DevanagriModelOCR_not_sure.py

import os
import h5py
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from keras import optimizers
from keras.models import Sequential
from keras.layers import Convolution2D,MaxPooling2D,Activation, Dropout, Flatten, Dense


trainDataGen = ImageDataGenerator(
		rotation_range = 5,
		width_shift_range = 0.1,
		height_shift_range = 0.1,
		rescale = 1.0/255,
		shear_range = 0.2,
		zoom_range = 0.2,		
		horizontal_flip = False,
		fill_mode = 'nearest')

test_datagen = ImageDataGenerator(rescale=1./255)
trainGenerator = trainDataGen.flow_from_directory(
			r"C:\Users\Devashish Bhake\Desktop\Computer Vision\Devnagri Text Dataset\DevanagariHandwrittenCharacterDataset\DevanagariHandwrittenCharacterDataset\Train",
			target_size = (32,32),
			batch_size = 32,
			color_mode = "grayscale",
			class_mode = "categorical")
prev = ""
labels = ["ka","kha","ga","gha","kna","cha","chha","ja","jha","yna","ta","tha","da","dha","adna","ta","tha","da","dha","na","pa","pha","ba","bha","ma","yaw","ra","la","waw","sha","shat","sa","ha","aksha","tra","gya","0","1","2","3","4","5","6","7","8","9"]
count = 0;

# get the count of all the images in each of the labels
'''for i in trainGenerator.classes:
	if prev == labels[i]:
		count = count+1
		continue;
	print count
	print labels[i]
	count = 1
	prev = labels[i]
print count
'''

validation_generator = test_datagen.flow_from_directory(
			r"C:\Users\Devashish Bhake\Desktop\Computer Vision\Devnagri Text Dataset\DevanagariHandwrittenCharacterDataset\DevanagariHandwrittenCharacterDataset\Train",
			target_size=(32,32),
			batch_size=32,
			color_mode = "grayscale",
			class_mode= 'categorical')
			
model = Sequential()
model.add(Convolution2D(filters = 32,
			kernel_size = (3,3),
			strides = 1,
			activation = "relu",
			input_shape = (32,32,1)))

model.add(Convolution2D(filters = 32,
			kernel_size = (3,3),
			strides = 1,
			activation = "relu",
			input_shape = (32,32,1)))

model.add(MaxPooling2D(pool_size=(2, 2),
			strides=(2, 2),
			padding="same"))
		
model.add(Convolution2D(filters = 64,
			kernel_size = (3,3),
			strides = 1,
			activation = "relu"))

model.add(Convolution2D(filters = 64,
			kernel_size = (3,3),
			strides= 1,
			activation = "relu"))

model.add(MaxPooling2D(pool_size=(2, 2),
			strides=(2, 2),
			padding="same"))			
			
model.add(Dropout(0.2))

model.add(Flatten())

model.add(Dense(128,
		activation = "relu",
		kernel_initializer = "uniform"))			

model.add(Dense(64,
		activation = "relu",
		kernel_initializer = "uniform"))			

model.add(Dense(46,
		activation = "softmax",
		kernel_initializer = "uniform"))			
			
model.compile(optimizer = "adam",
		loss = "categorical_crossentropy",
		metrics = ["accuracy"])
		
print model.summary()

model.fit(
		trainGenerator,
		nb_epoch = 20,
		steps_per_epoch = 2444,
		validation_data = validation_generator,
		validation_steps = 432
		)
		
model.save("DevanagariModel.h5")