yolov5训练与模型量化

模型训练

python train.py --img 96 --batch 16 --epochs 100 --data ../pigeon_config.yaml --cfg models/yolov5n.yaml --weights runs/train/exp2/weights/best.pt

模型量化

python export.py --img 96 --data ../pigeon_config.yaml --weights runs/train/exp8/weights/best.pt --include tflite --int8

模型转为静态代码

xxd -i best-int8.tflite model_data.cc

统计全部算子

# 加载TFLite模型
interpreter = Interpreter(model_path="model.tflite")
interpreter.allocate_tensors()

# 获取输入张量
input_details = interpreter.get_input_details()
print("Input details:")
print(input_details)

# 获取输出张量
output_details = interpreter.get_output_details()
print("Output details:")
print(output_details)

# 获取所有算子的名称和类型
all_ops = interpreter._get_ops_details()
print("All ops:")
s = set()
for op in all_ops:
    s.append(op['op_name'])
l = sorted(s)
print(l)

降低模型大小

修改 models/yolov5n.yaml 文件

# YOLOv5  by Ultralytics, AGPL-3.0 license

# Parameters
nc: 2  # number of classes
# depth_multiple: 0.33  # model depth multiple
# width_multiple: 0.25  # layer channel multiple
depth_multiple: 0.11  # model depth multiple
width_multiple: 0.08  # layer channel multiple
anchors:
  - [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, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.0 head
head:
  [[-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]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]