From the course: Deep Learning: Model Optimization and Tuning

Setting up exercise files

From the course: Deep Learning: Model Optimization and Tuning

Start my 1-month free trial Buy for my team

Setting up exercise files

“

- [Instructor] In this video, we will set up the exercise files and the environment to use in this course. All course exercises are built using Python 3.8. We will be using Anaconda and Jupyter Notebooks, for these exercises. You can download and install Anaconda from the website anaconda.com/products/individual for your specific operating system. Once downloaded, we will go to the Anaconda UI. Here, we will create a new virtual environment called deep learning. By clicking the create button at the bottom and providing the name of the environment. The package we will use is Python 3.8. This may take some time to set up. The deep learning environment is set up now. We will now go back to home. Choose the deep learning environment on the top, and then install Jupyter Notebook for that environment. Jupyter Notebook is installed now for the deep learning environment. Open the command prompt window. Please note that if you're on Windows, you would want to use the Anaconda command prompt for the same. The exercise files for this course have been downloaded to the folders users, LinkedIn, documents, exercise files. Please download exercise files on your computer on a similar folder. Navigate to this folder on the command prompt, we can explore these files from the command prompt. Now let's activate the new virtual environment we created using the command conda activate deep learning. Then, we can start the Jupyter Notebook server using the command Jupyter Notebook. Please make sure that you are in the same folder as the exercise files are before using the command. This command then opens up the Jupyter Notebook in your browser. The exercise files and the data files can be seen in the root directory. You will use these files in the later exercises. In the next chapter, we will discuss the basics of deep learning optimization.

Contents