Keras 多类图像分类和预测

Question

我正在用 ImageDataGenerator 进行图像 class 化。我的数据具有以下结构：

火车
- 101
- 102
- 103
- 104
测试
- 101
- 102
- 103
- 104

因此，如果我理解得很好，ImageGenerator 会自动执行所需的标签操作。我训练了模型，并获得了某种准确性。现在我想做预测。

- model.predict
- model.predict_proba
- model.predict_classes

所有这些都给了我同样的价值。你能快速解释或参考（我找不到任何关于我的问题的信息）我应该如何继续，或者我在代码中做了一些糟糕的事情。最大的问题是，我不明白 4 个不同的 classes 的输出会有何不同。由于 predict_classes 给我一个输出 [[1]]，它不应该给我预测的 class 吗？

from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, MaxPool2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras.regularizers import l1, l2, l1_l2

model = Sequential()
model.add(Conv2D(60, (3, 3), input_shape=(480, 640,3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(60, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(100, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())  # this converts our 3D feature maps to 1D feature vectors
model.add(Dense(100, activation='relu', activity_regularizer=l1(0.001)))
#model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('softmax'))

model.compile(loss='binary_crossentropy',
              optimizer='Adam',
              metrics=['accuracy'])

batch_size = 32

# augmentation configuration for train
train_datagen = ImageDataGenerator(
        rotation_range=30,
        width_shift_range=0.2,
        height_shift_range=0.2,
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=False,
        vertical_flip=True,
        fill_mode = 'nearest')

# augmentation configuration for testing, only rescale
test_datagen = ImageDataGenerator(rescale=1./255)

# reading pictures and  generating batches of augmented image data

train_generator = train_datagen.flow_from_directory(
        '/media/data/working_dir/categories/readytotest/train',
        target_size=(480, 640),
        batch_size=batch_size,
        class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
        '/media/data/working_dir/categories/readytotest/test',
        target_size=(480, 640),
        batch_size=batch_size,
        class_mode='binary')

model.fit_generator(
        train_generator,
        steps_per_epoch=800 // batch_size,
        epochs=15,
        validation_data=validation_generator,
        validation_steps=800 // batch_size)

Answer 1

您的模型和生成器不是多 class 而是二进制 class 化。首先，您需要修复模型的最后一层以获得 class 大小的输出。其次，您需要修复生成器以在 multi class.

中使用

(...)
model.add(Dense(CLS_SZ))
model.add(Activation('softmax'))
(...)

# I am not sure about this read some docs about generator you used.
train_generator = train_datagen.flow_from_directory(
        '/media/data/working_dir/categories/readytotest/train',
        target_size=(480, 640),
        batch_size=batch_size,
        class_mode=None)

validation_generator = test_datagen.flow_from_directory(
        '/media/data/working_dir/categories/readytotest/test',
        target_size=(480, 640),
        batch_size=batch_size,
        class_mode=None)

Keras 多类图像分类和预测

Keras multiclass images classification and prediction

python

classification

deep-learning

keras

tensorflow