Zerotogans Course Project - Notebook by Daffodil Jorda (dajo09)

Learn how to classify cats and dogs using Feed Forward and Convolutional Neural Networks in PyTorch. Compare models, use normalized and augmented datasets, and download the dataset using Kaggle API.

!pip install jovian --upgrade --quiet

#Cats and Dogs Classification using Feed Forward and Convolutional Neural Networks in PyTorch

This project will be running and comparing between the feed forward neural network and ResNet architectures.

Train and validation datasets will both be taken from the training_set and test_set respectively
Same batch size will be used for both models which is = 16
output size is 2
dataset used is normalized and augmented

# Project name used for jovian.commit
project_name = 'zerotogans-course-project'

#install dependencies
!pip install kaggle -q
!pip install torch
# !pip install torch===1.6.0 torchvision===0.7.0 -f https://download.pytorch.org/whl/torch_stable.html --quiet

Requirement already satisfied: torch in /usr/local/lib/python3.6/dist-packages (1.7.0+cu101)
Requirement already satisfied: dataclasses in /usr/local/lib/python3.6/dist-packages (from torch) (0.8)
Requirement already satisfied: future in /usr/local/lib/python3.6/dist-packages (from torch) (0.16.0)
Requirement already satisfied: typing-extensions in /usr/local/lib/python3.6/dist-packages (from torch) (3.7.4.3)
Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from torch) (1.19.5)

Choose and download the dataset

through kaggle API
While downloading the dataset, you will be asked to provide your Kaggle username and credentails, which you can obtain using the "Create New API Token" button on your account page on Kaggle. Upload the kaggle.json notebook using the files tab or enter the username and key manually when prompted.