利用语义分割算法做指针式仪表的读数识别

如何使用pspnet训练出仪表的指针和表盘
第一步先打标，打标之前先安装labelme，这里我用的labelme版本是3.16.7

pip install labelme==3.16.7

然后在终端桥labelme 打开labelme的界面
如下：

import argparse
import base64
import json
import os
import os.path as osp
import warnings

import numpy as np
import PIL.Image
import yaml
from labelme import utils

'''
我使用的labelme版本是3.16.7，建议使用该版本的labelme，有些版本的labelme会发生错误
此处生成的标签图是8位彩色图，每个像素点的值就是这个像素点所属的种类
'''
if __name__ == '__main__':
    jpgs_path = "datasets/JPEGImages"
    pngs_path = "datasets/SegmentationClass"
    #classes = ["_background_","aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
    classes = ["_background_","pan","zhen"]
    
    count = os.listdir("./datasets/before/") 
    for i in range(0, len(count)):
        path = os.path.join("./datasets/before", count[i])

        if os.path.isfile(path) and path.endswith('json'):
            data = json.load(open(path))
            
            if data['imageData']:
                imageData = data['imageData']
            else:
                imagePath = os.path.join(os.path.dirname(path), data['imagePath'])
                with open(imagePath, 'rb') as f:
                    imageData = f.read()
                    imageData = base64.b64encode(imageData).decode('utf-8')

            img = utils.img_b64_to_arr(imageData)
            label_name_to_value = {'_background_': 0}
            for shape in data['shapes']:
                label_name = shape['label']
                if label_name in label_name_to_value:
                    label_value = label_name_to_value[label_name]
                else:
                    label_value = len(label_name_to_value)
                    label_name_to_value[label_name] = label_value
            
            # label_values must be dense
            label_values, label_names = [], []
            for ln, lv in sorted(label_name_to_value.items(), key=lambda x: x[1]):
                label_values.append(lv)
                label_names.append(ln)
            assert label_values == list(range(len(label_values)))
            
            lbl = utils.shapes_to_label(img.shape, data['shapes'], label_name_to_value)
            
                
            PIL.Image.fromarray(img).save(osp.join(jpgs_path, count[i].split(".")[0]+'.jpg'))

            new = np.zeros([np.shape(img)[0],np.shape(img)[1]])
            for name in label_names:
                index_json = label_names.index(name)
                index_all = classes.index(name)
                new = new + index_all*(np.array(lbl) == index_json)

            utils.lblsave(osp.join(pngs_path, count[i].split(".")[0]+'.png'), new)
            print('Saved ' + count[i].split(".")[0] + '.jpg and ' + count[i].split(".")[0] + '.png')

处理成voc的数据格式以后，第二步我们需要对数据进行分类，分为训练集和验证集。
分类的代码如下

import os
import random 
random.seed(0)
 
segfilepath=r'./datasets/VOC2007/SegmentationClass'
saveBasePath=r"./datasets/VOC2007/ImageSets/Segmentation/"
 
#----------------------------------------------------------------------#
#   想要增加测试集修改trainval_percent
#   修改train_percent用于改变验证集的比例
#----------------------------------------------------------------------#
trainval_percent=1
train_percent=0.9

temp_seg = os.listdir(segfilepath)
total_seg = []
for seg in temp_seg:
    if seg.endswith(".png"):
        total_seg.append(seg)

num=len(total_seg)  
list=range(num)  
tv=int(num*trainval_percent)  
tr=int(tv*train_percent)  
trainval= random.sample(list,tv)  
train=random.sample(trainval,tr)  
 
print("train and val size",tv)
print("traub suze",tr)
ftrainval = open(os.path.join(saveBasePath,'trainval.txt'), 'w')  
ftest = open(os.path.join(saveBasePath,'test.txt'), 'w')  
ftrain = open(os.path.join(saveBasePath,'train.txt'), 'w')  
fval = open(os.path.join(saveBasePath,'val.txt'), 'w')  
 
for i  in list:  
    name=total_seg[i][:-4]+'\n'  
    if i in trainval:  
        ftrainval.write(name)  
        if i in train:  
            ftrain.write(name)  
        else:  
            fval.write(name)  
    else:  
        ftest.write(name)  
  
ftrainval.close()  
ftrain.close()  
fval.close()  
ftest .close()

python train.py

训练过程如图所示，收敛就好