PaddlePaddle 深度学习实战（第一部分）

PaddlePaddle 深度学习实战（第二部分）

PaddlePaddle 深度学习实战（第三部分）

PaddlePaddle 深度学习实战（第四部分）

PaddlePaddle 深度学习实战（第五部分）

深度学习框架的作用

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 1

AI术语

激活函数、优化方法、损失函数(成本函数)

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 2

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 3

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 4

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 5

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 6

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 7

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 8

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 9

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 10

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 11

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 12

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 13

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 14

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 15

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 16

二分类、多分类与多标签问题的区别，对应损失函数的选择

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 17

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 18

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 19

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 20

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 21

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 22

二分类、多分类、多标签和多输出问题解析

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 23

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 24

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 25

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 26

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 27

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 28

创建模型的关键代码
class FashionNet:
    @staticmethod
    def build_category_branch(inputs, numCategories,
        finalAct="softmax", chanDim=-1):
        # utilize a lambda layer to convert the 3 channel input to a
        # grayscale representation
        x = Lambda(lambda c: tf.image.rgb_to_grayscale(c))(inputs)
        # CONV => RELU => POOL
        x = Conv2D(32, (3, 3), padding="same")(x)
        x = Activation("relu")(x)
        x = BatchNormalization(axis=chanDim)(x)
        x = MaxPooling2D(pool_size=(3, 3))(x)
        x = Dropout(0.25)(x)
    # Omit some similar code
        # define a branch of output layers for the number of different
        # clothing categories (i.e., shirts, jeans, dresses, etc.)
        x = Flatten()(x)
        x = Dense(256)(x)
        x = Activation("relu")(x)
        x = BatchNormalization()(x)
        x = Dropout(0.5)(x)
        x = Dense(numCategories)(x)
        x = Activation(finalAct, name="category_output")(x)
        # return the category prediction sub-network
        return x
    @staticmethod
    def build_color_branch(inputs, numColors, finalAct="softmax",
        chanDim=-1):
        # CONV => RELU => POOL
        x = Conv2D(16, (3, 3), padding="same")(inputs)
        x = Activation("relu")(x)
        x = BatchNormalization(axis=chanDim)(x)
        x = MaxPooling2D(pool_size=(3, 3))(x)
        x = Dropout(0.25)(x)
    # Omit some similar code
        # define a branch of output layers for the number of different
        # colors (i.e., red, black, blue, etc.)
        x = Flatten()(x)
        x = Dense(128)(x)
        x = Activation("relu")(x)
        x = BatchNormalization()(x)
        x = Dropout(0.5)(x)
        x = Dense(numColors)(x)
        x = Activation(finalAct, name="color_output")(x)
        # return the color prediction sub-network
        return x
    @staticmethod
    def build(width, height, numCategories, numColors,
        finalAct="softmax"):
        # initialize the input shape and channel dimension (this code
        # assumes you are using TensorFlow which utilizes channels
        # last ordering)
        inputShape = (height, width, 3)
        chanDim = -1
        # construct both the "category" and "color" sub-networks
        inputs = Input(shape=inputShape)
        categoryBranch = FashionNet.build_category_branch(inputs,
            numCategories, finalAct=finalAct, chanDim=chanDim)
        colorBranch = FashionNet.build_color_branch(inputs,
            numColors, finalAct=finalAct, chanDim=chanDim)
        # create the model using our input (the batch of images) and
        # two separate outputs -- one for the clothing category
        # branch and another for the color branch, respectively
        model = Model(
            inputs=inputs,
            outputs=[categoryBranch, colorBranch],
            name="fashionnet")
        # return the constructed network architecture
        return model