diff --git a/cfg/yolov7-mask.yaml b/cfg/yolov7-mask.yaml new file mode 100644 index 0000000..fa5cf75 --- /dev/null +++ b/cfg/yolov7-mask.yaml @@ -0,0 +1,168 @@ +# parameters +nc: 80 # number of classes +depth_multiple: 1.0 # model depth multiple +width_multiple: 1.0 # layer channel multiple +pooler_scale: 0.25 + +# anchors +anchors: + - [12,16, 19,36, 40,28] # P3/8 + - [36,75, 76,55, 72,146] # P4/16 + - [142,110, 192,243, 459,401] # P5/32 + +# yolov7 backbone +backbone: + [[-1, 1, Conv, [32, 3, 1]], # 0 + + [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 + [-1, 1, Conv, [64, 3, 1]], + + [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 + [-1, 1, Conv, [64, 1, 1]], + [-2, 1, Conv, [64, 1, 1]], + [-1, 1, Conv, [64, 3, 1]], + [-1, 1, Conv, [64, 3, 1]], + [-1, 1, Conv, [64, 3, 1]], + [-1, 1, Conv, [64, 3, 1]], + [[-1, -3, -5, -6], 1, Concat, [1]], + [-1, 1, Conv, [256, 1, 1]], # 11 + + [-1, 1, MP, []], + [-1, 1, Conv, [128, 1, 1]], + [-3, 1, Conv, [128, 1, 1]], + [-1, 1, Conv, [128, 3, 2]], + [[-1, -3], 1, Concat, [1]], # 16-P3/8 + [-1, 1, Conv, [128, 1, 1]], + [-2, 1, Conv, [128, 1, 1]], + [-1, 1, Conv, [128, 3, 1]], + [-1, 1, Conv, [128, 3, 1]], + [-1, 1, Conv, [128, 3, 1]], + [-1, 1, Conv, [128, 3, 1]], + [[-1, -3, -5, -6], 1, Concat, [1]], + [-1, 1, Conv, [512, 1, 1]], # 24 + + [-1, 1, MP, []], + [-1, 1, Conv, [256, 1, 1]], + [-3, 1, Conv, [256, 1, 1]], + [-1, 1, Conv, [256, 3, 2]], + [[-1, -3], 1, Concat, [1]], # 29-P4/16 + [-1, 1, Conv, [256, 1, 1]], + [-2, 1, Conv, [256, 1, 1]], + [-1, 1, Conv, [256, 3, 1]], + [-1, 1, Conv, [256, 3, 1]], + [-1, 1, Conv, [256, 3, 1]], + [-1, 1, Conv, [256, 3, 1]], + [[-1, -3, -5, -6], 1, Concat, [1]], + [-1, 1, Conv, [1024, 1, 1]], # 37 + + [-1, 1, MP, []], + [-1, 1, Conv, [512, 1, 1]], + [-3, 1, Conv, [512, 1, 1]], + [-1, 1, Conv, [512, 3, 2]], + [[-1, -3], 1, Concat, [1]], # 42-P5/32 + [-1, 1, Conv, [256, 1, 1]], + [-2, 1, Conv, [256, 1, 1]], + [-1, 1, Conv, [256, 3, 1]], + [-1, 1, Conv, [256, 3, 1]], + [-1, 1, Conv, [256, 3, 1]], + [-1, 1, Conv, [256, 3, 1]], + [[-1, -3, -5, -6], 1, Concat, [1]], + [-1, 1, Conv, [1024, 1, 1]], # 50 + ] + +# yolov7 head +head: + [[-1, 1, SPPCSPC, [512]], # 51 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [37, 1, Conv, [256, 1, 1]], # route backbone P4 + [[-1, -2], 1, Concat, [1]], + + [-1, 1, Conv, [256, 1, 1]], + [-2, 1, Conv, [256, 1, 1]], + [-1, 1, Conv, [128, 3, 1]], + [-1, 1, Conv, [128, 3, 1]], + [-1, 