Tensorflow分類器項目自定義數(shù)據(jù)讀入的實現(xiàn)

import os
import keras
import matplotlib.pyplot as plt
from PIL import Image
from keras.preprocessing.image import ImageDataGenerator
from sklearn.model_selection import train_test_split

image_path = r'D:\Projects\ImageClassifier\data\set'
path = ".\data"
# 你也可以使用相對路徑的方式
# image_path =os.path.join(path, "set")

label_name = "labels.txt"
label_path = os.path.join(path, label_name)
class_names = np.loadtxt(label_path, type(""))

re_load = False
re_build = False
# re_load = True
re_build = True

data_name = "data.npz"
data_path = os.path.join(path, data_name)
model_name = "model.h6"
model_path = os.path.join(path, model_name)

count = 0

# 這里判斷是否存在序列化之后的數(shù)據(jù)，re_load是一個開關(guān)，是否強制重新處理，測試用，可以去除。
if not os.path.exists(data_path) or re_load:
  labels = []
  images = []
  print('Handle images')
  # 由于label.txt是和圖片防止目錄的分類目錄一一對應(yīng)的，即每個子目錄的目錄名就是labels.txt里的一個label，所以這里可以通過讀取class_names的每一項去拼接path后讀取
  for index, name in enumerate(class_names):
    # 這里是拼接后的子目錄path
    classpath = os.path.join(image_path, name)
    # 先判斷一下是否是目錄
    if not os.path.isdir(classpath):
      continue
    # limit是測試時候用的這里可以去除
    limit = 0
    for image_name in os.listdir(classpath):
      if limit >= max_size:
        break
      # 這里是拼接后的待處理的圖片path
      imagepath = os.path.join(classpath, image_name)
      count = count + 1
      limit = limit + 1
      # 利用Image打開圖片
      img = Image.open(imagepath)
      # 縮放到你最初確定要處理的圖片分辨率大小
      img = img.resize((IMG_SIZE_X, IMG_SIZE_Y))
      # 轉(zhuǎn)為灰度圖片，這里彩色通道會干擾結(jié)果，并且會加大計算量
      img = img.convert("L")
      # 轉(zhuǎn)為numpy數(shù)組
      img = np.array(img)
      # 由（30，30）轉(zhuǎn)為（1，30，30）（即`channels_first`），當然你也可以轉(zhuǎn)換為（30，30，1）（即`channels_last`）但為了之后預覽處理后的圖片方便這里采用了（1，30，30）的格式存放
      img = np.reshape(img, (1, IMG_SIZE_X, IMG_SIZE_Y))
      # 這里利用循環(huán)生成labels數(shù)據(jù)，其中存放的實際是class_names中對應(yīng)元素的索引
      labels.append([index])
      # 添加到images中，最后統(tǒng)一處理
      images.append(img)
      # 循環(huán)中一些狀態(tài)的輸出，可以去除
      print("{} class: {} {} limit: {} {}"
         .format(count, index + 1, class_names[index], limit, imagepath))
  # 最后一次性將images和labels都轉(zhuǎn)換成numpy數(shù)組
  npy_data = np.array(images)
  npy_labels = np.array(labels)
  # 處理數(shù)據(jù)只需要一次，所以我們選擇在這里利用numpy自帶的方法將處理之后的數(shù)據(jù)序列化存儲
  np.savez(data_path, x=npy_data, y=npy_labels)
  print("Save images by npz")
else:
  # 如果存在序列化號的數(shù)據(jù)，便直接讀取，提高速度
  npy_data = np.load(data_path)["x"]
  npy_labels = np.load(data_path)["y"]
  print("Load images by npz")
image_data = npy_data
labels_data = npy_labels

# 最后一步就是將原始數(shù)據(jù)分成訓練數(shù)據(jù)和測試數(shù)據(jù)
train_images, test_images, train_labels, test_labels = \
  train_test_split(image_data, labels_data, test_size=0.2, random_state=6)

print("_________________________________________________________________")
print("%-28s %-s" % ("Name", "Shape"))
print("=================================================================")
print("%-28s %-s" % ("Image Data", image_data.shape))
print("%-28s %-s" % ("Labels Data", labels_data.shape))
print("=================================================================")

print('Split train and test data,p=%')
print("_________________________________________________________________")
print("%-28s %-s" % ("Name", "Shape"))
print("=================================================================")
print("%-28s %-s" % ("Train Images", train_images.shape))
print("%-28s %-s" % ("Test Images", test_images.shape))
print("%-28s %-s" % ("Train Labels", train_labels.shape))
print("%-28s %-s" % ("Test Labels", test_labels.shape))
print("=================================================================")

print("Normalize images")
train_images = train_images / 255.0
test_images = test_images / 255.0

import os

import keras
import matplotlib.pyplot as plt
from PIL import Image
from keras.layers import *
from keras.models import *
from keras.optimizers import Adam
from keras.preprocessing.image import ImageDataGenerator
from sklearn.model_selection import train_test_split

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
# 支持中文
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用來正常顯示中文標簽
plt.rcParams['axes.unicode_minus'] = False # 用來正常顯示負號
re_load = False
re_build = False
# re_load = True
re_build = True
epochs = 50
batch_size = 5
count = 0
max_size = 2000000000