import numpy as np

import os

import skimage.io as io

import skimage.transform as trans

import numpy as np

from keras.models import *

from keras.layers import *

from keras.optimizers import *

from keras.callbacks import ModelCheckpoint, LearningRateScheduler

from keras import backend as keras

import tensorflow as tf

from keras import initializers

from keras import regularizers

def fu(pretrained_weights=None, input_size=(256, 256, 3)):

    inputs = Input(input_size)

    paddings = tf.constant([[0, 0], [1, 1], [1, 1], [0, 0], [0, 0]])  # only pads dim 2 and 3 (h and w)

    [ inputtemp, inputspet,inputsct] = Lambda(tf.split, arguments={'axis': 3, 'num_or_size_splits': 3})(inputs)

    inputs_temp = Lambda(tf.add, arguments={'y': (inputsct)})(inputspet)

    conv1 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(inputs_temp)

    conv1 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv1)

    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)

    conv2 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(pool1)

    conv2 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv2)

    pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)

    conv3 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(pool2)

    conv3 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv3)

    pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)

    conv4 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(pool3)

    conv4 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv4)

    drop4 = Dropout(0.5)(conv4)

    pool4 = MaxPooling2D(pool_size=(2, 2))(conv4)

    up5 = Conv2D(64, 2, activation='relu', padding='same', kernel_initializer='he_normal')(

        UpSampling2D(size=(2, 2))(pool4))

    conv5 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(up5)

    conv5 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv5)

    up6 = Conv2D(64, 2, activation='relu', padding='same', kernel_initializer='he_normal')(

        UpSampling2D(size=(2, 2))(conv5))

    conv6 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(up6)

    conv6 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv6)

    up7 = Conv2D(64, 2, activation='relu', padding='same', kernel_initializer='he_normal')(

        UpSampling2D(size=(2, 2))(conv6))

    conv7 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(up7)

    conv7 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv7)

    up8 = Conv2D(64, 2, activation='relu', padding='same', kernel_initializer='he_normal')(

        UpSampling2D(size=(2, 2))(conv7))

    conv8 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(up8)

    conv8 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv8)

    conv9 = Conv2D(4, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv8)

    conv10 = Conv2D(1, 1, activation='sigmoid')(conv9)

    model = Model(input=inputs, output=conv10)

    model.compile(optimizer=Adam(lr=1e-4), loss='binary_crossentropy', metrics=['accuracy'])

    if (pretrained_weights):

        model.load_weights(pretrained_weights)

    return model

def expand_dim_backend(x,dim):

    xe = K.expand_dims(x, dim)

    return xe