pytorch Dataset,DataLoader產(chǎn)生自定義的訓(xùn)練數(shù)據(jù)案例

class CustomDataset(data.Dataset):#需要繼承data.Dataset
 def __init__(self):
  # TODO
  # 1. Initialize file path or list of file names.
  pass
 def __getitem__(self, index):
  # TODO
  # 1. Read one data from file (e.g. using numpy.fromfile, PIL.Image.open).
  # 2. Preprocess the data (e.g. torchvision.Transform).
  # 3. Return a data pair (e.g. image and label).
  #這里需要注意的是，第一步：read one data，是一個(gè)data
  pass
 def __len__(self):
  # You should change 0 to the total size of your dataset.
  return 0

0.jpg 0
1.jpg 1
2.jpg 2
3.jpg 3
4.jpg 4
5.jpg 5
6.jpg 6
7.jpg 7
8.jpg 8
9.jpg 9

0.jpg 0 10
1.jpg 1 11
2.jpg 2 12
3.jpg 3 13
4.jpg 4 14
5.jpg 5 15
6.jpg 6 16
7.jpg 7 17
8.jpg 8 18
9.jpg 9 19

import torch
from torch.autograd import Variable
from torchvision import transforms
from torch.utils.data import Dataset, DataLoader
import numpy as np
from utils import image_processing
import os
 
class TorchDataset(Dataset):
 def __init__(self, filename, image_dir, resize_height=256, resize_width=256, repeat=1):
  '''
  :param filename: 數(shù)據(jù)文件TXT：格式：imge_name.jpg label1_id labe2_id
  :param image_dir: 圖片路徑：image_dir+imge_name.jpg構(gòu)成圖片的完整路徑
  :param resize_height 為None時(shí)，不進(jìn)行縮放
  :param resize_width 為None時(shí)，不進(jìn)行縮放，
        PS：當(dāng)參數(shù)resize_height或resize_width其中一個(gè)為None時(shí)，可實(shí)現(xiàn)等比例縮放
  :param repeat: 所有樣本數(shù)據(jù)重復(fù)次數(shù)，默認(rèn)循環(huán)一次，當(dāng)repeat為None時(shí)，表示無(wú)限循環(huán)sys.maxsize
  '''
  self.image_label_list = self.read_file(filename)
  self.image_dir = image_dir
  self.len = len(self.image_label_list)
  self.repeat = repeat
  self.resize_height = resize_height
  self.resize_width = resize_width
 
  # 相關(guān)預(yù)處理的初始化
  '''class torchvision.transforms.ToTensor'''
  # 把shape=(H,W,C)的像素值范圍為[0, 255]的PIL.Image或者numpy.ndarray數(shù)據(jù)
  # 轉(zhuǎn)換成shape=(C,H,W)的像素?cái)?shù)據(jù)，并且被歸一化到[0.0, 1.0]的torch.FloatTensor類型。
  self.toTensor = transforms.ToTensor()
 
  '''class torchvision.transforms.Normalize(mean, std)
  此轉(zhuǎn)換類作用于torch. * Tensor,給定均值(R, G, B) 和標(biāo)準(zhǔn)差(R, G, B)，
  用公式channel = (channel - mean) / std進(jìn)行規(guī)范化。
  '''
  # self.normalize=transforms.Normalize()
 
 def __getitem__(self, i):
  index = i % self.len
  # print("i={},index={}".format(i, index))
  image_name, label = self.image_label_list[index]
  image_path = os.path.join(self.image_dir, image_name)
  img = self.load_data(image_path, self.resize_height, self.resize_width, normalization=False)
  img = self.data_preproccess(img)
  label=np.array(label)
  return img, label
 
 def __len__(self):
  if self.repeat == None:
   data_len = 10000000
  else:
   data_len = len(self.image_label_list) * self.repeat
  return data_len
 
