distillpub / post--activation-atlas
Using feature inversion to visualize millions of activations from an image classification network, we create an explorable activation atlas of features the network has learned which can reveal how the network typically represents some concepts.
☆43Updated 4 years ago
Related projects: ⓘ
- ☆25Updated 5 years ago
- Odds and Ends and Things I've implemented.☆78Updated 5 years ago
- torch code to decode (and almost encode) latents from art-DCGAN's Portrait GAN☆40Updated 5 years ago
- This repository is created to show the Neural Arithmetic Logic Unit implementation in python using Tensorflow. The code in this repo comp…☆43Updated 6 years ago
- PyTorch implementation of CVPR'18 - Perturbative Neural Networks http://xujuefei.com/pnn.html☆57Updated 5 years ago
- A lightweight library for tensorflow 2.0☆66Updated 4 years ago
- Here I will share the code from the lectures of the course: Generative Image Modelling with Deep Neural Networks taught in the Summer Ter…☆26Updated 7 years ago
- presentations☆44Updated 5 years ago
- Notes from ICLR 2019☆24Updated 5 years ago
- Synthetic book pages created with a PGGAN☆73Updated 5 years ago
- Binary Stochastic Neurons in PyTorch☆56Updated 6 years ago
- Code for "Aggregated Momentum: Stability Through Passive Damping", Lucas et al. 2018☆34Updated 5 years ago
- The Singular Values of Convolutional Layers☆71Updated 5 years ago
- The Building Blocks of Interpretability☆87Updated last year
- ☆73Updated 4 years ago
- Plugging TensorBoard in an autoencoder on the MNIST dataset for demonstrating t-SNE embeddings visualization of unsupervised machine lear…☆71Updated 5 years ago
- Code for the paper "Learning sparse transformations through backpropagation"☆42Updated 4 years ago
- Implementation of "Learning with Random Learning Rates" in PyTorch.☆102Updated 4 years ago
- ☆27Updated last year
- Equi-normalization of Neural Networks☆115Updated 5 years ago
- BOLD5000: Brain, Object, Landscape Dataset☆30Updated 5 years ago
- ☆77Updated 8 years ago
- Yes you GAN!☆34Updated 2 years ago
- Generative Adversarial Interpolative Autoencoder (GAIA) is a Generative Adversarial Network (GAN) made up of Autoencoders (AE) trained ex…☆77Updated 5 years ago
- Implements an infinite sum of poisson-weighted convolutions☆26Updated 6 years ago
- Implementation of "GANs for Biological Image Synthesis"☆95Updated 6 years ago
- Probabilistic classification in PyTorch/TensorFlow/scikit-learn with Fenchel-Young losses☆183Updated last year
- ☆105Updated this week
- ☆32Updated 6 years ago
- ☆36Updated 5 years ago