Prasad9’s gists

Prasad9 / annotation.xml

Created November 6, 2017 13:54

A sample XML annotation file based on Pascal VOC format.

	<annotation>
	<folder>GeneratedData_Train</folder>
	<filename>000001.png</filename>
	<path>/my/path/GeneratedData_Train/000001.png</path>
	<source>
	<database>Unknown</database>
	</source>
	<size>
	<width>224</width>
	<height>224</height>

Prasad9 / perspective_transform.py

Last active October 21, 2017 07:27

Perform the perspective transform on an image

	def get_mask_coord(imshape):
	vertices = np.array([[(0.09 * imshape[1], 0.99 * imshape[0]),
	(0.43 * imshape[1], 0.32 * imshape[0]),
	(0.56 * imshape[1], 0.32 * imshape[0]),
	(0.85 * imshape[1], 0.99 * imshape[0])]], dtype = np.int32)
	return vertices

	def get_perspective_matrices(X_img):
	offset = 15
	img_size = (X_img.shape[1], X_img.shape[0])

Prasad9 / add_gaussian_noise.py

Last active July 20, 2025 20:39

Python code to add random Gaussian noise on images

	import cv2

	def add_gaussian_noise(X_imgs):
	gaussian_noise_imgs = []
	row, col, _ = X_imgs[0].shape
	# Gaussian distribution parameters
	mean = 0
	var = 0.1
	sigma = var ** 0.5

Prasad9 / salt_pepper_noise_images.py

Last active June 3, 2021 16:38

Add salt and pepper noise to images

	def add_salt_pepper_noise(X_imgs):
	# Need to produce a copy as to not modify the original image
	X_imgs_copy = X_imgs.copy()
	row, col, _ = X_imgs_copy[0].shape
	salt_vs_pepper = 0.2
	amount = 0.004
	num_salt = np.ceil(amount * X_imgs_copy[0].size * salt_vs_pepper)
	num_pepper = np.ceil(amount * X_imgs_copy[0].size * (1.0 - salt_vs_pepper))

	for X_img in X_imgs_copy:

Prasad9 / rotate_images.py

Created October 21, 2017 05:27

Tensorflow framework to rotate images at given start and end angle with total number of images to produce

	from math import pi

	def rotate_images(X_imgs, start_angle, end_angle, n_images):
	X_rotate = []
	iterate_at = (end_angle - start_angle) / (n_images - 1)

	tf.reset_default_graph()
	X = tf.placeholder(tf.float32, shape = (None, IMAGE_SIZE, IMAGE_SIZE, 3))
	radian = tf.placeholder(tf.float32, shape = (len(X_imgs)))
	tf_img = tf.contrib.image.rotate(X, radian)

Prasad9 / flip_images.py

Last active October 21, 2017 03:41

Tensorflow framework code to flip images left-right, up-down and transpose.

	def flip_images(X_imgs):
	X_flip = []
	tf.reset_default_graph()
	X = tf.placeholder(tf.float32, shape = (IMAGE_SIZE, IMAGE_SIZE, 3))
	tf_img1 = tf.image.flip_left_right(X)
	tf_img2 = tf.image.flip_up_down(X)
	tf_img3 = tf.image.transpose_image(X)
	with tf.Session() as sess:
	sess.run(tf.global_variables_initializer())
	for img in X_imgs:

Prasad9 / rotate90_images.py

Created October 20, 2017 21:59

Tensorflow framework code to rotate image at 90, 180 and 270 degrees

	def rotate_images(X_imgs):
	X_rotate = []
	tf.reset_default_graph()
	X = tf.placeholder(tf.float32, shape = (IMAGE_SIZE, IMAGE_SIZE, 3))
	k = tf.placeholder(tf.int32)
	tf_img = tf.image.rot90(X, k = k)
	with tf.Session() as sess:
	sess.run(tf.global_variables_initializer())
	for img in X_imgs:
	for i in range(3): # Rotation at 90, 180 and 270 degrees

Prasad9 / translate_images.py

Last active October 21, 2017 07:26

Tensorflow framework code to translate images in all sides

	from math import ceil, floor

	def get_translate_parameters(index):
	if index == 0: # Translate left 20 percent
	offset = np.array([0.0, 0.2], dtype = np.float32)
	size = np.array([IMAGE_SIZE, ceil(0.8 * IMAGE_SIZE)], dtype = np.int32)
	w_start = 0
	w_end = int(ceil(0.8 * IMAGE_SIZE))
	h_start = 0
	h_end = IMAGE_SIZE

Prasad9 / central_scale_images.py

Last active October 20, 2017 20:56

Tensorflow framework code to centrally scale images

	def central_scale_images(X_imgs, scales):
	# Various settings needed for Tensorflow operation
	boxes = np.zeros((len(scales), 4), dtype = np.float32)
	for index, scale in enumerate(scales):
	x1 = y1 = 0.5 - 0.5 * scale # To scale centrally
	x2 = y2 = 0.5 + 0.5 * scale
	boxes[index] = np.array([y1, x1, y2, x2], dtype = np.float32)
	box_ind = np.zeros((len(scales)), dtype = np.int32)
	crop_size = np.array([IMAGE_SIZE, IMAGE_SIZE], dtype = np.int32)

Prasad9 / resize_images.py

Last active May 9, 2019 23:40

Resize images to a common size

	import tensorflow as tf
	import matplotlib.image as mpimg
	import numpy as np

	IMAGE_SIZE = 224

	def tf_resize_images(X_img_file_paths):
	X_data = []
	tf.reset_default_graph()
	X = tf.placeholder(tf.float32, (None, None, 3))