audio.py

import os 
#os.environ["CUDA_VISIBLE_DEVICES"] = "0"
import numpy as np
from keras.models import *
from keras.layers import Input, merge, Conv2D, MaxPooling2D, UpSampling2D, Dropout, Cropping2D, BatchNormalization, Flatten
from keras.optimizers import *
from keras.callbacks import ModelCheckpoint, LearningRateScheduler, TensorBoard
from keras import backend as keras
from data import *

def getAudio(r = 224, c = 224):
    inputs = Input((r, c,1))

    conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(inputs)
    print ("conv1 shape:",conv1.shape)
    conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv1)
    print ("conv1 shape:",conv1.shape)
    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
    print ("pool1 shape:",pool1.shape)

    conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool1)
    print ("conv2 shape:",conv2.shape)
    conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv2)
    print ("conv2 shape:",conv2.shape)
    pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
    print ("pool2 shape:",pool2.shape)

    conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool2)
    print ("conv3 shape:",conv3.shape)
    conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv3)
    print ("conv3 shape:",conv3.shape)
    pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
    print ("pool3 shape:",pool3.shape)

    conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool3)
    conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv4)
    drop4 = Dropout(0.5)(conv4)
    pool4 = MaxPooling2D(pool_size=(2, 2))(drop4)

    conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool4)
    conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv5)
    drop5 = Dropout(0.5)(conv5)

    model = Model(inputs, drop5)

    return drop5, inputs, model