Question

我是Python和Keras深度学习的新手。在网上有一些关于猫和非猫分类的教程，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 fire 检测，因此我认为我需要使用彩色图像而不是此灰度版本（+会有所帮助吗？！）。换句话说，要摆脱img = img.convert('L')并使用颜色进行训练。

当我尝试将频道数增加到3时，遇到了此错误：

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)

如何解决此错误？

这是我原来的培训代码：

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

要转换图像，必须复制单个图像的通道。请注意，复制通道后，您只需要“会聚图像”即可。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()

训练我的彩色图像而不是灰度的简单模型

1 个答案: