santhalakshminarayana

sequences, next_chars = [], []
window = 5
for name in names:
  if len(name) < window:
    sequences.append(name+'.'*(window-len(name)))
    next_chars.append('.')
    seq_lengths.append(len(name))
  else:
    for i in range(0,len(name) - window + 1):
      sequences.append(name[i:i+window])

santhalakshminarayana

group_names = []
for name in names:
  name_list = name.split(' ')
  group_names.extend(name_list)
  
group_names = set(group_names)

unique_chars=set()
names = []
for name in group_names:

santhalakshminarayana

import pandas as pd
import numpy as np

names_df = pd.read_csv('Indian Names.txt',error_bad_lines=False)

names_df = names_df.drop_duplicates(keep='first').reset_index(drop=True)
names_df = np.squeeze(names_df).values.tolist()

santhalakshminarayana

def conv_block(X,filters,block):
    # resiudal block with dilated convolutions
    # add skip connection at last after doing convoluion operation to input X
    
    b = 'block_'+str(block)+'_'
    f1,f2,f3 = filters
    X_skip = X
    # block_a
    X = Convolution2D(filters=f1,kernel_size=(1,1),dilation_rate=(1,1),
                      padding='same',kernel_initializer='he_normal',name=b+'a')(X)

santhalakshminarayana

train_folder="/kaggle/input/cityscapes-image-pairs/cityscapes_data/cityscapes_data/train/"
valid_folder="/kaggle/input/cityscapes-image-pairs/cityscapes_data/cityscapes_data/val/"

def get_images_masks(path):
    names=os.listdir(path)
    img_g,img_m=[],[]
    for name in names:
        img=cv2.imread(path+name)
        img=cv2.normalize(img,None,0,1,cv2.NORM_MINMAX,cv2.CV_32F)
        img=img[:,:,::-1]

santhalakshminarayana

import numpy as np
import os
import matplotlib.pyplot as plt
import cv2
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.layers import Convolution2D,BatchNormalization,ReLU,LeakyReLU,Add,Activation
from tensorflow.keras.layers import GlobalAveragePooling2D,AveragePooling2D,UpSampling2D

santhalakshminarayana

# Label names for class numbers
person_rep={0:'Lakshmi Narayana',
 1: 'Vladimir Putin',
 2: 'Angela Merkel',
 3: 'Narendra Modi',
 4: 'Donald Trump',
 5: 'Xi Jinping'}

if __name__ == '__main__':
  file_path=input("Path to image with file size < 100 kb ? ")

santhalakshminarayana

# Softmax regressor to classify images based on encoding 
classifier_model=Sequential()	
classifier_model.add(Dense(units=100,input_dim=x_train.shape[1],kernel_initializer='glorot_uniform'))		
classifier_model.add(BatchNormalization())		
classifier_model.add(Activation('tanh'))
classifier_model.add(Dropout(0.3))
classifier_model.add(Dense(units=10,kernel_initializer='glorot_uniform'))
classifier_model.add(BatchNormalization())
classifier_model.add(Activation('tanh'))
classifier_model.add(Dropout(0.2))

santhalakshminarayana

# Prepare Train Data
x_train=[]
y_train=[]
person_rep=dict()
person_folders=os.listdir(path+'/Images_crop/')
for i,person in enumerate(person_folders):
  person_rep[i]=person
  image_names=os.listdir('Images_crop/'+person+'/')
  for image_name in image_names:
    img=load_img(path+'/Images_crop/'+person+'/'+image_name,target_size=(224,224))

santhalakshminarayana

# Tensorflow version == 2.0.0
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.models import Sequential,Model
from tensorflow.keras.layers import ZeroPadding2D,Convolution2D,MaxPooling2D
from tensorflow.keras.layers import Dense,Dropout,Softmax,Flatten,Activation,BatchNormalization
from tensorflow.keras.preprocessing.image import load_img,img_to_array
from tensorflow.keras.applications.imagenet_utils import preprocess_input
import tensorflow.keras.backend as K