The Mustache Movement
summary
Demonstrates a working GAN built from existing Python modules (TensorFlow/PyTorch and numpy/scikit‑learn) trained on 8,000 celebrity images to learn “mustache‑ness.” The pipeline uses a 3‑layer convolutional generator and discriminator producing 128×128×3 color outputs from random noise, yields synthetic faces with plausible mustaches that start odd then improve, and applies the generator as an inpainting step to add mustaches to women’s photos.
AI-written summary · about
chapters (29)
- 0:00Introduction
- 1:00Aerial Networks
- 1:30The Objective
- 2:00The generative adversarial network
- 3:30The generator
- 4:00The generator is trained
- 5:00The mustache
- 6:30Zerosum game
- 7:00Celebrity database
- 7:30Training the generator
- 8:00Handwritten digits
- 9:00Two people playing chess
- 13:00Is it real
- 14:00Code
- 16:00Mustaches
- 19:00Mustache List
- 21:00Questions
- 21:30Random Noise
- 22:00Feedback Loop
- 22:30Real Pictures
- 23:00Massage
- 23:30Generate
- 24:00Bit Fill
- 24:30How many pictures
- 25:30If it was already detected
- 26:00The forger wouldnt learn
- 27:00Faces are faces of men
- 27:30All faces have a moustache
- 28:00This is a woman
related talks
20mA Girls Guide To Growing A Moustache with Python
01h 27mMaking Faces: Conditional Generation of Faces using GANs...
15mDrag Makeovers, via AI!
37mHarnessing the power of Generative Adversarial Networks (GANS) for supervised learning
06mGAN-based Style Transformation to Improve Gesture-recognition Accuracy
18mDance of the Ancestors...
03mBuilding artificial people: Endless possibilities and the dark side
56mDeep Fakes 2.0 - How Neural Networks are Changing our World