 def read_file(self, filename):
  image_label_list = []
  with open(filename, 'r') as f:
   lines = f.readlines()
   for line in lines:
    # rstrip：用來(lái)去除結(jié)尾字符、空白符(包括\n、\r、\t、' '，即：換行、回車、制表符、空格)
    content = line.rstrip().split(' ')
    name = content[0]
    labels = []
    for value in content[1:]:
     labels.append(int(value))
    image_label_list.append((name, labels))
  return image_label_list
 
 def load_data(self, path, resize_height, resize_width, normalization):
  '''
  加載數(shù)據(jù)
  :param path:
  :param resize_height:
  :param resize_width:
  :param normalization: 是否歸一化
  :return:
  '''
  image = image_processing.read_image(path, resize_height, resize_width, normalization)
  return image
 
 def data_preproccess(self, data):
  '''
  數(shù)據(jù)預(yù)處理
  :param data:
  :return:
  '''
  data = self.toTensor(data)
  return data

if __name__=='__main__':
 train_filename="../dataset/train.txt"
 # test_filename="../dataset/test.txt"
 image_dir='../dataset/images'
 
 epoch_num=2 #總樣本循環(huán)次數(shù)
 batch_size=7 #訓(xùn)練時(shí)的一組數(shù)據(jù)的大小
 train_data_nums=10
 max_iterate=int((train_data_nums+batch_size-1)/batch_size*epoch_num) #總迭代次數(shù)
 
 train_data = TorchDataset(filename=train_filename, image_dir=image_dir,repeat=1)
 # test_data = TorchDataset(filename=test_filename, image_dir=image_dir,repeat=1)
 train_loader = DataLoader(dataset=train_data, batch_size=batch_size, shuffle=False)
 # test_loader = DataLoader(dataset=test_data, batch_size=batch_size,shuffle=False)
 
 # [1]使用epoch方法迭代，TorchDataset的參數(shù)repeat=1
 for epoch in range(epoch_num):
  for batch_image, batch_label in train_loader:
   image=batch_image[0,:]
   image=image.numpy()#image=np.array(image)
   image = image.transpose(1, 2, 0) # 通道由[c,h,w]->[h,w,c]
   image_processing.cv_show_image("image",image)
   print("batch_image.shape:{},batch_label:{}".format(batch_image.shape,batch_label))
   # batch_x, batch_y = Variable(batch_x), Variable(batch_y)

 '''
 下面兩種方式，TorchDataset設(shè)置repeat=None可以實(shí)現(xiàn)無(wú)限循環(huán)，退出循環(huán)由max_iterate設(shè)定
 '''
 train_data = TorchDataset(filename=train_filename, image_dir=image_dir,repeat=None)
 train_loader = DataLoader(dataset=train_data, batch_size=batch_size, shuffle=False)
 # [2]第2種迭代方法
 for step, (batch_image, batch_label) in enumerate(train_loader):
  image=batch_image[0,:]
  image=image.numpy()#image=np.array(image)
  image = image.transpose(1, 2, 0) # 通道由[c,h,w]->[h,w,c]
  image_processing.cv_show_image("image",image)
  print("step:{},batch_image.shape:{},batch_label:{}".format(step,batch_image.shape,batch_label))
  # batch_x, batch_y = Variable(batch_x), Variable(batch_y)
  if step>=max_iterate:
   break
 # [3]第3種迭代方法
 # for step in range(max_iterate):
 #  batch_image, batch_label=train_loader.__iter__().__next__()
 #  image=batch_image[0,:]
 #  image=image.numpy()#image=np.array(image)
 #  image = image.transpose(1, 2, 0) # 通道由[c,h,w]->[h,w,c]
 #  image_processing.cv_show_image("image",image)
 #  print("batch_image.shape:{},batch_label:{}".format(batch_image.shape,batch_label))
 #  # batch_x, batch_y = Variable(batch_x), Variable(batch_y)

