MohanaRC

# @author : https://github.com/MohanaRC
# @description : Python wrapper for Detection of gender from camera using Lua

'''Uses lutorpy to call lua processes within a python function and finds the result of the gender code'''

import lutorpy
import numpy as np
import cv2
import time
import os

MohanaRC

import all the required packages


'''tagging_function : loads training images and allows the user to tag them into categories
   input variables:
   path_of_images : indicates the path of the input images
   path_to_store_tagged_images : indicates the path where the tagged images are renamed and stored'''

define tagging_function(path_of_images, path_to_store_tagged_images):
    get the names of all the images in path_of_images and store it in variable listing

MohanaRC

import numpy as np
import tensorflow as tf

MohanaRC

def tf_gradient_tape(x):
    """
    Simple implementation to understand the functioning of gradient tape
    Inputs:
    x: Tensor value 

    Returns:
    EagerTensor: Derivative of y with respect to input tensor x
    """
    with tf.GradientTape() as t:

MohanaRC

# Run the function for x=5
tmp_x = tf.constant(5.0)
dy_dx = tf_gradient_tape(tmp_x)
result = dy_dx.numpy()

MohanaRC

def tf_gradient_tape2(x):
    """
    Simple implementation to understand the functioning of gradient tape for chain rule
    Inputs:
    x: Tensor value 

    Returns:
    EagerTensor: Derivative of z with respect to input tensor y
    """
    with tf.GradientTape() as t:

MohanaRC

# Run the function for x=5
tmp_x = tf.constant(3.0)
dz_dx = tf_gradient_tape2(tmp_x)
result = dz_dx.numpy()

MohanaRC

def tf_gradient_tape2(x):
    """
    Simple implementation to understand the functioning of gradient tape for chain rule
    Inputs:
    x: Tensor value 

    Returns:
    EagerTensor: Derivative of z with respect to input tensor x
    """
    with tf.GradientTape() as t:

MohanaRC

def tf_gradient_tape_no_persistent(x):
    """
    Simple implementation to understand the functioning of gradient tape for chain rule and return intermediate values without
    setting persistent parameter
    Inputs:
    x: Tensor value 

    Returns:
    EagerTensor: Derivative of y with respect to input tensor x and derivative of z with respect to input tensor x 
    """

MohanaRC

def tf_gradient_tape_persistent(x):
    """
    Simple implementation to understand the functioning of gradient tape for chain rule with persistent set to True
    Inputs:
    x: Tensor value 

    Returns:
    EagerTensor: Derivative of y with respect to input tensor x and derivate of z with respect to x
    """
    with tf.GradientTape(persistent=True) as t: