从功能API模型上的Keras CNN预测中获得概率

时间:2019-04-03 09:40:24

标签: python tensorflow keras

我如何从Keras获得概率?

我为3个班级训练了CNN模型。当我在新的测试图像上使用经过训练的模型的predict()方法(使用Functional API)时,总是得到一个热编码输出,ei [0, 1, 0],而我想得到诸如[0.1, 0.95, 0.1]之类的输出

我使用softmax作为最后一次激活,因此所有概率之和总计为1。但是,我创建了一个虚拟模型,仅在一个时期内对其进行了训练,但仍然获得了一个热编码输出,而不是概率。

我在这里做错了吗,比如调用错误的方法?否则如何获取最后一层的输出,以便可以对输出进行规范化?

预测脚本的片段:

model = load_model('./model.h5')
model.compile(loss='categorical_crossentropy',
              optimizer='adadelta',
              metrics=['acc'])

img = image.load_img(path.name,
                     target_size=(128, 128),
                     color_mode='grayscale')
img = image.img_to_array(img)
img = np.expand_dims(img, axis=0)
probability = model.predict(img)
print(probability)

培训脚本:

# Creates input shape for theano or tensorflow.
if K.image_data_format() == 'channels_first':
    input_shape = (1, 128, 128)
else:
    input_shape = (128, 128, 1)
visible = Input(shape=input_shape)

conv1_1 = Conv2D(filters=8,kernel_size=(5, 5),padding='same', strides = 1)(visible)
prelu1_1 = PReLU(alpha_initializer='zeros')(conv1_1)
pool1_1 = MaxPooling2D(pool_size=(2, 2),strides=2)(prelu1_1)

flat1 = Flatten()(pool1_1)

conv2_1 = Conv2D(filters=8,kernel_size=(5, 5),padding='same', strides = 1)(visible)
prelu2_1 = PReLU(alpha_initializer='zeros')(conv2_1)
pool2_1 = MaxPooling2D(pool_size=(2, 2),strides=2)(prelu2_1)

flat2 = Flatten()(pool2_1)

# Merge layers
merge = concatenate([flat1, flat2])

dense = Dense(64)(merge)
prelu3 = PReLU(alpha_initializer='zeros')(dense)
dropout3 = Dropout(rate=0.4)(prelu3)

dense4 = Dense(3)(dropout3)
output = Activation('softmax')(dense4)

model = Model(inputs=visible, outputs=output)

model.compile(loss='categorical_crossentropy',
              optimizer='Adadelta',
              metrics=['accuracy'])

train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    width_shift_range=0.1,
    height_shift_range=0.1,
    rotation_range=5,
    horizontal_flip=True)

test_datagen = ImageDataGenerator(
    rescale=1. / 255, )


train_data_dir = r'D:\path\to\train'
validation_data_dir = r'D:\path\to\validation'

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(128, 128),
    batch_size=32,
    color_mode='grayscale',
    class_mode='categorical')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(128, 128),
    batch_size=32,
    color_mode='grayscale',
    class_mode='categorical')

model_final = model.fit_generator(
    train_generator,
    steps_per_epoch=11000 // 32,
    epochs=1,
    validation_data=validation_generator,
    validation_steps=3000 // 32)

# Save model
model.save('./model.h5')

Keras版本:2.1.6

注意: model建立在功能性API上,即(keras.models.Model()

1 个答案:

答案 0 :(得分:1)

如果您不使用功能性API,则可以进行console.log以获取概率。

model.predict_proba()

希望这会有所帮助。