# -*-coding: utf-8 -*-
"""
 @Project: IntelligentManufacture
 @File : image_processing.py
 @Author : panjq
 @E-mail : pan_jinquan@163.com
 @Date : 2019-02-14 15:34:50
"""
 
import os
import glob
import cv2
import numpy as np
import matplotlib.pyplot as plt
 
def show_image(title, image):
 '''
 調(diào)用matplotlib顯示RGB圖片
 :param title: 圖像標(biāo)題
 :param image: 圖像的數(shù)據(jù)
 :return:
 '''
 # plt.figure("show_image")
 # print(image.dtype)
 plt.imshow(image)
 plt.axis('on') # 關(guān)掉坐標(biāo)軸為 off
 plt.title(title) # 圖像題目
 plt.show()
 
def cv_show_image(title, image):
 '''
 調(diào)用OpenCV顯示RGB圖片
 :param title: 圖像標(biāo)題
 :param image: 輸入RGB圖像
 :return:
 '''
 channels=image.shape[-1]
 if channels==3:
  image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR) # 將BGR轉(zhuǎn)為RGB
 cv2.imshow(title,image)
 cv2.waitKey(0)
 
def read_image(filename, resize_height=None, resize_width=None, normalization=False):
 '''
 讀取圖片數(shù)據(jù),默認(rèn)返回的是uint8,[0,255]
 :param filename:
 :param resize_height:
 :param resize_width:
 :param normalization:是否歸一化到[0.,1.0]
 :return: 返回的RGB圖片數(shù)據(jù)
 '''
 
 bgr_image = cv2.imread(filename)
 # bgr_image = cv2.imread(filename,cv2.IMREAD_IGNORE_ORIENTATION|cv2.IMREAD_COLOR)
 if bgr_image is None:
  print("Warning:不存在:{}", filename)
  return None
 if len(bgr_image.shape) == 2: # 若是灰度圖則轉(zhuǎn)為三通道
  print("Warning:gray image", filename)
  bgr_image = cv2.cvtColor(bgr_image, cv2.COLOR_GRAY2BGR)
 
 rgb_image = cv2.cvtColor(bgr_image, cv2.COLOR_BGR2RGB) # 將BGR轉(zhuǎn)為RGB
 # show_image(filename,rgb_image)
 # rgb_image=Image.open(filename)
 rgb_image = resize_image(rgb_image,resize_height,resize_width)
 rgb_image = np.asanyarray(rgb_image)
 if normalization:
  # 不能寫成:rgb_image=rgb_image/255
  rgb_image = rgb_image / 255.0
 # show_image("src resize image",image)
 return rgb_image
 
def fast_read_image_roi(filename, orig_rect, ImreadModes=cv2.IMREAD_COLOR, normalization=False):
 '''
 快速讀取圖片的方法
 :param filename: 圖片路徑
 :param orig_rect:原始圖片的感興趣區(qū)域rect
 :param ImreadModes: IMREAD_UNCHANGED
      IMREAD_GRAYSCALE
      IMREAD_COLOR
      IMREAD_ANYDEPTH
      IMREAD_ANYCOLOR
      IMREAD_LOAD_GDAL
      IMREAD_REDUCED_GRAYSCALE_2
      IMREAD_REDUCED_COLOR_2
      IMREAD_REDUCED_GRAYSCALE_4
      IMREAD_REDUCED_COLOR_4
      IMREAD_REDUCED_GRAYSCALE_8
      IMREAD_REDUCED_COLOR_8
      IMREAD_IGNORE_ORIENTATION
 :param normalization: 是否歸一化
 :return: 返回感興趣區(qū)域ROI
 '''
 # 當(dāng)采用IMREAD_REDUCED模式時(shí)，對(duì)應(yīng)rect也需要縮放
 scale=1
 if ImreadModes == cv2.IMREAD_REDUCED_COLOR_2 or ImreadModes == cv2.IMREAD_REDUCED_COLOR_2:
  scale=1/2
 elif ImreadModes == cv2.IMREAD_REDUCED_GRAYSCALE_4 or ImreadModes == cv2.IMREAD_REDUCED_COLOR_4:
  scale=1/4
 elif ImreadModes == cv2.IMREAD_REDUCED_GRAYSCALE_8 or ImreadModes == cv2.IMREAD_REDUCED_COLOR_8:
  scale=1/8
 rect = np.array(orig_rect)*scale
 rect = rect.astype(int).tolist()
 bgr_image = cv2.imread(filename,flags=ImreadModes)
 