1, Conv, [128, 3, 1]], + [-1, 1, Conv, [128, 3, 1]], + [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], + [-1, 1, Conv, [256, 1, 1]], # 63 + + [-1, 1, Conv, [128, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [24, 1, Conv, [128, 1, 1]], # route backbone P3 + [[-1, -2], 1, Concat, [1]], + + [-1, 1, Conv, [128, 1, 1]], + [-2, 1, Conv, [128, 1, 1]], + [-1, 1, Conv, [64, 3, 1]], + [-1, 1, Conv, [64, 3, 1]], + [-1, 1, Conv, [64, 3, 1]], + [-1, 1, Conv, [64, 3, 1]], + [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], + [-1, 1, Conv, [128, 1, 1]], # 75 + + [-1, 1, MP, []], + [-1, 1, Conv, [128, 1, 1]], + [-3, 1, Conv, [128, 1, 1]], + [-1, 1, Conv, [128, 3, 2]], + [[-1, -3, 63], 1, Concat, [1]], + + [-1, 1, Conv, [256, 1, 1]], + [-2, 1, Conv, [256, 1, 1]], + [-1, 1, Conv, [128, 3, 1]], + [-1, 1, Conv, [128, 3, 1]], + [-1, 1, Conv, [128, 3, 1]], + [-1, 1, Conv, [128, 3, 1]], + [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], + [-1, 1, Conv, [256, 1, 1]], # 88 + + [-1, 1, MP, []], + [-1, 1, Conv, [256, 1, 1]], + [-3, 1, Conv, [256, 1, 1]], + [-1, 1, Conv, [256, 3, 2]], + [[-1, -3, 51], 1, Concat, [1]], + + [-1, 1, Conv, [512, 1, 1]], + [-2, 1, Conv, [512, 1, 1]], + [-1, 1, Conv, [256, 3, 1]], + [-1, 1, Conv, [256, 3, 1]], + [-1, 1, Conv, [256, 3, 1]], + [-1, 1, Conv, [256, 3, 1]], + [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], + [-1, 1, Conv, [512, 1, 1]], # 101 + + [75, 1, Conv, [256, 3, 1] ], + [88, 1, Conv, [512, 3, 1] ], + [101, 1, Conv, [1024, 3, 1]], + + [[102, 103, 104], 1, Merge, [[256, 512, 1024]]], # 105 + + [75, 1, Conv, [64, 1, 1] ], + [-1, 1, nn.Upsample, [None, 2, 'nearest'] ], + [11, 1, Conv, [64, 1, 1] ], # route backbone P2 + [[-1, -2], 1, Concat, [1] ], + [-1, 2, BottleneckCSPB, [64] ], + [-1, 1, Conv, [64, 1, 1] ], # 111 + + [[75, 88, 101], 1, Refine, [128, 3, 1]], + [-1, 1, Conv, [128, 3, 1]], + [-1, 1, nn.Upsample, [None, 2, 'bilinear']], + [-1, 1, Conv, [128, 3, 1]], + [111, 1, Conv, [128, 3, 1]], + [[-1, -2], 1, Shortcut, [1]], + [-1, 1, Conv, [128, 3, 1]], + [-1, 1, nn.Conv2d, [4, 1]], # 119 + + [[75, 63, 51], 1, Refine, [128, 3, 1]], + [-1, 1, Conv, [128, 3, 1]], + [-1, 1, nn.Upsample, [None, 2, 'bilinear']], + [-1, 1, Conv, [128, 3, 1]], + [111, 1, Conv, [128, 3, 1]], + [[-1, -2], 1, Shortcut, [1]], + [-1, 1, Conv, [128, 3, 1]], + [-1, 1, nn.Conv2d, [1, 1]], # 127 + + [[105, 119, 127], 1, MT, [nc, anchors, 980]], # Detect(P3, P4, P5) + ] +