Pierre-Antoine

Computer vision engineer

[Alister @SchnockRevue]

Le franchouille "YMCA" (signé par nos compatriotes Henri Belolo et Jacques Morali) d'office pour célébrer Trump.
Hymne gay par excellence devenu le parangon du MAGA.
On est bien, Tintin.
#VillagePeople

[Soumith Chintala @soumithchintala]

can @huggingface quickly start a Twitter clone for AI/ML folks 🤪

[Pierre-Antoine @trypag]

@JoshWComeau I just noticed ARIA links are broken in the breadcrumbs lesson (last two links of the page actually). Thanks for your nice work :)

[Pierre-Antoine @trypag]

@TobiasCornille @SegmentsAI @huggingface @NielsRogge The latency seems really small, can you share some details about the tech stack (api, model serving) ? nice job !

[Pierre-Antoine @trypag]

@PierreFillard Merci pour le partage, bien sympa de suivre les progrès technos de plusieurs années en quelques minutes.

[Pierre-Antoine @trypag]

@matthieurouif @GooglePlay voted ;)

[Pierre-Antoine @trypag]

Best. Blog. Ever.

[Lilian Weng @lilianweng]

Training large models demands a lot of GPU memory and a long training time. With several training parallelism strategies and a variety of memory saving designs, it is possible to train very large neural networks across many GPUs.

https://t.co/Rlla5ABfG2

[Pierre-Antoine @trypag]

@abursuc 😬 courage

[Lilian Weng @lilianweng]

Contrastive learning aims to learn representation such that similar samples stay close, while dissimilar ones are far apart. It can be applied to supervised / unsupervised data and has been shown to achieve good results on various tasks.

📚 A long read: https://t.co/TZiaVA0qNS

[Simon Kuestenmacher @simongerman600]

Video shows how high you would be able to jump on each planet. This includes (!) Pluto where our spaceman friend can jump really high. Source: https://t.co/TgDn5eozwQ

[Yann N. Dauphin @ynd]

An empirical study on the regularization effects of Batch Normalization. We find that preventing explosive growth at the final layer at initialization and during training can recover a large part of BatchNorm’s regularization boost. https://t.co/uUIdIfhvMe

[Pierre-Antoine @trypag]

@ptrblck_de @NVIDIAAI @soumithchintala @PyTorch 100% deserved 👍 thanks to the discuss grandmaster

[Pierre-Antoine @trypag]

@raydistributed @Hydra_Framework dead link

[Pierre-Antoine @trypag]

@leboncoin pourquoi vous refusez systématiquement mes annonces ?

[Pierre-Antoine @trypag]

Automatic Mixed Precision (AMP) is now a native feature of PyTorch. https://t.co/WSPiwzDuiD

[Pierre-Antoine @trypag]

@omarsar0 Handling sequences ! BTT

[Pierre-Antoine @trypag]

@deanwampler @deanwampler I've heard of you through the scala community first, then again through Ray. My question : how do you manage to code in multiple languages ? I am struggling to remember js after small periods of interruption with Python.

[François Fleuret @francoisfleuret]

I have five open PhD positions in deep ml @unige_en

https://t.co/uTPFETqwZ7

Please apply or circulate!

[Pierre-Antoine @trypag]

@streamlit wow, clearly deserved, there is a huge potential and market for it !

[#DataXDay @DataXDay]

On commencera la journée avec @trypag Co-founder de @radiostic et Data Scientist qui animera le talk :

"Toute la vérité sur l'utilisation du #DeepLearning en imagerie médicale"

Pour ne pas manquer ça... rendez-vous à 13h ici 👉 https://t.co/6XmmTLob1s
#DataScience #Data