The PyTorch Ecosystem continues to grow with projects that improve performance, scalability, and developer workflows across training, inference, AI infrastructure, and scientific machine learning.
Our latest ecosystem update highlights new additions including FlagGems, Kubeflow Trainer, LMCache, DeepInverse, Feast, NeuralOperator, PINA, and verl. It also spotlights sc2bench, a project under consideration that could benefit from broader community review and contributions.
🔗 hubs.la/Q03Yql100
#PyTorch #OpenSource #AIInfrastructure #MachineLearning
2
12
65
8,979
13 Nov 2025
▶️ We created a 1-hour live-coding tutorial to get started in imaging problems with AI, using the deepinverse library
youtu.be/YRJRgmXV8_I?si=VX8y…
6
316
13 Nov 2025
DeepInverse
A PyTorch library for solving imaging inverse problems using deep learning.
github.com/deepinv/deepinv
5
19
2,112
5 Nov 2025
💥 DeepInverse is now part of the official PyTorch Landscape💥
We are excited to join an ecosystem of great open-source AI libraries, including @huggingface diffusers, MONAI, @kornia_foss , einops, etc.
DeepInverse has joined the PyTorch Ecosystem, making imaging with deep learning easier and more reproducible across research and industry.
DeepInverse is an open source framework for solving imaging inverse problems in medical imaging, computational photography, remote sensing, astronomical imaging, microscopy and more. DeepInverse makes imaging with deep learning easy and is developed by a passionate community of researchers, practitioners and engineers.
🔗 Learn more & explore how to get involved: hubs.la/Q03RKyHJ0
#PyTorch #OpenSourceAI #DeepInverse #Imaging #DeepLearning
1
2
6
541
DeepInverse has joined the PyTorch Ecosystem, making imaging with deep learning easier and more reproducible across research and industry.
DeepInverse is an open source framework for solving imaging inverse problems in medical imaging, computational photography, remote sensing, astronomical imaging, microscopy and more. DeepInverse makes imaging with deep learning easy and is developed by a passionate community of researchers, practitioners and engineers.
🔗 Learn more & explore how to get involved: hubs.la/Q03RKyHJ0
#PyTorch #OpenSourceAI #DeepInverse #Imaging #DeepLearning
2
12
87
13,232
10 Sep 2025
☀️ Just wrapped up the DeepInverse Hackathon!
We had 30 imaging scientists from all over the world coding during 3 days next to the beautiful Calanques in Marseille, France. It was a great moment to meet new people, discuss science, and code new imaging algorithms!
1
4
241
20 Aug 2025
🔬 Are you working in computational imaging or interested in learning?
📖 DeepInverse just released a new 5-minute quickstart tutorial
deepinv.github.io/deepinv/au…
which gets you started developing AI models for reconstructing images!
1
2
4
347
16 Apr 2025
All of this is possible thanks to deepinverse (deepinv.github.io/), which allows us to seamlessly train on a large set of acquisition physics.
1
2
71
14 Apr 2025
🚢🚢 deepinv v0.3.0 is here, with many new features! 🚢 🚢
Our passionate team of contributors keeps shipping more exciting tools!
Deepinverse (deepinv.github.io/) is a library for solving imaging inverse problems with deep learning.
1
4
12
397
1 Jan 2025
Summer School's Hands-On Tutorials
💻DeepInverse: A PyTorch Library for Imaging Inverse Problems
🎓By @TachellaJulian (ENS Lyon) @MatthieuTerris (Inria) @HuraultSamuel (CNRS)
📡Build Your Own Radar With MIT’s Next-Generation Kit
🎓By Brad Perry & Ken Kolodziej, MIT Lincoln Lab
4
6
441
26 Nov 2024
Not coming back from Marseille empty handed #DeepInverse @TachellaJulian @MatthieuTerris @ddongchen @minhhai712
4
20
1,005
26 Nov 2024
@TachellaJulian, chercheur @CNRS au @lpensl (🤝@CNRS @ENSdeLyon 📍 @CNRS_dr07) est espoir de la catégorie « Documentation » du prix de la science ouverte du logiciel libre de la recherche pour le développement de la bibliothèque DeepInverse.
1
2
3
413
26 Nov 2024
Toutes nos félicitations aux deux espoirs des prix science ouverte du logiciel libre de la recherche qui travaillent dans des laboratoires rattachés à @CNRSphysique : @TachellaJulian (DeepInverse) et Sébastien Weber (PyMoDAQ) 👏
Pour en savoir plus ⤵️
inp.cnrs.fr/fr/cnrsinfo/deep…
1
6
7
834
2 Nov 2024
Day 2: Hands-on Lectures
▶️Track 1: "Build Your Own Radar with MIT’s Next-Generation" Kit by Bradley Perry and Ken Kolodziej
▶️Track 2: "DeepInverse: A PyTorch Library For Solving Imaging Inverse Problems With Deep Learning" by @TachellaJulian @MatthieuTerris
@HuraultSamuel
1
1
2
255
30 Oct 2024
🚀 deepinverse hackathon🚀
We just finished a couple of days working on deepinverse in the beautiful CIRM venue.
deepinv.github.io/deepinv/
Immensely grateful to the dream team of contributors that participated in the hackathon!
A thread 🧵
2
7
26
1,631
17 Oct 2024
@MatthieuTerris, @HuraultSamuel and I will be giving a tutorial on deepinverse in Luxembourg next year!
the symposium has a great lineup of speakers!
17 Oct 2024
𝗔𝗻𝗻𝗼𝘂𝗻𝗰𝗶𝗻𝗴 𝘁𝗵𝗲 𝗜𝗦𝗖𝗦 𝟮𝟬𝟮𝟱 𝗦𝘆𝗺𝗽𝗼𝘀𝗶𝘂𝗺 𝗮𝗻𝗱 𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽!
The Call for Papers for the 2025 𝗜𝗻𝘁𝗲𝗿𝗻𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝗦𝘆𝗺𝗽𝗼𝘀𝗶𝘂𝗺 𝗼𝗳 #𝗖𝗼𝗺𝗽𝘂𝘁𝗮𝘁𝗶𝗼𝗻𝗮𝗹𝗦𝗲𝗻𝘀𝗶𝗻𝗴 (ISCS2025.com) is now available!
2
10
446
14 Oct 2024
The Unknown Noise level SURE (UNSURE) loss is now part of deepinverse:
deepinv.github.io/deepinv/st…
Just set 'unsure=True' in your standard SURE loss and the noise level will get tuned automatically.
a jupyter notebook demo here: deepinv.github.io/deepinv/au…
1
1
32
2,072
20 Sep 2024
It is always nice to be back in Edinburgh!
I presented UNSURE
slides: tachella.github.io/assets/pd…
paper: arxiv.org/abs/2409.01985
and of course deepinverse:
deepinv.github.io/deepinv/
2
2
35
1,350
12 Jun 2024
Here are the google colab files that we covered in yesterday deepinverse tutorial:
Intro to forward operators:
colab.research.google.com/dr…
Variational methods and Implicit priors (PnP and RED): colab.research.google.com/dr…
Unrolled networks:
colab.research.google.com/dr…
11 Jun 2024
Will the sessions be recorded? If yes, can you please share the link?
1
8
40
5,060
10 Jun 2024
Tomorrow we are giving a deepinverse computational imaging tutorial in Bologna, Italy, with fellow deepinverters @HuraultSamuel @MatthieuTerris @ddongchen
site.unibo.it/mathematical-m…
2
5
29
1,946