caffe人脸遮挡回归分数

目录

数据准备

输入为截取出来的人脸，分数为0-1浮点型小数，只能用hdf5准备数据集
（数据不均衡先做数据扩充，平衡数据后）
caffe人脸遮挡回归分数
masstohdf5.py ：一个hdf5文件太大，我划分为两个，视数据集大小而定，一个hdf5文件最大不能超过2G，参数是保存所有人脸路径的txt文件，这里是3通道彩色图像

#!/usr/bin/env python
# coding=utf-8
import os
from PIL import Image
import sys
import numpy as np
import h5py

IMAGE_SIZE = (112, 112)

filename = sys.argv[1]
setname, ext = filename.split('.')

with open(filename, 'r') as f:
    lines = f.readlines()

# anno = list()
# anno = sorted(lines, key= lambda x: float(x.split()[1]), reverse=True)
# for i in anno:
#     print(i)


np.random.shuffle(lines)

label_path = 'label_{}x{}'.format(IMAGE_SIZE[0], IMAGE_SIZE[1])
if not os.path.exists(label_path):
    os.makedirs(label_path)

for seg in range(2):#int(len(lines)/1000)):
    if seg==0:
       lines_seg =lines[:int(len(lines)/2)]#[1000*seg:1000*seg+1000-1]
    else:
       lines_seg = lines[int(len(lines)/2):]
    sample_size = len(lines_seg)
    imgs = np.zeros((sample_size, 3,)+ IMAGE_SIZE, dtype=np.float32)
    scores = np.zeros(sample_size, dtype=np.float32)
    h5_filename = '{}/{}_{}.h5'.format(label_path, setname, seg)
    with h5py.File(h5_filename, 'a') as h:
        for i, line in enumerate(lines_seg):
            image_name, score = line[:-1].split()
            img = Image.open(os.path.join('data',image_name))
            img = img.resize(IMAGE_SIZE, Image.BILINEAR)
            img = np.array(img, dtype=np.float32) # img:(h,w,3) RGB
            img = img[:, :, ::-1] # img: (h,w,3) BGR
            img -= np.array((104, 117, 123)) #  BGR
            img = img.transpose((2, 0, 1)) # img:(3,h,w)
            img = img.reshape((1, )+img.shape)

            imgs[i] = img
            scores[i] = float(score)
            if (i+1) % 100 == 0:
                print('processed {} images!'.format(i+1))
        h.create_dataset('data', data=imgs)
        h.create_dataset('score', data=scores)


    with open('{}/{}_h5.txt'.format(label_path, setname), 'a+') as f:
        f.write(h5_filename)
        f.write('\n')

网络结构

solver.prototxt

net: "./regress_train.prototxt"
test_iter: 100    #len(val_dataset)/batch_size
test_interval: 230
base_lr: 0.01
lr_policy: "step"
gamma: 0.1
stepsize: 5000
display: 50
max_iter: 21000   #len(train_dataset)/batch_size*epoch_size
momentum: 0.85    
weight_decay: 0.0005
snapshot: 2000
snapshot_prefix: "./regress_112_result/occ"
solver_mode: GPU
type: "Nesterov"

train.prototxt

name: "Regression"
layer {
  name: "data"
  type: "HDF5Data"
  top: "data"
  top: "score"
  include {
    phase: TRAIN
  }
  hdf5_data_param {
    source: "./label_112x112/occ_train_h5.txt"
    batch_size: 128
  } 
}
layer {
  name: "data"
  type: "HDF5Data"
  top: "data"
  top: "score"
  include {
    phase: TEST
  }
  hdf5_data_param {
    source: "./label_112x112/occ_val_h5.txt"
    batch_size: 128
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  convolution_param {
    num_output: 96
    kernel_size: 5
    stride: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  convolution_param {
    num_output: 96
    pad: 2
    kernel_size: 3
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "pool2"
  top: "conv3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "pool3"
  type: "Pooling"
  bottom: "conv3"
  top: "pool3"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "fc4"
  type: "InnerProduct"
  bottom: "pool3"
  top: "fc4"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  inner_product_param {
    num_output: 192
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu4"
  type: "ReLU"
  bottom: "fc4"
  top: "fc4"
}
layer {
  name: "drop4"
  type: "Dropout"
  bottom: "fc4"
  top: "fc4"
  dropout_param {
    dropout_ratio: 0.35
  }
}
layer {
  name: "fc5"
  type: "InnerProduct"
  bottom: "fc4"
  top: "fc5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  inner_product_param {
    num_output: 1
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "sigmoid5"
  type: "Sigmoid"
  bottom: "fc5"
  top: "pred"
}
layer {
  name: "loss"
  type: "EuclideanLoss"
  bottom: "pred"
  bottom: "score"
  top: "loss"
}

deploy.prototxt

name: "Regression"
input: "data"
input_shape { 
  dim: 1
  dim: 3
  dim: 112
  dim: 112
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  convolution_param {
    num_output: 96
    kernel_size: 5
    stride: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  convolution_param {
    num_output: 96
    pad: 2
    kernel_size: 3
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "pool2"
  top: "conv3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "pool3"
  type: "Pooling"
  bottom: "conv3"
  top: "pool3"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "fc4"
  type: "InnerProduct"
  bottom: "pool3"
  top: "fc4"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  inner_product_param {
    num_output: 192
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu4"
  type: "ReLU"
  bottom: "fc4"
  top: "fc4"
}
layer {
  name: "drop4"
  type: "Dropout"
  bottom: "fc4"
  top: "fc4"
  dropout_param {
    dropout_ratio: 0.35
  }
}
layer {
  name: "fc5"
  type: "InnerProduct"
  bottom: "fc4"
  top: "fc5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  inner_product_param {
    num_output: 1
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "sigmoid5"
  type: "Sigmoid"
  bottom: "fc5"
  top: "pred"
}

训练

python caffe_root/build/tools/caffe train-solver solver.prototxt

引用

相关文章：

猜你喜欢
相关资源
相似解决方案
热门标签
Java Python linux javascript Mysql C# Docker 算法 前端 SpringBoot Redis Vue spring 设计模式 .net core .net kubernetes c++ 数据库 数据结构 大数据 js 机器学习 微服务 Android Go 程序员 面试 JVM ASP.net core 云原生 人工智能 后端 PHP git CSS golang k8s Nginx Django mybatis 深度学习 多线程 React 架构 devops 爬虫 云计算 Spring Boot LeetCode