为彩色图像而不是灰度图像训练我的简单模型

Question

我是 Python 和 Keras 深度学习的新手。通过一些关于猫与非猫分类的在线教程，我能够为我的分类编译这个简单的训练代码。但是，我的目标应用程序是火灾检测，所以我认为我需要使用彩色图像而不是这个灰度版本（+ 会有帮助吗？！）。换句话说，摆脱img = img.convert('L') 并使用颜色进行训练。

当我尝试将频道数量增加到3 时，我遇到了这个错误：

training_images = np.array([i[0] for i in training_data]).reshape(-1, IMAGE_SIZE, IMAGE_SIZE, 3)
ValueError: could not broadcast input array from shape (300,300,3) into shape (300,300)

我该如何解决这个错误？

这是我原来的训练代码：

from keras.models import Sequential, load_model
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.layers.normalization import BatchNormalization
from PIL import Image
from random import shuffle, choice
import numpy as np
import os

IMAGE_SIZE = 256
IMAGE_DIRECTORY = './data/test_set'

def label_img(name):
  if name == 'cats': return np.array([1, 0])
  elif name == 'notcats' : return np.array([0, 1])

def load_data():
  print("Loading images...")
  train_data = []
  directories = next(os.walk(IMAGE_DIRECTORY))[1]

  for dirname in directories:
    print("Loading {0}".format(dirname))
    file_names = next(os.walk(os.path.join(IMAGE_DIRECTORY, dirname)))[2]

    for i in range(200):
      image_name = choice(file_names)
      image_path = os.path.join(IMAGE_DIRECTORY, dirname, image_name)
      label = label_img(dirname)
      if "DS_Store" not in image_path:
        img = Image.open(image_path)
        img = img.convert('L')
        img = img.resize((IMAGE_SIZE, IMAGE_SIZE), Image.ANTIALIAS)
        train_data.append([np.array(img), label])

  return train_data

def create_model():
  model = Sequential()
  model.add(Conv2D(32, kernel_size = (3, 3), activation='relu', 
                   input_shape=(IMAGE_SIZE, IMAGE_SIZE, 1)))
  model.add(MaxPooling2D(pool_size=(2,2)))
  model.add(BatchNormalization())
  model.add(Conv2D(64, kernel_size=(3,3), activation='relu'))
  model.add(MaxPooling2D(pool_size=(2,2)))
  model.add(BatchNormalization())
  model.add(Conv2D(128, kernel_size=(3,3), activation='relu'))
  model.add(MaxPooling2D(pool_size=(2,2)))
  model.add(BatchNormalization())
  model.add(Conv2D(128, kernel_size=(3,3), activation='relu'))
  model.add(MaxPooling2D(pool_size=(2,2)))
  model.add(BatchNormalization())
  model.add(Conv2D(64, kernel_size=(3,3), activation='relu'))
  model.add(MaxPooling2D(pool_size=(2,2)))
  model.add(BatchNormalization())
  model.add(Dropout(0.2))
  model.add(Flatten())
  model.add(Dense(256, activation='relu'))
  model.add(Dropout(0.2))
  model.add(Dense(64, activation='relu'))
  model.add(Dense(2, activation = 'softmax'))

  return model

training_data = load_data()
training_images = np.array([i[0] for i in training_data]).reshape(-1, IMAGE_SIZE, IMAGE_SIZE, 1)
training_labels = np.array([i[1] for i in training_data])

print('creating model')
model = create_model()
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
print('training model')
model.fit(training_images, training_labels, batch_size=50, epochs=10, verbose=1)
model.save("model.h5")

Answer 1

为了转换图像，您必须复制单个图像的通道。请注意，您只需要“复制通道后的转换图像。 您可以编写一个执行以下操作的函数并将其传递给理解列表

>>> img = np.random.randint(low=0,high=255, size=(330,330))
>>> converted=np.empty([330,330,3], dtype=int)
>>> red = img.copy()
>>> blue = img.copy()
>>> green = img.copy()
>>> converted[:,:,0]= red
>>> converted[:,:,1]= blue
>>> converted[:,:,2]= green
>>> from PIL import Image
>>> s = Image.fromarray(converted,'RGB')
>>> s.save("rand_image.png")
>>> s.show()