from __future__ import print_function

import numpy as np

from keras.models import Model

from keras.models import Sequential

from keras.layers import Input, merge, Convolution2D, MaxPooling2D, UpSampling2D, ZeroPadding2D, Activation, Flatten, Dense, Dropout

from keras.optimizers import Adam

from keras.callbacks import ModelCheckpoint, LearningRateScheduler

from keras.preprocessing.image import ImageDataGenerator

from keras.layers.normalization import BatchNormalization

from keras.regularizers import l2

from keras import backend as K

from keras.utils.generic_utils import Progbar

from resnet import *

datagen = ImageDataGenerator(

vertical_flip=True)

def clf_train(X_train,y_train,validation_data,nb_epoch=30,MODEL_TYPE=RESNET):

return model

def clf_train_more(model,X_train,y_train,validation_data,nb_epoch):

return model

def train_vs_test(train_preds,test_preds,nb_epoch=25):

model.fit(X, y, batch_size=32,validation_split=0.2,nb_epoch=nb_epoch)

def predict_over_augmentations(model,X,y,n_aug=10,evaluate=True):

return probs

def VGG_16(image_shape):

return model