sadimanna

'''
"Contrast Limited Adaptive Histogram Equalization"
by Karel Zuiderveld, [email protected]
in "Graphics Gems IV", Academic Press, 1994

_Author_ -- Siladittya Manna

The below implementation does not assume that the 
X- and Y image resolutions are an integer multiple
of the X- and Y sizes of the contextual regions.

sadimanna

def conv2d(x,numfilt,filtsz,strides=1,pad='same',act=True,name=None):
  x = Conv2D(numfilt,filtsz,strides,padding=pad,data_format='channels_last',use_bias=False,name=name+'conv2d')(x)
  x = BatchNormalization(axis=3,scale=False,name=name+'conv2d'+'bn')(x)
  if act:
    x = Activation('relu',name=name+'conv2d'+'act')(x)
  return x

sadimanna

def incresA(x,scale,name=None):
    pad = 'same'
    branch0 = conv2d(x,32,1,1,pad,True,name=name+'b0')
    branch1 = conv2d(x,32,1,1,pad,True,name=name+'b1_1')
    branch1 = conv2d(branch1,32,3,1,pad,True,name=name+'b1_2')
    branch2 = conv2d(x,32,1,1,pad,True,name=name+'b2_1')
    branch2 = conv2d(branch2,48,3,1,pad,True,name=name+'b2_2')
    branch2 = conv2d(branch2,64,3,1,pad,True,name=name+'b2_3')
    branches = [branch0,branch1,branch2]
    mixed = Concatenate(axis=3, name=name + '_concat')(branches)

sadimanna

def incresB(x,scale,name=None):
    pad = 'same'
    branch0 = conv2d(x,192,1,1,pad,True,name=name+'b0')
    branch1 = conv2d(x,128,1,1,pad,True,name=name+'b1_1')
    branch1 = conv2d(branch1,160,[1,7],1,pad,True,name=name+'b1_2')
    branch1 = conv2d(branch1,192,[7,1],1,pad,True,name=name+'b1_3')
    branches = [branch0,branch1]
    mixed = Concatenate(axis=3, name=name + '_mixed')(branches)
    filt_exp_1x1 = conv2d(mixed,1152,1,1,pad,False,name=name+'filt_exp_1x1')
    final_lay = Lambda(lambda inputs, scale: inputs[0] + inputs[1] * scale,

sadimanna

def incresC(x,scale,name=None):
    pad = 'same'
    branch0 = conv2d(x,192,1,1,pad,True,name=name+'b0')
    branch1 = conv2d(x,192,1,1,pad,True,name=name+'b1_1')
    branch1 = conv2d(branch1,224,[1,3],1,pad,True,name=name+'b1_2')
    branch1 = conv2d(branch1,256,[3,1],1,pad,True,name=name+'b1_3')
    branches = [branch0,branch1]
    mixed = Concatenate(axis=3, name=name + '_mixed')(branches)
    filt_exp_1x1 = conv2d(mixed,2048,1,1,pad,False,name=name+'fin1x1')
    final_lay = Lambda(lambda inputs, scale: inputs[0] + inputs[1] * scale,

sadimanna

img_input = Input(shape=(256,256,3))

x = conv2d(img_input,32,3,2,'valid',True,name='conv1')
x = conv2d(x,32,3,1,'valid',True,name='conv2')
x = conv2d(x,64,3,1,'valid',True,name='conv3')

x_11 = MaxPooling2D(3,strides=1,padding='valid',name='stem_br_11'+'_maxpool_1')(x)
x_12 = conv2d(x,64,3,1,'valid',True,name='stem_br_12')

x = Concatenate(axis=3, name = 'stem_concat_1')([x_11,x_12])

sadimanna

#Inception-ResNet-A modules
x = incresA(x,0.15,name='incresA_1')
x = incresA(x,0.15,name='incresA_2')
x = incresA(x,0.15,name='incresA_3')
x = incresA(x,0.15,name='incresA_4')

#35 × 35 to 17 × 17 reduction module.
x_red_11 = MaxPooling2D(3,strides=2,padding='valid',name='red_maxpool_1')(x)

x_red_12 = conv2d(x,384,3,2,'valid',True,name='x_red1_c1')

sadimanna

import numpy as np
import pandas as pd
import os
from sklearn.model_selection import KFold, StratifiedKFold
import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator

sadimanna

train_data = pd.read_csv('training_labels.csv')
Y = train_data[['label']]

kf = KFold(n_splits = 5)
                         
skf = StratifiedKFold(n_split = 5, random_state = 7, shuffle = True) 

sadimanna

VALIDATION_ACCURACY = []
VALIDAITON_LOSS = []

save_dir = '/saved_models/'
fold_var = 1

for train_index, val_index in kf.split(np.zeros(n),Y):
	training_data = train_data.iloc[train_index]
	validation_data = train_data.iloc[val_index]