While building a Deep Learning model, the first task is to import datasets online and this task proves to be very hectic sometimes.
We can easily import Kaggle datasets in just a few steps:
Code: Importing CIFAR 10 dataset
Now go to your Kaggle account and create new API token from my account section, a kaggle.json file will be downloaded in your PC.
Code: Uploading the kaggle.json file
Copy the URL of your dataset and paste it in another cell.
Code: To unzip the uploaded dataset.
Now your training and test set is ready to be used.
- How to use Google Colaboratory for Video Processing
- How to run Python code on Google Colaboratory
- ML | Boston Housing Kaggle Challenge with Linear Regression
- Getting started with Kaggle : A quick guide for beginners
- ML | Kaggle Breast Cancer Wisconsin Diagnosis using KNN and Cross Validation
- ML | Kaggle Breast Cancer Wisconsin Diagnosis using Logistic Regression
- How Should a Machine Learning Beginner Get Started on Kaggle?
- Applying Convolutional Neural Network on mnist dataset
- ML | Using SVM to perform classification on a non-linear dataset
- Pandas | Parsing JSON Dataset
- Pyspark | Linear regression with Advanced Feature Dataset using Apache MLlib
- Tensorflow | tf.data.Dataset.reduce()
- Tensorflow | tf.data.Dataset.from_tensor_slices()
- Plotting graph For IRIS Dataset Using Seaborn And Matplotlib
- Python - Basics of Pandas using Iris Dataset
- Python Bokeh – Visualizing the Iris Dataset
- Different dataset forms in Social Networks
- Image Caption Generator using Deep Learning on Flickr8K dataset
- Visualising ML DataSet Through Seaborn Plots and Matplotlib
- Python - Removing Constant Features From the Dataset
If you like GeeksforGeeks and would like to contribute, you can also write an article using contribute.geeksforgeeks.org or mail your article to firstname.lastname@example.org. See your article appearing on the GeeksforGeeks main page and help other Geeks.
Please Improve this article if you find anything incorrect by clicking on the "Improve Article" button below.