# Ultralytics YOLO 🚀, AGPL-3.0 license
# RT-DETR-ResNet50 object detection model with P3-P5 outputs.

# Parameters
nc: 3
nc_list: {'detection': 1, 'segmentation': 2} # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
  # [depth, width, max_channels]
  l: [1.00, 1.00, 1024]

backbone:
  # [from, repeats, module, args]   640
  - [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0   320
  - [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1   160
  - [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2   80
  - [-1, 1, ResNetLayer, [512, 256, 2, False, 6]] # 3   40
  - [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4   20

head:
  - [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 5
  - [-1, 1, AIFI, [1024, 8]]
  - [-1, 1, STB, [[20,20], 4, 4]]    #6  JW here should add the correct resolution for stb, it is tuple. Second parameter is number of heads. Third is depth.
  - [-1, 1, Conv, [256, 1, 1]] # 7

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 9
  - [[-2, -1], 1, Concat, [1]]
  - [-1, 3, RepC3, [256]] # 11
  - [-1, 1, Conv, [256, 1, 1]] # 12

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [2, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14
  - [[-2, -1], 1, Concat, [1]] # cat backbone P4
  - [-1, 3, RepC3, [256]] # X3 (16), fpn_blocks.1

  - [-1, 1, Conv, [256, 3, 2]] # 17, downsample_convs.0
  - [[-1, 13], 1, Concat, [1]] # cat Y4
  - [-1, 3, RepC3, [256]] # F4 (19), pan_blocks.0

  - [-1, 1, Conv, [256, 3, 2]] # 20, downsample_convs.1
  - [[-1, 8], 1, Concat, [1]] # cat Y5
  - [-1, 3, RepC3, [256]] # F5 (22), pan_blocks.1

  - [[17, 20, 23], 1, MTDETRDecoder, [nc_list]] # Detect(P3, P4, P5)