Learn practical skills, build real-world projects, and advance your career

Classifying images of everyday objects using a neural network

The ability to try many different neural network architectures to address a problem is what makes deep learning really powerful, especially compared to shallow learning techniques like linear regression, logistic regression etc.

In this assignment, you will:

  1. Explore the CIFAR10 dataset: https://www.cs.toronto.edu/~kriz/cifar.html
  2. Set up a training pipeline to train a neural network on a GPU
  3. Experiment with different network architectures & hyperparameters

As you go through this notebook, you will find a ??? in certain places. Your job is to replace the ??? with appropriate code or values, to ensure that the notebook runs properly end-to-end. Try to experiment with different network structures and hypeparameters to get the lowest loss.

You might find these notebooks useful for reference, as you work through this notebook:

# Uncomment and run the commands below if imports fail
!conda install numpy pandas pytorch torchvision cpuonly -c pytorch -y
!pip install matplotlib --upgrade --quiet
Collecting package metadata (current_repodata.json): done Solving environment: done ## Package Plan ## environment location: /opt/conda added / updated specs: - cpuonly - numpy - pandas - pytorch - torchvision The following packages will be downloaded: package | build ---------------------------|----------------- ca-certificates-2020.4.5.2 | hecda079_0 147 KB conda-forge certifi-2020.4.5.2 | py37hc8dfbb8_0 152 KB conda-forge numpy-1.18.5 | py37h8960a57_0 5.1 MB conda-forge pandas-1.0.4 | py37h0da4684_0 10.1 MB conda-forge ------------------------------------------------------------ Total: 15.5 MB The following packages will be UPDATED: ca-certificates 2020.4.5.1-hecc5488_0 --> 2020.4.5.2-hecda079_0 certifi 2020.4.5.1-py37hc8dfbb8_0 --> 2020.4.5.2-py37hc8dfbb8_0 numpy 1.18.1-py37h8960a57_1 --> 1.18.5-py37h8960a57_0 pandas 1.0.3-py37h0da4684_1 --> 1.0.4-py37h0da4684_0 Downloading and Extracting Packages certifi-2020.4.5.2 | 152 KB | ##################################### | 100% pandas-1.0.4 | 10.1 MB | ##################################### | 100% ca-certificates-2020 | 147 KB | ##################################### | 100% numpy-1.18.5 | 5.1 MB | ##################################### | 100% Preparing transaction: done Verifying transaction: done Executing transaction: done
import torch
import torchvision
import numpy as np
import matplotlib.pyplot as plt
import torch.nn as nn
import torch.nn.functional as F
from torchvision.datasets import CIFAR10
from torchvision.transforms import ToTensor
from torchvision.utils import make_grid
from torch.utils.data.dataloader import DataLoader
from torch.utils.data import random_split
%matplotlib inline
# Project name used for jovian.commit
project_name = '03-cifar10-feedforward'

Exploring the CIFAR10 dataset