How to Install PyTorch in Jupyter Notebook

PyTorch is an open-source machine learning library for Python, which is widely used for developing deep learning applications. Jupyter Notebook is a popular tool for interactive data science and scientific computing.

Step 1: Install Anaconda

Before installing PyTorch, it is recommended to install Anaconda, which is a free and open-source distribution of Python and R programming languages for scientific computing, that aims to simplify package management and deployment.

Step 2: Create a conda environment

Once Anaconda is installed, you can create a new conda environment for your PyTorch installation. Open a terminal or command prompt and run the following command:


conda create -n myenv python=3.8


Replace “myenv” with the desired name of your environment.

Step 3: Activate the conda environment

Once the environment is created, you can activate it using the following command:


conda activate myenv


Step 4: Install PyTorch

With the conda environment activated, you can now install PyTorch using the following command:


conda install pytorch torchvision torchaudio cudatoolkit=11.1 -c pytorch -c conda-forge


This command will install the PyTorch library along with torchvision and torchaudio, as well as the necessary CUDA toolkit for GPU acceleration.

Step 5: Install Jupyter Notebook

If you haven’t already installed Jupyter Notebook, you can install it using the following command:


conda install jupyter


Step 6: Launch Jupyter Notebook

Once everything is installed, you can launch Jupyter Notebook by running the following command in the terminal:


jupyter notebook


After running the command, Jupyter Notebook will open in your default web browser, and you can start working on your PyTorch projects in a notebook environment.

By following these steps, you can easily install PyTorch in Jupyter Notebook and start developing deep learning applications with the power and flexibility of PyTorch, combined with the interactive environment of Jupyter Notebook.