Assignment: Creating a Dataset/Computing with Tensorflow
This first homework assignment is contained in the session-1.ipynb notebook file. If you are unsure of how to use notebook, please first follow the installation instructions.
And follow the instructions on getting notebook running.
Then come back here and work through the notebook session-1.ipynb. This will guide you through working with a small dataset of images. For Part 1, you'll need to find 100 images and use the function I've provided to create a montage of your images, saving it to the file "dataset.png" (template code provided below). You can load an existing dataset of images, find your own images, or perhaps create your own images using a creative process such as painting, photography, or something along those lines. Each image will be reshaped to 100 x 100 pixels. There needs to be at least 100 images. For Parts 2 and 3, you'll then calculate the mean and deviation of it using a tensorflow session. In Part 4, you'll normalize your dataset using the mean and deviation. Then in Part 5, you will convolve your normalized dataset. For Part 6, you'll need to sort the entire convolved dataset. Finally, the last part will package everything for you in a zip file which you can upload to Kadenze to get assessed (only if you are a Kadenze Premium member, $10 p/m, includes online portfolio and more). Remember to complete the additional exercises online, including the Gallery participation and the Forum post. If you have any questions, be sure to enroll in the course and ask your peers in the #CADL community or me on the forums!
https://www.kadenze.com/courses/creative-applications-of-deep-learning-with-tensorflow/info
- Comment on 1 student's open-ended arrangement (Part 6) in the course gallery titled "Creating a Dataset/ Computing with Tensorflow". Think about what images they've used in their dataset and how the arrangement reflects what could be represented by that data.
- Finally make a forum post in the forum for this assignment "Creating a Dataset/ Computing with Tensorflow".
- Including a link to an artist making use of machine learning to organize data or finding representations within large datasets
- Tell a little about their work (min 20 words).
- Comment on at least 2 other student's forum posts (min 20 words)
If you have any questions, be sure to enroll in the course and ask your peers in the #CADL community or me on the forums!
https://www.kadenze.com/courses/creative-applications-of-deep-learning-with-tensorflow/info