srikarplus

Edit: This list is now maintained in the rust-anthology repo.

• Introduction
  • Understanding Over Guesswork
  • An Alternative Introduction to Rust
  • Rust and CSV Parsing
• Ownership
  • Where Rust Really Shines
  • Rust Means Never Having to Close a Socket
• The Problem with Single-threaded Shared Mutability

srikarplus

def make_weights_for_balanced_classes(images, nclasses):                        
    count = [0] * nclasses                                                      
    for item in images:                                                         
        count[item[1]] += 1                                                     
    weight_per_class = [0.] * nclasses                                      
    N = float(sum(count))                                                   
    for i in range(nclasses):                                                   
        weight_per_class[i] = N/float(count[i])                                 
    weight = [0] * len(images)                                              
    for idx, val in enumerate(images):                                          

srikarplus

import torch
import numpy as np

from utils import plot_images
from torchvision import datasets
from torchvision import transforms
from torch.utils.data.sampler import SubsetRandomSampler


def get_train_valid_loader(data_dir,

srikarplus

def randInitializeWeights(L_in, L_out):
    epsilon = 0.12
    return np.random.rand(L_out, L_in+1) * 2 * epsilon - epsilon

initial_theta1 = randInitializeWeights(input_layer_size, hidden_layer_size)
initial_theta2 = randInitializeWeights(hidden_layer_size, num_labels)

# unrolling parameters into a single column vector
nn_initial_params = np.hstack((initial_theta1.ravel(order='F'), initial_theta2.ravel(order='F')))

srikarplus

def predict(theta1, theta2, X, y):
    m = len(y)
    ones = np.ones((m,1))
    a1 = np.hstack((ones, X))
    a2 = sigmoid(a1 @ theta1.T)
    a2 = np.hstack((ones, a2))
    h = sigmoid(a2 @ theta2.T)
    return np.argmax(h, axis = 1) + 1

srikarplus

theta_opt = opt.fmin_cg(maxiter = 50, f = nnCostFunc, x0 = nn_initial_params, fprime = nnGrad, \
                        args = (input_layer_size, hidden_layer_size, num_labels, X, y.flatten(), lmbda))

theta1_opt = np.reshape(theta_opt[:hidden_layer_size*(input_layer_size+1)], (hidden_layer_size, input_layer_size+1), 'F')
theta2_opt = np.reshape(theta_opt[hidden_layer_size*(input_layer_size+1):], (num_labels, hidden_layer_size+1), 'F')

srikarplus

def checkGradient(nn_initial_params,nn_backprop_Params,input_layer_size, hidden_layer_size, num_labels,myX,myy,mylambda=0.):
    myeps = 0.0001
    flattened = nn_initial_params
    flattenedDs = nn_backprop_Params
    n_elems = len(flattened) 
    #Pick ten random elements, compute numerical gradient, compare to respective D's
    for i in range(10):
        x = int(np.random.rand()*n_elems)
        epsvec = np.zeros((n_elems,1))
        epsvec[x] = myeps

srikarplus

def nnGrad(nn_params, input_layer_size, hidden_layer_size, num_labels, X, y, lmbda):
    
    initial_theta1 = np.reshape(nn_params[:hidden_layer_size*(input_layer_size+1)], (hidden_layer_size, input_layer_size+1), 'F')
    initial_theta2 = np.reshape(nn_params[hidden_layer_size*(input_layer_size+1):], (num_labels, hidden_layer_size+1), 'F')
    y_d = pd.get_dummies(y.flatten())
    delta1 = np.zeros(initial_theta1.shape)
    delta2 = np.zeros(initial_theta2.shape)
    m = len(y)
    
    for i in range(X.shape[0]):

srikarplus

def nnCostFunc(nn_params, input_layer_size, hidden_layer_size, num_labels, X, y, lmbda):
    theta1 = np.reshape(nn_params[:hidden_layer_size*(input_layer_size+1)], (hidden_layer_size, input_layer_size+1), 'F')
    theta2 = np.reshape(nn_params[hidden_layer_size*(input_layer_size+1):], (num_labels, hidden_layer_size+1), 'F')

    m = len(y)
    ones = np.ones((m,1))
    a1 = np.hstack((ones, X))
    a2 = sigmoid(a1 @ theta1.T)
    a2 = np.hstack((ones, a2))
    h = sigmoid(a2 @ theta2.T)