Add files via upload

10911831_3.py

@@ -0,0 +1,49 @@
+# -*- coding: UTF-8 -*-
+import wave
+import numpy as np
+import matplotlib.pyplot as plt
+
+# 打开wav文件 ，open返回一个的是一个Wave_read类的实例，通过调用它的方法读取WAV文件的格式和数据。
+f = wave.open(r"D:\CloudMusic\ss/000005.wav","rb")
+# 读取格式信息
+# 一次性返回所有的WAV文件的格式信息，它返回的是一个组元(tuple)：声道数, 量化位数（byte单位）, 采
+# 样频率, 采样点数, 压缩类型, 压缩类型的描述。wave模块只支持非压缩的数据，因此可以忽略最后两个信息
+params = f.getparams()
+[nchannels, sampwidth, framerate, nframes] = params[:4]
+# 读取波形数据
+# 读取声音数据，传递一个参数指定需要读取的长度（以取样点为单位）
+str_data  = f.readframes(nframes)
+f.close()
+# 将波形数据转换成数组
+# 需要根据声道数和量化单位，将读取的二进制数据转换为一个可以计算的数组
+wave_data = np.fromstring(str_data,dtype = np.short)
+# 将wave_data数组改为2列，行数自动匹配。在修改shape的属性时，需使得数组的总长度不变。
+wave_data.shape = -1,2
+# 转置数据
+wave_data = wave_data.T
+# 通过取样点数和取样频率计算出每个取样的时间。
+time=np.arange(0,nframes/2)/framerate
+# print(params)
+plt.figure(1)
+# time 也是一个数组，与wave_data[0]或wave_data[1]配对形成系列点坐标
+plt.subplot(211)
+plt.plot(time,wave_data[0])
+plt.xlabel("time/s")
+plt.title('Wave')
+
+
+N=44100
+start=0
+# 开始采样位置
+df = framerate/(N-1)
+# 分辨率
+freq = [df*n for n in range(0,N)]
+# N个元素
+wave_data2=wave_data[0][start:start+N]
+c=np.fft.fft(wave_data2)*2/N
+# 常规显示采样频率一半的频谱
+plt.subplot(212)
+plt.plot(freq[:round(len(freq)/2)],abs(c[:round(len(c)/2)]),'r')
+plt.title('Freq')
+plt.xlabel("Freq/Hz")
+plt.show()

AVOC.py

@@ -0,0 +1,149 @@
+from lxml import etree
+
+
+class GEN_Annotations:
+    def __init__(self, filename, imgpath):
+        self.root = etree.Element("annotation")
+
+        child1 = etree.SubElement(self.root, "folder")
+        child1.text = "ss"
+
+        child2 = etree.SubElement(self.root, "filename")
+        child2.text = filename
+
+        child3 = etree.SubElement(self.root,"path")
+        child3.text = imgpath
+
+        child4 = etree.SubElement(self.root, "source")
+
+        # child4 = etree.SubElement(child3, "annotation")
+        # child4.text = "PASCAL VOC2007"
+        child5 = etree.SubElement(child4, "database")
+        child5.text = "Unknown"
+        #
+        # child6 = etree.SubElement(child3, "image")
+        # child6.text = "flickr"
+        # child7 = etree.SubElement(child3, "flickrid")
+        # child7.text = "35435"
+
+    def set_size(self, witdh, height, channel):
+        size = etree.SubElement(self.root, "size")
+        widthn = etree.SubElement(size, "width")
+        widthn.text = str(witdh)
+        heightn = etree.SubElement(size, "height")
+        heightn.text = str(height)
+        channeln = etree.SubElement(size, "depth")
+        channeln.text = str(channel)
+
+    def set_segmented(self,seg=0):
+        segmented = etree.SubElement(self.root,"segmented")
+        segmented.text = str(seg)
+
+
+    def savefile(self, filename):
+        tree = etree.ElementTree(self.root)
+        tree.write(filename, pretty_print=True, xml_declaration=False, encoding='utf-8')
+
+    def add_pic_attr(self, label, xmin, ymin, xmax, ymax):
+        object = etree.SubElement(self.root, "object")
+
+        namen = etree.SubElement(object, "name")
+        namen.text = label
+
+        pose = etree.SubElement(object,"pose")
+        pose.text = "Unspecified"
+
+        truncated = etree.SubElement(object,"truncated")
+        truncated.text = "0"
+
+        difficult = etree.SubElement(object,"difficult")
+        difficult.text = "0"
+
+        bndbox = etree.SubElement(object, "bndbox")
+        xminn = etree.SubElement(bndbox, "xmin")
+        xminn.text = str(xmin)
+        yminn = etree.SubElement(bndbox, "ymin")
+        yminn.text = str(ymin)
+        xmaxn = etree.SubElement(bndbox, "xmax")
+        xmaxn.text = str(xmax)
+        ymaxn = etree.SubElement(bndbox, "ymax")
+        ymaxn.text = str(ymax)
+
+
+import os
+import cv2
+
+
+def getFileList(dir, Filelist, ext=None):
+    """
+    获取文件夹及其子文件夹中文件列表
+    输入 dir：文件夹根目录
+    输入 ext: 扩展名
+    返回： 文件路径列表
+    """
+    newDir = dir
+    if os.path.isfile(dir):
+        if ext is None:
+            Filelist.append(dir)
+        else:
+            if ext in dir[-3:]:
+                Filelist.append(dir)
+
+    elif os.path.isdir(dir):
+        for s in os.listdir(dir):
+            newDir = os.path.join(dir, s)
+            getFileList(newDir, Filelist, ext)
+
+    return Filelist
+
+
+# org_img_folder = './org'
+
+# 检索文件
+# imglist = getFileList(org_img_folder, [], 'jpg')
+# print('本次执行检索到 ' + str(len(imglist)) + ' 张图像\n')
+
+# for imgpath in imglist:
+#     imgname = os.path.splitext(os.path.basename(imgpath))[0]
+#     img = cv2.imread(imgpath, cv2.IMREAD_COLOR)
+    # 对每幅图像执行相关操作
+
+if __name__ == '__main__':
+    org_img_folder = r'.\标注文件\mfcc\ss'
+
+    # 检索文件
+    imglist = getFileList(org_img_folder, [], 'png')
+    print('本次执行检索到 ' + str(len(imglist)) + ' 张图像\n')
+    #
+    # filename = imglist[0]
+    # name = filename.split('\\')
+    # # print(name)
+    # anno = GEN_Annotations(name[4],filename)
+    # anno.set_size(800, 550, 3)
+    # anno.set_segmented()
+    # for i in range(1):
+    #     xmin = i + 1
+    #     ymin = i + 1
+    #     xmax = i + 799
+    #     ymax = i + 549
+    #     anno.add_pic_attr("Snoring", xmin, ymin, xmax, ymax)
+    # filename_saved = filename.split('.')
+    # # print(filename_saved)
+    # anno.savefile('.'+filename_saved[1]+".xml")
+
+    for imagepath in imglist:
+        filename = imagepath
+        name = filename.split('\\')
+        # print(name)
+        anno = GEN_Annotations(name[4], filename)
+        anno.set_size(800, 550, 3)
+        for i in range(1):
+            xmin = i + 99
+            ymin = i + 64
+            xmax = i + 724
+            ymax = i + 493
+            anno.add_pic_attr("Snoring", xmin, ymin, xmax, ymax)
+        # filename_saved = filename.split('.')
+        filename_saved=name[4].split('.')
+        path=r'E:\语音处理\频谱\VOC\mfcc/ss/'
+        anno.savefile(path + filename_saved[0] + ".xml")

