EAST自用笔记

FCN（全卷及网络）
FCN将CNN最后的全链接层（FC）换成了卷积层，输出为一张已经label好的图

网络结构

分为四个阶段

第一阶段：

全链接层

第二阶段：

layer {
  name: "upscore"
  type: "Deconvolution"
  bottom: "score_fr"
  top: "upscore"
  param {
    lr_mult: 0
  }
  convolution_param {
    num_output: 21
    bias_term: false
    kernel_size: 64
    stride: 32
  }
}
layer {
  name: "score"
  type: "Crop"
  bottom: "upscore"
  bottom: "data"
  top: "score"
  crop_param {
    axis: 2
    offset: 19
  }
}

第三阶段：

layer {
  name: "upscore16"
  type: "Deconvolution"
  bottom: "fuse_pool4"
  top: "upscore16"
  param {
    lr_mult: 0
  }
  convolution_param {
    num_output: 21
    bias_term: false
    kernel_size: 32
    stride: 16
  }
}
layer {
  name: "score"
  type: "Crop"
  bottom: "upscore16"
  bottom: "data"
  top: "score"
  crop_param {
    axis: 2
    offset: 27
  }
}

第四阶段：

layer {
  name: "upscore8"
  type: "Deconvolution"
  bottom: "fuse_pool3"
  top: "upscore8"
  param {
    lr_mult: 0
  }
  convolution_param {
    num_output: 21
    bias_term: false
    kernel_size: 16
    stride: 8
  }
}
layer {
  name: "score"
  type: "Crop"
  bottom: "upscore8"
  bottom: "data"
  top: "score"
  crop_param {
    axis: 2
    offset: 31
  }
}

NMS（非极大值抑制）

构建一个边框例子

import numpy as np
import matplotlib.pyplot as plt

boxes=np.array([[100,100,210,210,0.7],
        [250,250,420,420,0.8],
        [230,230,320,330,0.9],
        [100,100,210,210,0.7],
        [230,240,325,330,0.8],
        [220,230,315,340,0.9]]) 

def plot_bbox(dets, c='k'):
    
    x1 = dets[:,0]
    y1 = dets[:,1]
    x2 = dets[:,2]
    y2 = dets[:,3]

    plt.plot([x1,x2], [y1,y1], c)
    plt.plot([x1,x1], [y1,y2], c)
    plt.plot([x1,x2], [y2,y2], c)
    plt.plot([x2,x2], [y1,y2], c)

plt.title("Initial border")    
plot_bbox(boxes,'k')

def py_cpu_nms(dets, thresh):
    
    x1 = dets[:,0]
    y1 = dets[:,1]
    x2 = dets[:,2]
    y2 = dets[:,3]
    
    areas = (y2-y1+1) * (x2-x1+1)       # 求像素点的面积所以加一
    scores = dets[:,4]
    keep = []
    
    index = scores.argsort()[::-1]
    
    while index.size >0:

        i = index[0]
        keep.append(i)
        
        x11 = np.maximum(x1[i], x1[index[1:]])    # 计算窗口i与其他所以窗口的交叠部分的面积 
        y11 = np.maximum(y1[i], y1[index[1:]])
        x22 = np.minimum(x2[i], x2[index[1:]])
        y22 = np.minimum(y2[i], y2[index[1:]])
        
        w = np.maximum(0, x22-x11+1)
        h = np.maximum(0, y22-y11+1)
       
        overlaps = w*h
        
        ious = overlaps / (areas[i]+areas[index[1:]] - overlaps)
        
        idx = np.where(ious<=thresh)[0]
        
        index = index[idx+1]
        
    return keep

keep = py_cpu_nms(boxes, thresh=0.6)
plt.title("After nms")
plot_bbox(boxes[keep], 'r')