YOLOv3使用笔记——曲线可视化

1.输出重定向

做训练的时候输出重定向得到训练日志文件

./darknet detector train cfg/voc.data cfg/yolov3-voc.cfg darknet53.conv.74 -gpus 0,1 2>1 | tee train_yolov3.log

2.解析日志文件

extract_log.py

    # coding=utf-8
    # 该文件用来提取训练log，去除不可解析的log后使log文件格式化，生成新的log文件供可视化工具绘图
    import inspect
    import os
    import random
    import sys
    def extract_log(log_file,new_log_file,key_word):
        with open(log_file, 'r') as f:
          with open(new_log_file, 'w') as train_log:   
      #f = open(log_file)
        #train_log = open(new_log_file, 'w')
            for line in f:
        # 去除多gpu的同步log
              if 'Syncing' in line:
                continue
        # 去除除零错误的log
              if 'nan' in line:
                continue
              if key_word in line:
                train_log.write(line)
        f.close()
        train_log.close()
     
    extract_log('train_yolov3.log','train_log_loss.txt','images')
    extract_log('train_yolov3.log','train_log_iou.txt','IOU')

解析loss行和iou行得到两个txt文件

 

3.loss曲线可视化

train_loss_visualization.py

根据train_log_loss.txt行数修改lines行

 

   import pandas as pd
    import numpy as np
    import matplotlib.pyplot as plt
    #%matplotlib inline
     
    #lines =9873
    lines=25100
    result = pd.read_csv('train_log_loss.txt', skiprows=[x for x in range(lines)] ,error_bad_lines=False, names=['loss', 'avg', 'rate', 'seconds', 'images'])
    result.head()
     
    result['loss']=result['loss'].str.split(' ').str.get(1)
    result['avg']=result['avg'].str.split(' ').str.get(1)
    result['rate']=result['rate'].str.split(' ').str.get(1)
    result['seconds']=result['seconds'].str.split(' ').str.get(1)
    result['images']=result['images'].str.split(' ').str.get(1)
    result.head()
    result.tail()
     
    #print(result.head())
    # print(result.tail())import pandas as pd
    import numpy as np
    import matplotlib.pyplot as plt
    #%matplotlib inline
     
    lines =9873
    result = pd.read_csv('train_log_loss.txt', skiprows=[x for x in range(lines) if ((x<1000))] ,error_bad_lines=False, names=['loss', 'avg', 'rate', 'seconds', 'images'])
    result.head()
     
    result['loss']=result['loss'].str.split(' ').str.get(1)
    result['avg']=result['avg'].str.split(' ').str.get(1)
    result['rate']=result['rate'].str.split(' ').str.get(1)
    result['seconds']=result['seconds'].str.split(' ').str.get(1)
    result['images']=result['images'].str.split(' ').str.get(1)
    result.head()
    result.tail()
     
    #print(result.head())
    # print(result.tail())
    # print(result.dtypes)
     
    print(result['loss'])
    print(result['avg'])
    print(result['rate'])
    print(result['seconds'])
    print(result['images'])
     
    result['loss']=pd.to_numeric(result['loss'])
    result['avg']=pd.to_numeric(result['avg'])
    result['rate']=pd.to_numeric(result['rate'])
    result['seconds']=pd.to_numeric(result['seconds'])
    result['images']=pd.to_numeric(result['images'])
    result.dtypes
     
     
    fig = plt.figure()
    ax = fig.add_subplot(1, 1, 1)
    ax.plot(result['avg'].values,label='avg_loss')
    #ax.plot(result['loss'].values,label='loss')
    ax.legend(loc='best')
    ax.set_title('The loss curves')
    ax.set_xlabel('batches')
    fig.savefig('avg_loss')
    #fig.savefig('loss')
    # print(result.dtypes)
     
    print(result['loss'])
    print(result['avg'])
    print(result['rate'])
    print(result['seconds'])
    print(result['images'])
     
    result['loss']=pd.to_numeric(result['loss'])
    result['avg']=pd.to_numeric(result['avg'])
    result['rate']=pd.to_numeric(result['rate'])
    result['seconds']=pd.to_numeric(result['seconds'])
    result['images']=pd.to_numeric(result['images'])
    result.dtypes
     
     
    fig = plt.figure()
    ax = fig.add_subplot(1, 1, 1)
    ax.plot(result['avg'].values,label='avg_loss')
    #ax.plot(result['loss'].values,label='loss')
    ax.legend(loc='best')
    ax.set_title('The loss curves')
    ax.set_xlabel('batches')
    fig.savefig('avg_loss')
    #fig.savefig('loss')

4.iou曲线可视化

train_iou_visualization.py

根据train_log_iou.txt行数修改一下lines行，这个数值比较大。

    import pandas as pd
    import numpy as np
    import matplotlib.pyplot as plt
    #%matplotlib inline
     
    lines =1994726
    result = pd.read_csv('train_log_iou.txt', skiprows=[x for x in range(lines) if (x%39!=0|(x<1000))] ,error_bad_lines=False, names=['Region Avg IOU', 'Class', 'Obj', 'No Obj', 'Avg Recall','count'])
    result.head()
     
    result['Region Avg IOU']=result['Region Avg IOU'].str.split(': ').str.get(1)
    result['Class']=result['Class'].str.split(': ').str.get(1)
    result['Obj']=result['Obj'].str.split(': ').str.get(1)
    result['No Obj']=result['No Obj'].str.split(': ').str.get(1)
    result['Avg Recall']=result['Avg Recall'].str.split(': ').str.get(1)
    result['count']=result['count'].str.split(': ').str.get(1)
    result.head()
    result.tail()
     
    #print(result.head())
    # print(result.tail())
    # print(result.dtypes)
    print(result['Region Avg IOU'])
     
    result['Region Avg IOU']=pd.to_numeric(result['Region Avg IOU'])
    result['Class']=pd.to_numeric(result['Class'])
    result['Obj']=pd.to_numeric(result['Obj'])
    result['No Obj']=pd.to_numeric(result['No Obj'])
    result['Avg Recall']=pd.to_numeric(result['Avg Recall'])
    result['count']=pd.to_numeric(result['count'])
    result.dtypes
     
    fig = plt.figure()
    ax = fig.add_subplot(1, 1, 1)
    ax.plot(result['Region Avg IOU'].values,label='Region Avg IOU')
    #ax.plot(result['Class'].values,label='Class')
    #ax.plot(result['Obj'].values,label='Obj')
    #ax.plot(result['No Obj'].values,label='No Obj')
    #ax.plot(result['Avg Recall'].values,label='Avg Recall')
    #ax.plot(result['count'].values,label='count')
    ax.legend(loc='best')
    #ax.set_title('The Region Avg IOU curves')
    ax.set_title('The Region Avg IOU curves')
    ax.set_xlabel('batches')
    #fig.savefig('Avg IOU')
    fig.savefig('Region Avg IOU')

原文链接：https://blog.csdn.net/cgt19910923/article/details/80783614