 if bgr_image is None:
  print("Warning:不存在:{}", filename)
  return None
 if len(bgr_image.shape) == 3: #
  rgb_image = cv2.cvtColor(bgr_image, cv2.COLOR_BGR2RGB) # 將BGR轉(zhuǎn)為RGB
 else:
  rgb_image=bgr_image #若是灰度圖
 rgb_image = np.asanyarray(rgb_image)
 if normalization:
  # 不能寫成:rgb_image=rgb_image/255
  rgb_image = rgb_image / 255.0
 roi_image=get_rect_image(rgb_image , rect)
 # show_image_rect("src resize image",rgb_image,rect)
 # cv_show_image("reROI",roi_image)
 return roi_image
 
def resize_image(image,resize_height, resize_width):
 '''
 :param image:
 :param resize_height:
 :param resize_width:
 :return:
 '''
 image_shape=np.shape(image)
 height=image_shape[0]
 width=image_shape[1]
 if (resize_height is None) and (resize_width is None):#錯(cuò)誤寫法：resize_height and resize_width is None
  return image
 if resize_height is None:
  resize_height=int(height*resize_width/width)
 elif resize_width is None:
  resize_width=int(width*resize_height/height)
 image = cv2.resize(image, dsize=(resize_width, resize_height))
 return image
def scale_image(image,scale):
 '''
 :param image:
 :param scale: (scale_w,scale_h)
 :return:
 '''
 image = cv2.resize(image,dsize=None, fx=scale[0],fy=scale[1])
 return image
 
def get_rect_image(image,rect):
 '''
 :param image:
 :param rect: [x,y,w,h]
 :return:
 '''
 x, y, w, h=rect
 cut_img = image[y:(y+ h),x:(x+w)]
 return cut_img
def scale_rect(orig_rect,orig_shape,dest_shape):
 '''
 對(duì)圖像進(jìn)行縮放時(shí)，對(duì)應(yīng)的rectangle也要進(jìn)行縮放
 :param orig_rect: 原始圖像的rect=[x,y,w,h]
 :param orig_shape: 原始圖像的維度shape=[h,w]
 :param dest_shape: 縮放后圖像的維度shape=[h,w]
 :return: 經(jīng)過(guò)縮放后的rectangle
 '''
 new_x=int(orig_rect[0]*dest_shape[1]/orig_shape[1])
 new_y=int(orig_rect[1]*dest_shape[0]/orig_shape[0])
 new_w=int(orig_rect[2]*dest_shape[1]/orig_shape[1])
 new_h=int(orig_rect[3]*dest_shape[0]/orig_shape[0])
 dest_rect=[new_x,new_y,new_w,new_h]
 return dest_rect
 
def show_image_rect(win_name,image,rect):
 '''
 :param win_name:
 :param image:
 :param rect:
 :return:
 '''
 x, y, w, h=rect
 point1=(x,y)
 point2=(x+w,y+h)
 cv2.rectangle(image, point1, point2, (0, 0, 255), thickness=2)
 cv_show_image(win_name, image)
 
def rgb_to_gray(image):
 image = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
 return image
 
