Merge pull request #4 from aash1999/cbam-imp

adding hyp and model files as mentioned in paper

data/hyps/cbam.hyp.yaml

@@ -0,0 +1,34 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+# Hyperparameters for low-augmentation COCO training from scratch
+# python train.py --batch 64 --cfg yolov5n6.yaml --weights '' --data coco.yaml --img 640 --epochs 300 --linear
+# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
+
+lr0: 0.001  # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.01  # final OneCycleLR learning rate (lr0 * lrf)
+momentum: 0.937  # SGD momentum/Adam beta1
+weight_decay: 0.0005  # optimizer weight decay 5e-4
+warmup_epochs: 3.0  # warmup epochs (fractions ok)
+warmup_momentum: 0.8  # warmup initial momentum
+warmup_bias_lr: 0.1  # warmup initial bias lr
+box: 0.05  # box loss gain
+cls: 0.25  # cls loss gain
+cls_pw: 1.0  # cls BCELoss positive_weight
+obj: 0.5  # obj loss gain (scale with pixels)
+obj_pw: 1.0  # obj BCELoss positive_weight
+iou_t: 0.20  # IoU training threshold
+anchor_t: 4.0  # anchor-multiple threshold
+# anchors: 3  # anchors per output layer (0 to ignore)
+fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
+hsv_h: 0.4  # image HSV-Hue augmentation (fraction)
+hsv_s: 0.3  # image HSV-Saturation augmentation (fraction)
+hsv_v: 0.5  # image HSV-Value augmentation (fraction)
+degrees: 0.2  # image rotation (+/- deg)
+translate: 0.1  # image translation (+/- fraction)
+scale: 0.4  # image scale (+/- gain)
+shear: 0.0  # image shear (+/- deg)
+perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
+flipud: 0.0  # image flip up-down (probability)
+fliplr: 0.5  # image flip left-right (probability)
+mosaic: 1.0  # image mosaic (probability)s
+mixup: 0.2  # image mixup (probability)
+copy_paste: 0.1  # segment copy-paste (probability)

models/yolov5s-cbam-involution.yaml

@@ -0,0 +1,60 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 10  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [2.9434,4.0435, 3.8626,8.5592, 6.8534, 5.9391]
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 3, CBAMBottleneck, [1024, 3]],
+   [-1, 1, SPPF, [1024, 5]],  # 10
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Involution, [1024, 1, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 2], 1, Concat, [1]],
+   [-1, 3, C3, [256, False]], # 23 160*160  p2 head
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 19], 1, Concat, [1]],
+   [-1, 3, C3, [512, False]],  # 26  80*80 p3 head
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 15], 1, Concat, [1]],
+   [-1, 3, C3, [256, False]], # 29 40*40 p4 head
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 11], 1, Concat, [1]],
+   [-1, 3, C3, [1024, False]],  # 32 20*20 p5 head
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P2, P3, P4, P5)
+  ]