Handmade Dataset Experiments

Handmade Dataset Experiment #1: Generating Images

8% of your grade

Part I: Gathering Training Data:

Option 1:

Go for a walk. Look for a specific chosen shape (heart, letter A, circle, etc). You will begin to notice it everywhere: stamped on plastic trash, faded on cardboard boxes, spray-painted on brick walls, printed on food wrappers, or glowing on storefront signs.

  1. Take at least 300 photos of this character.
  2. Get close. Frame each shot so the character sits directly in the center and takes up most of the frame. Your images will eventually be cropped to be square so just keep that in mind.
  3. If you took these on your phone, transfer all 300 photos to your laptop before class next week.

Option 2:

Find a continuous movement (clouds drifting, a patch of sunlight across your floorboards, or an ice cube melting, etc.) and set up your phone/camera in such a way to film it. You will then split this video into ~300 frames to use as training images.

  1. Prop your camera up securely (using a small tripod, a phone stand, or a steady stack of books) and record the movement for about half an hour.
  2. Ideally, your subject matter is pretty homogenous. You don’t want a bunch of random stuff happening in the background. For example, if you are filming a leaf shaking in the wind, it would be better if the leaf was against a plain wall rather than with a whole park scene in the background.
  3. Convert your video to images using ->How to convert video to images in Adobe Media Encoder
  4. Have this video file and images on your laptop before class next week.

Part II

  1. Using the demo from class, finish training your GAN model. You may opt for the pix2pix version instead of the lightweight GAN. Up to you. But be ready to share results with the class next week.

Handmade Dataset Experiment #2: Generating Text

8% of your grade

Part I: Gathering Data

Option 1:

  1. Use text you’ve already written for school or personal creative writing.
  2. Your combined text file must be about 2,000 words long. (For example, if one essay isn't long enough, copy and paste two or three of your past papers into the same file).
  3. Bring your .txt file to class.

Option 2:

  1. Open your email spam folder. Copy the text of 20 to 30 spam emails/texts and paste them into a single plain text file (.txt).
  2. Your combined text file must be about 2,000 words long.
  3. Bring your .txt file to class.

Option 3:

  1. Go to your local Craigslist "Missed Connections" page (or a similar public, anonymous forum where strangers post short messages). Copy and paste these anonymous posts into a single text file (.txt) until you reach 2,000 words.
  2. Bring your .txt file to class.

Part II

  1. Using the demo from class, finish training your text model. Be ready to share results with the class next week.

Handmade Dataset Experiment #3: Generating Sound

8% of your grade

Part I: Gathering Data

Option 1:

  1. Record a routine noise with your phone or a recording device. For example, as you do work for another class on your computer, you could record the sound of your own typing. You could record yourself chopping vegetables.
  2. Try to get at least 2 hours of audio total.
  3. Try to reduce the amount of background/extraneous noise
  4. Move the audio from the phone/device to your laptop before next class.

Option 2:

  1. Record your own voice. You could be reading a text aloud, talking to someone, singing, or humming.
  2. Try to get at least 2 hours of audio total.
  3. Try to reduce the amount of background/extraneous noise
  4. Move the audio from the phone/device to your laptop before next class.

Option 3:

  1. If you play an instrument, record yourself playing it in a relatively quiet room.
  2. Try to get at least 2 hours of audio total.
  3. Try to reduce the amount of background/extraneous noise
  4. Move the audio from the phone/device to your laptop before next class.

Part II

  1. Using the demo from class, finish training your audio model. Be ready to share results with the class next week.