def save_image(image_path, rgb_image,toUINT8=True):
 if toUINT8:
  rgb_image = np.asanyarray(rgb_image * 255, dtype=np.uint8)
 if len(rgb_image.shape) == 2: # 若是灰度圖則轉(zhuǎn)為三通道
  bgr_image = cv2.cvtColor(rgb_image, cv2.COLOR_GRAY2BGR)
 else:
  bgr_image = cv2.cvtColor(rgb_image, cv2.COLOR_RGB2BGR)
 cv2.imwrite(image_path, bgr_image)
 
def combime_save_image(orig_image, dest_image, out_dir,name,prefix):
 '''
 命名標(biāo)準(zhǔn)：out_dir/name_prefix.jpg
 :param orig_image:
 :param dest_image:
 :param image_path:
 :param out_dir:
 :param prefix:
 :return:
 '''
 dest_path = os.path.join(out_dir, name + "_"+prefix+".jpg")
 save_image(dest_path, dest_image)
 
 dest_image = np.hstack((orig_image, dest_image))
 save_image(os.path.join(out_dir, "{}_src_{}.jpg".format(name,prefix)), dest_image)

# -*-coding: utf-8 -*-
"""
 @Project: pytorch-learning-tutorials
 @File : dataset.py
 @Author : panjq
 @E-mail : pan_jinquan@163.com
 @Date : 2019-03-07 18:45:06
"""
import torch
from torch.autograd import Variable
from torchvision import transforms
from torch.utils.data import Dataset, DataLoader
import numpy as np
from utils import image_processing
import os
 
class TorchDataset(Dataset):
 def __init__(self, filename, image_dir, resize_height=256, resize_width=256, repeat=1):
  '''
  :param filename: 數(shù)據(jù)文件TXT：格式：imge_name.jpg label1_id labe2_id
  :param image_dir: 圖片路徑：image_dir+imge_name.jpg構(gòu)成圖片的完整路徑
  :param resize_height 為None時(shí)，不進(jìn)行縮放
  :param resize_width 為None時(shí)，不進(jìn)行縮放，
        PS：當(dāng)參數(shù)resize_height或resize_width其中一個(gè)為None時(shí)，可實(shí)現(xiàn)等比例縮放
  :param repeat: 所有樣本數(shù)據(jù)重復(fù)次數(shù)，默認(rèn)循環(huán)一次，當(dāng)repeat為None時(shí)，表示無(wú)限循環(huán)sys.maxsize
  '''
  self.image_label_list = self.read_file(filename)
  self.image_dir = image_dir
  self.len = len(self.image_label_list)
  self.repeat = repeat
  self.resize_height = resize_height
  self.resize_width = resize_width
 
  # 相關(guān)預(yù)處理的初始化
  '''class torchvision.transforms.ToTensor'''
  # 把shape=(H,W,C)的像素值范圍為[0, 255]的PIL.Image或者numpy.ndarray數(shù)據(jù)
  # 轉(zhuǎn)換成shape=(C,H,W)的像素?cái)?shù)據(jù)，并且被歸一化到[0.0, 1.0]的torch.FloatTensor類型。
  self.toTensor = transforms.ToTensor()
 
  '''class torchvision.transforms.Normalize(mean, std)
  此轉(zhuǎn)換類作用于torch. * Tensor,給定均值(R, G, B) 和標(biāo)準(zhǔn)差(R, G, B)，
  用公式channel = (channel - mean) / std進(jìn)行規(guī)范化。
  '''
  # self.normalize=transforms.Normalize()
 
 def __getitem__(self, i):
  index = i % self.len
  # print("i={},index={}".format(i, index))
  image_name, label = self.image_label_list[index]
  image_path = os.path.join(self.image_dir, image_name)
  img = self.load_data(image_path, self.resize_height, self.resize_width, normalization=False)
  img = self.data_preproccess(img)
  label=np.array(label)
  return img, label
 
 def __len__(self):
  if self.repeat == None:
   data_len = 10000000
  else:
   data_len = len(self.image_label_list) * self.repeat
  return data_len
 
