Niranjankumar-c

def imshow(img, title):
  
  """Custom function to display the image using matplotlib"""
  
  #define std correction to be made
  std_correction = np.asarray([0.229, 0.224, 0.225]).reshape(3, 1, 1)
  
  #define mean correction to be made
  mean_correction = np.asarray([0.485, 0.456, 0.406]).reshape(3, 1, 1)
  

Niranjankumar-c

#required libraries
import warnings
warnings.filterwarnings("ignore")

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import torch 
import torch.nn as nn
import torchvision

Niranjankumar-c

#generate data using make_blobs function from sklearn.
#centers = 4 indicates different types of classes
data, labels = make_blobs(n_samples=1000, centers=4, n_features=2, random_state=0)
print(data.shape, labels.shape)

#visualize the data
plt.scatter(data[:,0], data[:,1], c=labels, cmap=my_cmap)
plt.show()

#splitting the data into train and test

Niranjankumar-c

#required libraries
import numpy as np
import math
import matplotlib.pyplot as plt
import matplotlib.colors
import time
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, mean_squared_error, log_loss
from tqdm import tqdm_notebook 

Niranjankumar-c

def post_process(scatter_plot=False, gradient_plot=True, plot_scale=0.1):    
    #Method for evaluating the network performance and plot the graphs
    Y_pred_train = model.predict(X_train)
    Y_pred_train = np.argmax(Y_pred_train,1)
    Y_pred_val = model.predict(X_val)
    Y_pred_val = np.argmax(Y_pred_val,1)
    #computing the accuracy for test data and train data
    accuracy_train = accuracy_score(Y_pred_train, Y_train)
    accuracy_val = accuracy_score(Y_pred_val, Y_val)
    print("Training accuracy", round(accuracy_train, 4))

Niranjankumar-c

class FFNetwork:
  
  def __init__(self, init_method = 'random', activation_function = 'sigmoid', leaky_slope = 0.1):
        
    self.params={}
    self.params_h = []
    self.num_layers=2
    self.layer_sizes = [2, 2, 4]
    self.activation_function = activation_function
    self.leaky_slope = leaky_slope

Niranjankumar-c

data, labels = make_blobs(n_samples=1000, centers=4, n_features=2, random_state=0)
print(data.shape, labels.shape)

#plot graph
plt.scatter(data[:,0], data[:,1], c=labels, cmap=my_cmap)
plt.show()
#convert 4 class to 2 class data
labels_orig = labels
labels = np.mod(labels_orig, 2)

Niranjankumar-c

import numpy as np
import matplotlib.pyplot as plt
import matplotlib.colors
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, mean_squared_error, log_loss
from tqdm import tqdm_notebook
import seaborn as sns
import imageio
import time
from IPython.display import HTML

Niranjankumar-c

X = np.asarray([0.5, 2.5])
Y = np.asarray([0.2, 0.9])

algo = 'GD'
w_init = -2
b_init = -2
w_min = -7
w_max = 5
b_min = -7
b_max = 5

Niranjankumar-c

if plot_2d: 
  W = np.linspace(w_min, w_max, 256)
  b = np.linspace(b_min, b_max, 256)
  WW, BB = np.meshgrid(W, b)
  Z = sn.error(X, Y, WW, BB)

  fig = plt.figure(dpi=100)
  ax = plt.subplot(111)
  ax.set_xlabel('w')
  ax.set_xlim(w_min - 1, w_max + 1)