup
+  11: Street Lights
+  12: Cabinet/shelf
+  13: Handbag/Satchel
+  14: Bracelet
+  15: Plate
+  16: Picture/Frame
+  17: Helmet
+  18: Book
+  19: Gloves
+  20: Storage box
+  21: Boat
+  22: Leather Shoes
+  23: Flower
+  24: Bench
+  25: Potted Plant
+  26: Bowl/Basin
+  27: Flag
+  28: Pillow
+  29: Boots
+  30: Vase
+  31: Microphone
+  32: Necklace
+  33: Ring
+  34: SUV
+  35: Wine Glass
+  36: Belt
+  37: Monitor/TV
+  38: Backpack
+  39: Umbrella
+  40: Traffic Light
+  41: Speaker
+  42: Watch
+  43: Tie
+  44: Trash bin Can
+  45: Slippers
+  46: Bicycle
+  47: Stool
+  48: Barrel/bucket
+  49: Van
+  50: Couch
+  51: Sandals
+  52: Basket
+  53: Drum
+  54: Pen/Pencil
+  55: Bus
+  56: Wild Bird
+  57: High Heels
+  58: Motorcycle
+  59: Guitar
+  60: Carpet
+  61: Cell Phone
+  62: Bread
+  63: Camera
+  64: Canned
+  65: Truck
+  66: Traffic cone
+  67: Cymbal
+  68: Lifesaver
+  69: Towel
+  70: Stuffed Toy
+  71: Candle
+  72: Sailboat
+  73: Laptop
+  74: Awning
+  75: Bed
+  76: Faucet
+  77: Tent
+  78: Horse
+  79: Mirror
+  80: Power outlet
+  81: Sink
+  82: Apple
+  83: Air Conditioner
+  84: Knife
+  85: Hockey Stick
+  86: Paddle
+  87: Pickup Truck
+  88: Fork
+  89: Traffic Sign
+  90: Balloon
+  91: Tripod
+  92: Dog
+  93: Spoon
+  94: Clock
+  95: Pot
+  96: Cow
+  97: Cake
+  98: Dinning Table
+  99: Sheep
+  100: Hanger
+  101: Blackboard/Whiteboard
+  102: Napkin
+  103: Other Fish
+  104: Orange/Tangerine
+  105: Toiletry
+  106: Keyboard
+  107: Tomato
+  108: Lantern
+  109: Machinery Vehicle
+  110: Fan
+  111: Green Vegetables
+  112: Banana
+  113: Baseball Glove
+  114: Airplane
+  115: Mouse
+  116: Train
+  117: Pumpkin
+  118: Soccer
+  119: Skiboard
+  120: Luggage
+  121: Nightstand
+  122: Tea pot
+  123: Telephone
+  124: Trolley
+  125: Head Phone
+  126: Sports Car
+  127: Stop Sign
+  128: Dessert
+  129: Scooter
+  130: Stroller
+  131: Crane
+  132: Remote
+  133: Refrigerator
+  134: Oven
+  135: Lemon
+  136: Duck
+  137: Baseball Bat
+  138: Surveillance Camera
+  139: Cat
+  140: Jug
+  141: Broccoli
+  142: Piano
+  143: Pizza
+  144: Elephant
+  145: Skateboard
+  146: Surfboard
+  147: Gun
+  148: Skating and Skiing shoes
+  149: Gas stove
+  150: Donut
+  151: Bow Tie
+  152: Carrot
+  153: Toilet
+  154: Kite
+  155: Strawberry
+  156: Other Balls
+  157: Shovel
+  158: Pepper
+  159: Computer Box
+  160: Toilet Paper
+  161: Cleaning Products
+  162: Chopsticks
+  163: Microwave
+  164: Pigeon
+  165: Baseball
+  166: Cutting/chopping Board
+  167: Coffee Table
+  168: Side Table
+  169: Scissors
+  170: Marker
+  171: Pie
+  172: Ladder
+  173: Snowboard
+  174: Cookies
+  175: Radiator
+  176: Fire Hydrant
+  177: Basketball
+  178: Zebra
+  179: Grape
+  180: Giraffe
+  181: Potato
+  182: Sausage
+  183: Tricycle
+  184: Violin
+  185: Egg
+  186: Fire Extinguisher
+  187: Candy
+  188: Fire Truck
+  189: Billiards
+  190: Converter
+  191: Bathtub
+  192: Wheelchair
+  193: Golf Club
+  194: Briefcase
+  195: Cucumber
+  196: Cigar/Cigarette
+  197: Paint Brush
+  198: Pear
+  199: Heavy Truck
+  200: Hamburger
+  201: Extractor
+  202: Extension Cord
+  203: Tong
+  204: Tennis Racket
+  205: Folder
+  206: American Football
+  207: earphone
+  208: Mask
+  209: Kettle
+  210: Tennis
+  211: Ship
+  212: Swing
+  213: Coffee Machine
+  214: Slide
+  215: Carriage
+  216: Onion
+  217: Green beans
+  218: Projector
+  219: Frisbee
+  220: Washing Machine/Drying Machine
+  221: Chicken
+  222: Printer
+  223: Watermelon
+  224: Saxophone
+  225: Tissue
+  226: Toothbrush
+  227: Ice cream
+  228: Hot-air balloon
+  229: Cello
+  230: French Fries
+  231: Scale
+  232: Trophy
+  233: Cabbage
+  234: Hot dog
+  235: Blender
+  236: Peach
+  237: Rice
+  238: Wallet/Purse
+  239: Volleyball
+  240: Deer
+  241: Goose
+  242: Tape
+  243: Tablet
+  244: Cosmetics
+  245: Trumpet
+  246: Pineapple
+  247: Golf Ball
+  248: Ambulance
+  249: Parking meter
+  250: Mango
+  251: Key
+  252: Hurdle
+  253: Fishing Rod
+  254: Medal
+  255: Flute
+  256: Brush
+  257: Penguin
+  258: Megaphone
+  259: Corn
+  260: Lettuce
+  261: Garlic
+  262: Swan
+  263: Helicopter
+  264: Green Onion
+  265: Sandwich
+  266: Nuts
+  267: Speed Limit Sign
+  268: Induction Cooker
+  269: Broom
+  270: Trombone
+  271: Plum
+  272: Rickshaw
+  273: Goldfish
+  274: Kiwi fruit
+  275: Router/modem
+  276: Poker Card
+  277: Toaster
+  278: Shrimp
+  279: Sushi
+  280: Cheese
+  281: Notepaper
+  282: Cherry
+  283: Pliers
+  284: CD
+  285: Pasta
+  286: Hammer
+  287: Cue
+  288: Avocado
+  289: Hamimelon
+  290: Flask
+  291: Mushroom
+  292: Screwdriver
+  293: Soap
+  294: Recorder
+  295: Bear
+  296: Eggplant
+  297: Board Eraser
+  298: Coconut
+  299: Tape Measure/Ruler
+  300: Pig
+  301: Showerhead
+  302: Globe
+  303: Chips
+  304: Steak
+  305: Crosswalk Sign
+  306: Stapler
+  307: Camel
+  308: Formula 1
+  309: Pomegranate
+  310: Dishwasher
+  311: Crab
+  312: Hoverboard
+  313: Meat ball
+  314: Rice Cooker
+  315: Tuba
+  316: Calculator
+  317: Papaya
+  318: Antelope
+  319: Parrot
+  320: Seal
+  321: Butterfly
+  322: Dumbbell
+  323: Donkey
+  324: Lion
+  325: Urinal
+  326: Dolphin
+  327: Electric Drill
+  328: Hair Dryer
+  329: Egg tart
+  330: Jellyfish
+  331: Treadmill
+  332: Lighter
+  333: Grapefruit
+  334: Game board
+  335: Mop
+  336: Radish
+  337: Baozi
+  338: Target
+  339: French
+  340: Spring Rolls
+  341: Monkey
+  342: Rabbit
+  343: Pencil Case
+  344: Yak
+  345: Red Cabbage
+  346: Binoculars
+  347: Asparagus
+  348: Barbell
+  349: Scallop
+  350: Noddles
+  351: Comb
+  352: Dumpling
+  353: Oyster
+  354: Table Tennis paddle
+  355: Cosmetics Brush/Eyeliner Pencil
+  356: Chainsaw
+  357: Eraser
+  358: Lobster
+  359: Durian
+  360: Okra
+  361: Lipstick
+  362: Cosmetics Mirror
+  363: Curling
+  364: Table Tennis

configs/runtime.yml

@@ -0,0 +1,24 @@
+print_freq: 100
+output_dir: './logs'
+checkpoint_freq: 12
+
+
+sync_bn: True
+find_unused_parameters: False
+
+
+use_amp: False
+scaler:
+  type: GradScaler
+  enabled: True
+
+
+use_ema: False
+ema:
+  type: ModelEMA
+  decay: 0.9999
+  warmups: 1000
+
+use_wandb: False
+project_name: D-FINE # for wandb
+exp_name: baseline # wandb experiment name