 def read_file(self, filename):
  image_label_list = []
  with open(filename, 'r') as f:
   lines = f.readlines()
   for line in lines:
    # rstrip：用來(lái)去除結(jié)尾字符、空白符(包括\n、\r、\t、' '，即：換行、回車、制表符、空格)
    content = line.rstrip().split(' ')
    name = content[0]
    labels = []
    for value in content[1:]:
     labels.append(int(value))
    image_label_list.append((name, labels))
  return image_label_list
 
 def load_data(self, path, resize_height, resize_width, normalization):
  '''
  加載數(shù)據(jù)
  :param path:
  :param resize_height:
  :param resize_width:
  :param normalization: 是否歸一化
  :return:
  '''
  image = image_processing.read_image(path, resize_height, resize_width, normalization)
  return image
 
 def data_preproccess(self, data):
  '''
  數(shù)據(jù)預(yù)處理
  :param data:
  :return:
  '''
  data = self.toTensor(data)
  return data
 
if __name__=='__main__':
 train_filename="../dataset/train.txt"
 # test_filename="../dataset/test.txt"
 image_dir='../dataset/images'
 
 epoch_num=2 #總樣本循環(huán)次數(shù)
 batch_size=7 #訓(xùn)練時(shí)的一組數(shù)據(jù)的大小
 train_data_nums=10
 max_iterate=int((train_data_nums+batch_size-1)/batch_size*epoch_num) #總迭代次數(shù)
 
 train_data = TorchDataset(filename=train_filename, image_dir=image_dir,repeat=1)
 # test_data = TorchDataset(filename=test_filename, image_dir=image_dir,repeat=1)
 train_loader = DataLoader(dataset=train_data, batch_size=batch_size, shuffle=False)
 # test_loader = DataLoader(dataset=test_data, batch_size=batch_size,shuffle=False)
 
 # [1]使用epoch方法迭代，TorchDataset的參數(shù)repeat=1
 for epoch in range(epoch_num):
  for batch_image, batch_label in train_loader:
   image=batch_image[0,:]
   image=image.numpy()#image=np.array(image)
   image = image.transpose(1, 2, 0) # 通道由[c,h,w]->[h,w,c]
   image_processing.cv_show_image("image",image)
   print("batch_image.shape:{},batch_label:{}".format(batch_image.shape,batch_label))
   # batch_x, batch_y = Variable(batch_x), Variable(batch_y)
 
 '''
 下面兩種方式，TorchDataset設(shè)置repeat=None可以實(shí)現(xiàn)無(wú)限循環(huán)，退出循環(huán)由max_iterate設(shè)定
 '''
 train_data = TorchDataset(filename=train_filename, image_dir=image_dir,repeat=None)
 train_loader = DataLoader(dataset=train_data, batch_size=batch_size, shuffle=False)
 # [2]第2種迭代方法
 for step, (batch_image, batch_label) in enumerate(train_loader):
  image=batch_image[0,:]
  image=image.numpy()#image=np.array(image)
  image = image.transpose(1, 2, 0) # 通道由[c,h,w]->[h,w,c]
  image_processing.cv_show_image("image",image)
  print("step:{},batch_image.shape:{},batch_label:{}".format(step,batch_image.shape,batch_label))
  # batch_x, batch_y = Variable(batch_x), Variable(batch_y)
  if step>=max_iterate:
   break
 # [3]第3種迭代方法
 # for step in range(max_iterate):
 #  batch_image, batch_label=train_loader.__iter__().__next__()
 #  image=batch_image[0,:]
 #  image=image.numpy()#image=np.array(image)
 #  image = image.transpose(1, 2, 0) # 通道由[c,h,w]->[h,w,c]
 #  image_processing.cv_show_image("image",image)
 #  print("batch_image.shape:{},batch_label:{}".format(batch_image.shape,batch_label))
 #  # batch_x, batch_y = Variable(batch_x), Variable(batch_y)