DialoFlow This repository contains the code and pre-trained models for our ACL 2021 paper Conversations are not Flat: Modeling the Intrinsic Information Flow between Dialogue Utterances. We propose the DialoFlow, a new paradigm to construct the dynamic information flow in the dialogue history by addressing the semantic influence brought about by each utterance. Besides, we design an automatic reference-free evaluation metric Flow Score based on the pre-trained DialoFlow for interactive dialogue quality evaluation. DialoFlow We will release the code and […]

nerf-meta is a PyTorch re-implementation of NeRF experiments from the paper “Learned Initializations for Optimizing Coordinate-Based Neural Representations”. Simply by initializing NeRF with meta-learned weights, we can achieve: Environment Python 3.8 PyTorch 1.8 NumPy, imageio, imageio-ffmpeg Photo Tourism Starting from a meta-initialized NeRF, we can interpolate between camera pose, focal length, aspect ratio and scene appearance. The videos below are generated with a 5 layer only NeRF, trained for ~100k iterations. Your browser does not support the video tag.Your browser […]

AIPortfolio Logo Use AI, Modern Portfolio Theory, and Monte Carlo simulation’s to generate a optimized stock portfolio that minimizes risk while maximizing returns. How does it work? The app works by pulling the stock close data from the yahoo finance api. We then calculate the log returns and the volitility of the data to see what the overall trend for the stocks look like. We then generate random portfolio weights and use scipy to maximize a function that calculates the […]

ArtiStyle To quote authors Leon A. Gatys, Alexander S. Ecker, Matthias Bethge, “in light of the striking similarities between performance-optimised artificial neural networks and biological vision, our work offers a path forward to an algorithmic understanding of how humans create and perceive artistic imagery. The idea of Neural Style Transfer is taking a white noise as an input image, changing the input in such a way that it resembles the content of the content image and the texture/artistic style of […]

lucidmode lucidmode is an open-source, low-code and lightweight Python framework for transparent and interpretable machine learning models. It has built in machine learning methods optimized for visual interpretation of some of the most relevant calculations. Installation With package manager (coming soon) Install by using pip package manager: pip install lucidmode Clone entire github project [email protected]:lucidmode/lucidmode.git and then install dependencies pip install -r requirements.txt Models Artificial Neural Network Feedforward Multilayer perceptron with backpropagation. fit: Fit model to data predict: Prediction according […]

Geometric Vector Perceptron Implementation of equivariant GVP-GNNs as described in Learning from Protein Structure with Geometric Vector Perceptrons by B Jing, S Eismann, P Suriana, RJL Townshend, and RO Dror. This repository serves two purposes. If you would like to use the GVP architecture for structural biology tasks, we provide building blocks for models and data pipelines. If you are specifically interested in protein design as described in the paper, we provide scripts for training and testing models. Note: This […]

Federated Averaging (FedAvg) in PyTorch An unofficial implementation of FederatedAveraging (or FedAvg) algorithm proposed in the paper Communication-Efficient Learning of Deep Networks from Decentralized Data in PyTorch. (implemented in Python 3.9.2.) Implementation points Exactly implement the models (‘2NN’ and ‘CNN’ mentioned in the paper) to have the same number of parameters written in the paper. 2NN: TwoNN class in models.py; 199,210 parameters CNN: CNN class in models.py; 1,663,370 parameters Exactly implement the non-IID data split. Each client has at least […]

So-ViT This repository contains the source code under PyTorch framework and models trained on ImageNet-1K dataset for the following paper: @articles{So-ViT, author = {Jiangtao Xie, Ruiren Zeng, Qilong Wang, Ziqi Zhou, Peihua Li}, title = {So-ViT: Mind Visual Tokens for Vision Transformer}, booktitle = {arXiv:2104.10935}, year = {2021} } The Vision Transformer (ViT) heavily depends on pretraining using ultra large-scale datasets (e.g. ImageNet-21K or JFT-300M) to achieve high performance, while significantly underperforming on ImageNet-1K if trained from scratch. We propose […]

MLP Mixer – Pytorch An All-MLP solution for Vision, from Google AI, in Pytorch. No convolutions nor attention needed! Install $ pip install mlp-mixer-pytorch Usage import torch from mlp_mixer_pytorch import MLPMixer model = MLPMixer( image_size = 256, patch_size = 16, dim = 512, depth = 12, num_classes = 1000 ) img = torch.randn(1, 3, 256, 256) pred = model(img) # (1, 1000) Citations @misc{tolstikhin2021mlpmixer, title = {MLP-Mixer: An all-MLP Architecture for Vision}, author = {Ilya Tolstikhin and Neil Houlsby and […]

SMPLicit Implementation for the paper SMPLicit: Topology-aware Generative Model for Clothed People (CVPR 2021) Installation Follow these commands to install SMPLicit in your environment. The required libraries are standard, with the possible exception of Kaolin which requires a particular version to run with the current code. git clonehttps://github.com/ecorona/SMPLicit cd SMPLicit Install the dependencies listed in requirements.txt: pip install -r requirements.txt In particular, we use Kaolin v0.1 (see installation command) which should be easy to install. However, if you want to […]