Jovian
Sign In

Classifying Fruits 360 dataset images using ResNets, Regularization and Data Augmentation in PyTorch

This is the final course assignment.

!pip install jovian --upgrade --quiet
!pip install opendatasets --upgrade
Collecting opendatasets Downloading https://files.pythonhosted.org/packages/18/99/aaa3ebec81dc347302e730e0daff61735ed2f3e736129553fb3f9bf67ed3/opendatasets-0.1.10-py3-none-any.whl Requirement already satisfied, skipping upgrade: tqdm in /usr/local/lib/python3.6/dist-packages (from opendatasets) (4.41.1) Requirement already satisfied, skipping upgrade: kaggle in /usr/local/lib/python3.6/dist-packages (from opendatasets) (1.5.10) Requirement already satisfied, skipping upgrade: click in /usr/local/lib/python3.6/dist-packages (from opendatasets) (7.1.2) Requirement already satisfied, skipping upgrade: certifi in /usr/local/lib/python3.6/dist-packages (from kaggle->opendatasets) (2020.12.5) Requirement already satisfied, skipping upgrade: python-slugify in /usr/local/lib/python3.6/dist-packages (from kaggle->opendatasets) (4.0.1) Requirement already satisfied, skipping upgrade: requests in /usr/local/lib/python3.6/dist-packages (from kaggle->opendatasets) (2.23.0) Requirement already satisfied, skipping upgrade: six>=1.10 in /usr/local/lib/python3.6/dist-packages (from kaggle->opendatasets) (1.15.0) Requirement already satisfied, skipping upgrade: urllib3 in /usr/local/lib/python3.6/dist-packages (from kaggle->opendatasets) (1.24.3) Requirement already satisfied, skipping upgrade: python-dateutil in /usr/local/lib/python3.6/dist-packages (from kaggle->opendatasets) (2.8.1) Requirement already satisfied, skipping upgrade: text-unidecode>=1.3 in /usr/local/lib/python3.6/dist-packages (from python-slugify->kaggle->opendatasets) (1.3) Requirement already satisfied, skipping upgrade: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests->kaggle->opendatasets) (3.0.4) Requirement already satisfied, skipping upgrade: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests->kaggle->opendatasets) (2.10) Installing collected packages: opendatasets Successfully installed opendatasets-0.1.10

In this project, I'll use the following techniques to train a model to achieve over 99% accuracy in classifying images from the Fruits 360 dataset:

  • Data normalization
  • Data augmentation
  • Residual connections
  • Batch normalization
  • Learning rate scheduling
  • Weight Decay
  • Gradient clipping
  • Adam optimizer
import os
import torch
import torchvision
import tarfile
import torch.nn as nn
import numpy as np
import torch.nn.functional as F
from torchvision.datasets.utils import download_url
from torchvision.datasets import ImageFolder
from torch.utils.data import DataLoader
import torchvision.transforms as tt
from torch.utils.data import random_split
from torchvision.utils import make_grid
import matplotlib
import matplotlib.pyplot as plt
%matplotlib inline

matplotlib.rcParams['figure.facecolor'] = '#ffffff'