Open in app

Sign In

Write

Sign In

Francesco Zuppichini
Francesco Zuppichini

1.6K Followers

Home

About

Published in Towards Data Science

·Pinned

Implementing RepVGG in PyTorch

Make your CNN >100x faster — Hello There!! Today we’ll see how to implement RepVGG in PyTorch proposed in RepVGG: Making VGG-style ConvNets Great Again Code is here, an interactive version of this article can be downloaded from here. Let’s get started! The paper proposed a new architecture that can be tuned after training to make…

Python

5 min read

Implementing RepVGG in PyTorch
Implementing RepVGG in PyTorch
Python

5 min read


Published in Towards Data Science

·Pinned

Implementing SegFormer in PyTorch

A fast, efficient, and lightweight model for image segmentation — Hello There!! Today we’ll see how to implement SegFormer in PyTorch proposed in SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. Code is here, an interactive version of this article can be downloaded from here. Let’s get started! The paper proposes a new transformer-based model to tackle image…

Deep Learning

6 min read

Implementing SegFormer in PyTorch
Implementing SegFormer in PyTorch
Deep Learning

6 min read


Published in Towards Data Science

·Pinned

Implementing ConvNext in PyTorch

A new convnet that beats transformers — Hey, I am on LinkedIn come and say hi 👋 Hello There!! Today we are going to implement the famous ConvNext in PyTorch proposed in A ConvNet for the 2020s . Code is here, an interactive version of this article can be downloaded from here. Let’s get started! The paper…

Deep Learning

5 min read

Implementing ConvNext in PyTorch
Implementing ConvNext in PyTorch
Deep Learning

5 min read


Published in Towards Data Science

·Pinned

Distilling Transformers: (DeiT) Data-efficient Image Transformers

transformers go brum brum Hi guys! Today we are going to implement Training data-efficient image transformers & distillation through attention a new method to perform knowledge distillation on Vision Transformers called DeiT. You will soon see how elegant and simple this new approach is. Code is here, an interactive version…

Deep Learning

4 min read

Distilling Transformers: (DeiT) Data-efficient Image Transformers
Distilling Transformers: (DeiT) Data-efficient Image Transformers
Deep Learning

4 min read


Published in Towards Data Science

·Pinned

Implementing Vision Transformer (ViT) in PyTorch

I am on LinkedIn, come and say hi 👋 Hi guys, happy new year! Today we are going to implement the famous Vi(sion) T(ransformer) proposed in AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE. Code is here, an interactive version of this article can be downloaded…

Artificial Intelligence

6 min read

Implementing VisualTtransformer in PyTorch
Implementing VisualTtransformer in PyTorch
Artificial Intelligence

6 min read


2 days ago

Is PyTorch 2.0 faster?

Benchmark the new PyTorch 2.0 model.compile Hey, I am on LinkedIn come and say hi 👋 code is here TL;DR Yes, it makes inference faster by around 22%. I still need to test it during training, but I think it will be similar. Introduction PyTorch 2.0 is out, let's see how fast…

Deep Learning

3 min read

Is PyTorch 2.0 faster?
Is PyTorch 2.0 faster?
Deep Learning

3 min read


Mar 1

How to use ChatGPT APIs in Python 🤖🐍

Hey, I am on LinkedIn come and say hi 👋 Code is here OpenAI ChatGPT APIs are out! They open a new endless possibilities. Today we’re going to see how to use them in Python Setup Get an API key Log into OpenAI website and, if you are not on the free tier, add a…

Programming

3 min read

How to use ChatGPT with Python 🤖🐍
How to use ChatGPT with Python 🤖🐍
Programming

3 min read


Published in Towards AI

·Oct 26, 2022

Non Max Suppression (NMS) in PyTorch

I am on LinkedIn, come and say hi 👋 Today we’ll see how to implement non max suppression in PyTorch The code is here, and an interactive version of this article can be found here Preambula If you are doing computer vision (especially object detection), you know what non max suppression…

Data Science

4 min read

Non Max Suppression (NMS) in PyTorch
Non Max Suppression (NMS) in PyTorch
Data Science

4 min read


Apr 14, 2022

Loading Huge PyTorch Models with Linear Memory Consumption

Hello There! Code is here Today we will see how to load a Pytorch model with linear memory consumption. Loading a model takes 2x memory space. Let’s see why: First, we need a model: Upon creation, the model takes 1x memory, where x is its size At some…

Machine Learning

3 min read

Loading Huge PyTorch Models with Linear Memory Consumption
Loading Huge PyTorch Models with Linear Memory Consumption
Machine Learning

3 min read


Published in Towards Data Science

·Feb 7, 2022

Implementing Stochastic Depth/Drop Path In PyTorch

DropPath is available in glasses my computer vision library — Code is here an interactive version of this article can be downloaded from here. Introduction Today we are going to implement Stochastic Depth also known as Drop Path in PyTorch! Stochastic Depth introduced by Gao Huang et al is a technique to “deactivate” some layers during training. We’ll stick with DropPath. …

Computer Vision

5 min read

Implementing Stochastic Depth/Drop Path In PyTorch
Implementing Stochastic Depth/Drop Path In PyTorch
Computer Vision

5 min read

Francesco Zuppichini

Francesco Zuppichini

1.6K Followers

Computer Vision Engineer @ 🤗

Following
  • Sik-Ho Tsang

    Sik-Ho Tsang

  • Hassan Djirdeh

    Hassan Djirdeh

  • Soner Yıldırım

    Soner Yıldırım

  • Benjamin Sledge

    Benjamin Sledge

  • Marc Lalonde

    Marc Lalonde

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech