nvinayvarma189

def Custom_Conv(bottom):
	import tensorflow as tf
  	#bottom is the previous layer. Her it is UpSampling2D layer
	input_channels = int(bottom.get_shape()[-1])

	# initialize weights and biases using xavier
	weights = tf.Variable(tf.truncated_normal(shape=[1, 1, input_channels, 1], dtype=tf.float32, stddev=tf.sqrt(1.0 / (1 * 1 * input_channels))))

	biases = tf.Variable(tf.constant(0, dtype=tf.float32, shape=[1]))

nvinayvarma189

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
         
    <modelVersion>4.0.0</modelVersion>
    <artifactId>dl4j-quickstart</artifactId>
    
    <groupId>org.deeplearning4j</groupId>
    
    <version>1.0.0-beta4</version>
    <packaging>jar</packaging>

nvinayvarma189

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
         
    <modelVersion>4.0.0</modelVersion>
    <artifactId>dl4j-quickstart</artifactId>
    
    <groupId>org.deeplearning4j</groupId>
    
    <version>1.0.0-beta2</version>
    <packaging>jar</packaging>

nvinayvarma189

# Simulated Annealing for Clustering Problems
import math
import random
num_objects = 10 # numbers of objects to be clustered
num_cost_increases = 100
avg_cost_increase = 200
acc_ratio = 0.75 # acceptance ratio should e between 0 and 1
prob_e = 0.00000000001 # probability factor
beta = 0.125
max_iter =  4 * num_objects # maximum number of iterations