Iacopo Poli

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Training neural networks with back-prop, feedback-alignment and direct feedback-alignment

Implementation of OctConv in Pytorch (https://arxiv.org/abs/1904.05049)

Experiments with Direct Feedback Alignment training scheme for DNNs

Scripts and instructions to install CUDA, cuDNN and the most common deep learning frameworks.

No description.

No description.

No description.

No description.

A high-throughput and memory-efficient inference and serving engine for LLMs

:bathtub: Clean Code concepts adapted for Python

Full-featured Jekyll port of Ghost's default theme Casper v2 👻

Deep Texture Encoding Network

JupyterLab computational environment.

PyTorch code for training neural networks without global back-propagation

A plug-in replacement for DataLoader to load ImageNet disk-sequentially in PyTorch.

Pytorch Cheatsheet

simple audio I/O for pytorch

code for the paper "Improved Techniques for Training GANs"

starter from "How to Train a GAN?" at NIPS2016

95.16% on CIFAR10 with PyTorch

Annotated notes and summaries of the TensorFlow white paper, along with SVG figures and links to documentation

Implement Decoupled Neural Interfaces using Synthetic Gradients in Pytorch

Training Deep Convolutional Networks on visual classification tasks

92.45% on CIFAR-10 in Torch

Easy benchmarking of all publicly accessible implementations of convnets

State Of The Art deep neural network models

3.8% and 18.3% on CIFAR-10 and CIFAR-100

Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Notes on Molecular Dynamics numerical methods

Physics, Algorithms and Statistics homeworks

No description.