Objective: Find a neural network model that achieves the highest accuracy rate for the classification of Fruits360 images.

1. Deep Feed Forward
2. Convolutional Neural Network
3. Residual Neural Network (ResNet9)

Data Source: https://www.kaggle.com/moltean/fruits

Full Code Notebook: https://jovian.ml/limyingying2000/fruitsfinal

Data Preparation

First, let’s understand our dataset!

The Kaggle Fruits 360 dataset consists of 90483 images of 131 different types of fruits and vegetables.

To begin, we import the data and the required libraries to run our codes.

import torch
import os
import jovian
import torchvision
import numpy as np
import matplotlib.pyplot as plt
import torch.nn as nn
import torchvision.models as models
import torch.nn.functional as F
from torchvision.datasets import ImageFolder
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
import torchvision.models as models
%matplotlib inline

Each type of fruits has its unique folder comprising of its jpg images.

Using matplotlib library to display the colour image:

import matplotlib.pyplot as plt

def show_example(img, label):
    print('Label: ', dataset.classes[label], "("+str(label)+")")
    plt.imshow(img.permute(1, 2, 0))

dataset[5000] is an Apple Red Delicious

As we are using PyTorch, we need to convert the above pixel image into a tensor using ToTensor:

dataset = ImageFolder(data_dir + '/Training', transform=ToTensor())
img, label = dataset[0]
print(img.shape, label) 
img

An example of image converted into a tensor

There are 3 channels (red, green, blue) , 100*100 image size. Each value represents the colour intensity with respect to the channel colour.

Training and Validation Dataset

Next, we will randomly split the data to achieve 3 sets of data for different purposes.

1. Training Set : Train the model
2. Validation Set: Evaluate the model
3. Test Set: Report the final accuracy of the model

Size of training dataset : 57, 692

Size of validation dataset: 10, 000

Size of test dataset: 22, 688

Training in Batches

We have a total of 57, 692 training images. We should split our images into smaller batches before training our model using_DataLoader_. Working with a smaller set of data reduces memory space and in turn increases the speed of training.

For our dataset, we will use a batch size of 128.

![Image for post](https://miro.medium.com/max/1050/1*3Zp8qc3ZvGTzC7_r5ZFsWA.png

128 randomly assigned images in a training batch

Now, we will begin designing our models.

#neural-networks #pytorch #jovian #classification #resnet