autoVOC-new.py

@@ -0,0 +1,153 @@
+from lxml import etree
+
+
+class GEN_Annotations:
+    def __init__(self, filename):
+        self.root = etree.Element("annotation")
+
+        child1 = etree.SubElement(self.root, "folder")
+        child1.text = "folder"
+
+        child2 = etree.SubElement(self.root, "filename")
+        child2.text = filename
+
+        # child3 = etree.SubElement(self.root,"path")
+        # child3.text = imgpath
+
+        child4 = etree.SubElement(self.root, "source")
+
+        # child4 = etree.SubElement(child3, "annotation")
+        # child4.text = "PASCAL VOC2007"
+        child5 = etree.SubElement(child4, "database")
+        child5.text = "Unknown"
+        #
+        # child6 = etree.SubElement(child3, "image")
+        # child6.text = "flickr"
+        # child7 = etree.SubElement(child3, "flickrid")
+        # child7.text = "35435"
+
+    def set_size(self, witdh, height, channel):
+        size = etree.SubElement(self.root, "size")
+        widthn = etree.SubElement(size, "width")
+        widthn.text = str(witdh)
+        heightn = etree.SubElement(size, "height")
+        heightn.text = str(height)
+        channeln = etree.SubElement(size, "depth")
+        channeln.text = str(channel)
+
+    def set_segmented(self,seg=0):
+        segmented = etree.SubElement(self.root,"segmented")
+        segmented.text = str(seg)
+
+
+    def savefile(self, filename):
+        tree = etree.ElementTree(self.root)
+        tree.write(filename, pretty_print=True, xml_declaration=False, encoding='utf-8')
+
+    def add_pic_attr(self, label, xmin, ymin, xmax, ymax):
+        object = etree.SubElement(self.root, "object")
+
+        namen = etree.SubElement(object, "name")
+        namen.text = label
+
+        pose = etree.SubElement(object,"pose")
+        pose.text = "Unspecified"
+
+        truncated = etree.SubElement(object,"truncated")
+        truncated.text = "0"
+
+        difficult = etree.SubElement(object,"difficult")
+        difficult.text = "0"
+
+        bndbox = etree.SubElement(object, "bndbox")
+        xminn = etree.SubElement(bndbox, "xmin")
+        xminn.text = str(xmin)
+        yminn = etree.SubElement(bndbox, "ymin")
+        yminn.text = str(ymin)
+        xmaxn = etree.SubElement(bndbox, "xmax")
+        xmaxn.text = str(xmax)
+        ymaxn = etree.SubElement(bndbox, "ymax")
+        ymaxn.text = str(ymax)
+
+
+import os
+import cv2
+
+
+def getFileList(dir, Filelist, ext=None):
+    """
+    获取文件夹及其子文件夹中文件列表
+    输入 dir：文件夹根目录
+    输入 ext: 扩展名
+    返回： 文件路径列表
+    """
+    newDir = dir
+    if os.path.isfile(dir):
+        if ext is None:
+            Filelist.append(dir)
+        else:
+            if ext in dir[-3:]:
+                Filelist.append(dir)
+
+    elif os.path.isdir(dir):
+        for s in os.listdir(dir):
+            newDir = os.path.join(dir, s)
+            getFileList(newDir, Filelist, ext)
+
+    return Filelist
+
+
+# org_img_folder = './org'
+
+# 检索文件
+# imglist = getFileList(org_img_folder, [], 'jpg')
+# print('本次执行检索到 ' + str(len(imglist)) + ' 张图像\n')
+
+# for imgpath in imglist:
+#     imgname = os.path.splitext(os.path.basename(imgpath))[0]
+#     img = cv2.imread(imgpath, cv2.IMREAD_COLOR)
+    # 对每幅图像执行相关操作
+
+if __name__ == '__main__':
+    org_img_folder = r'.\标注文件\wave\ss'
+
+    # 检索文件
+    imglist = getFileList(org_img_folder, [], 'jpg')
+    print('本次执行检索到 ' + str(len(imglist)) + ' 张图像\n')
+    #
+    # filename = imglist[0]
+    # name = filename.split('\\')
+    # # print(name)
+    # anno = GEN_Annotations(name[4],filename)
+    # anno.set_size(800, 550, 3)
+    # anno.set_segmented()
+    # for i in range(1):
+    #     xmin = i + 1
+    #     ymin = i + 1
+    #     xmax = i + 799
+    #     ymax = i + 549
+    #     anno.add_pic_attr("Snoring", xmin, ymin, xmax, ymax)
+    # filename_saved = filename.split('.')
+    # # print(filename_saved)
+    # anno.savefile('.'+filename_saved[1]+".xml")
+
+    for imagepath in imglist:
+        filename = imagepath
+        name = filename.split('\\')
+        # print(name)
+        anno = GEN_Annotations(name[4])
+        anno.set_size(800, 550, 3)
+        anno.set_segmented()
+        for i in range(1):
+            xmin = 105
+            ymin = 72
+            xmax = 718
+            ymax = 486
+            # xmin = 99
+            # ymin = 64
+            # xmax = 724
+            # ymax = 493
+            anno.add_pic_attr("Snoring", xmin, ymin, xmax, ymax)
+        filename_saved = name[4].split('.')
+        path = r'E:\语音处理\频谱\anno\wave/'
+        anno.savefile(path + filename_saved[0] + ".xml")