Pytorch implementation of convolutional neural network adversarial attack techniques
-
Updated
Dec 3, 2018 - Python
Pytorch implementation of convolutional neural network adversarial attack techniques
LatentDE: Latent-based Directed Evolution for Protein Sequence Design
CLIP GUI - XAI app ~ explainable (and guessable) AI with ViT & ResNet models
CLIP Interrogator, fully in HuggingFace Transformers 🤗, with LongCLIP & CLIP's own words and / or *your* own words!
Get CLIP ViT text tokens about an image, visualize attention as a heatmap.
Visualizing and interpreting features of CNN model
Submission for the Flipkart GRiD 2.0 hackathon under the track "Fashion Intelligence Systems"
Like a CLIP + VQGAN. Except without a VQGAN.
Use CLIP to create matching texts + embeddings for given images; useful for XAI, adversarial training
What do we learn from inverting CLIP models? And what does a CLIP 'see' in an image?
Image classifier which classifies MNIST database of handwritten digits 0-9 using 28x28 pixel images
OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning. + A closer look in PyTorch!
Classic original Inception style DeepDream, but with CLIP ResNet. And CLIP ViT for comparison.
Repo for working on the additional Machine Learning seminar tasks, year 2023-2024.
CLIP guiding self towards an image, from text prompt
Like Golden Gate Claude, but with a CLIP Vision Transformer ~ feature activation manipulation fun!
Gradient ascent and simulated annealing optimization algorithms for multivariate Gaussian space from scratch.
Add a description, image, and links to the gradient-ascent topic page so that developers can more easily learn about it.
To associate your repository with the gradient-ascent topic, visit your repo's landing page and select "manage topics."