import numpy as np
from keras import layers as layers
from keras.layers import Input, Dense, Activation, ZeroPadding2D, BatchNormalization, Flatten, Conv2D
from keras.layers import AveragePooling2D, MaxPooling2D, Dropout, GlobalMaxPooling2D, GlobalAveragePooling2D
from keras.models import Model
from keras.preprocessing import image
from keras.utils import layer_utils
from keras.utils.data_utils import get_file
from keras.applications.imagenet_utils import preprocess_input
import pydot
from IPython.display import SVG
from keras.utils.vis_utils import model_to_dot
from keras.utils import plot_model
from kt_utils import *

import keras.backend as K
K.set_image_data_format('channels_last')
import matplotlib.pyplot as plt
from matplotlib.pyplot import imshow

#%% 构建网络

# GRADED FUNCTION: HappyModel

def HappyModel(input_shape):
    """
    Implementation of the HappyModel.

    Arguments:
    input_shape -- shape of dataset, 不含样本个数

    Returns:
    model -- a Model() instance in Keras
    """

    ### START CODE HERE ###
    # Feel free to use the suggested outline in the text above to get started, and run through the whole
    # exercise (including the later portions of this notebook) once. The come back also try out other
    # network architectures as well.

    X_input = Input(input_shape)

    X = ZeroPadding2D((3, 3))(X_input)

    # CONV -> BN -> RELU Block applied to X
    X = Conv2D(32, (7, 7), strides=(1, 1), name='conv0')(X)
    X = BatchNormalization(axis=3, name='bn0')(X)
    X = Activation('relu')(X)

    # MAXPOOL
    X = MaxPooling2D((2, 2), name='max_pool')(X)

    # FLATTEN X (means convert it to a vector) + FULLYCONNECTED
    X = Flatten()(X)
    X = Dense(1, activation='sigmoid', name='fc')(X)

    # Create model. This creates your Keras model instance, you'll use this instance to train/test the model.
    model = Model(inputs=X_input, outputs=X, name='HappyModel')

    ### END CODE HERE ###

    return model


happyModel = HappyModel(input_shape=(X_train.shape[1:]))

happyModel.compile(optimizer = "adam", loss = "categorical_crossentropy", metrics = ["accuracy"])
# loss:
# mean_squared_error或mse
# mean_absolute_error或mae
# mean_absolute_percentage_error或mape
# mean_squared_logarithmic_error或msle
# squared_hinge
# hinge
# binary_crossentropy（亦称作对数损失，logloss）
# categorical_crossentropy：亦称作多类的对数损失，注意使用该目标函数时，需要将标签转化为形如(nb_samples, nb_classes)的二值序列
# sparse_categorical_crossentrop：如上，但接受稀疏标签。注意，使用该函数时仍然需要你的标签与输出值的维度相同，你可能需要在标签数据上增加一个维度：np.expand_dims(y,-1)
# kullback_leibler_divergence:从预测值概率分布Q到真值概率分布P的信息增益,用以度量两个分布的差异.
# cosine_proximity：即预测值与真实标签的余弦距离平均值的相反数

happyModel.fit(x=X_train,y=Y_train,epochs=500,batch_size=512)
# 再次训练是接着上一次的

#%%
preds = happyModel.evaluate(x = X_test, y = y_test) # 返回loss 和你设置的 metrics

#%%

# 模型展示
happyModel.summary()

plot_model(happyModel, to_file='HappyModel.png')
SVG(model_to_dot(happyModel).create(prog='dot', format='svg'))