We will use the famous MNIST Handwritten Digits Databases as our training dataset.It consists of 28px by 28px grayscale images of handwritten disgits(0–9), along with labels for each image indicating which digit it represents. MNIST stands for Modified National Institute of Standards and Technology.PyTorch is an optimized tensor library for deep learning using GPUs and CPUs.
Quick Navigation
1. Brief about PyTorch
2. Working with images in PyToch(using MNIST Dataset)
3. Splitting a dataset into training, Validation and test sets
4. Creating PyTorch models with custom logic by extending the nn.Module Class
5. Interpreting model outputs as probabilities using softmax, and picking predicted labels
6. Picking a good evaluation metric(accuracy) and loss function(cross entropy) for Classification problems
7.Setting up a training loop that also evaluates the model using Validation set
8. Testing the model manually on randomly picked examples
9.Saving and loading the model checkpoints to avoid retraining from scratch
10. References
## Imports
import torch
import torchvision ## Contains some utilities for working with the image data
from torchvision.datasets import MNIST
import matplotlib.pyplot as plt
#%matplotlib inline
import torchvision.transforms as transforms
from torch.utils.data import random_split
from torch.utils.data import DataLoader
import torch.nn.functional as FWe will…
In the ever-changing ecosystem of convolution neural network (CNN), Recently I read an interesting article on “Alexnet Architecture”. I decided to unravel the learning of amazing paper on Alexnet.AlexNet is the name of a Convolution Neural Network, designed by Alex Krizhevskly,and published with Ilya Sutskever and Krizhevsky’s PhD advisor Geoffrey Hinton.
AlexNet competed in the ImageNet Large Scale Visual Recognition Challenge in 2012. The Network achieved a top-5 error of 15.3%.
Key Points of this Architecture ->
1. Non-Saturating Non-linearity: In this Architecture, we have used ReLu Activation function. …
