Explore tweets tagged as #PyTorch
🤝 We’re thrilled to welcome @OpenTeams as a Diamond Sponsor for PyTorch Conference 2025. Since the early 2000s, founder Travis Oliphant released SciPy, NumPy, and Numba to the world. These became the bedrock of modern AI—and shook computing forever. It's time for an update. And
0
0
1
I'm building my own OpenCV from scratch - fastcv. fastcv is a C++ CUDA rewrite with Pytorch bindings of the image filters in the OpenCV library. I have already written two optimized kernels and will keep studying and implementing more. I have also added current benchmarks.
38
58
990
If you’re getting into PyTorch, give this a read. It discusses the usability, design patterns and implementation ideas behind the framework. A few bits and pieces that can help you build a good foundation.
19
116
1K
🌍 We’re proud to welcome the first-ever PyTorch Ambassadors! 💡 31 leaders 🗺️ 21 countries 🤝 5 continents They’ll host events, create content, and mentor new users to grow the PyTorch community worldwide. 👏 Meet the 2025 PyTorch Ambassadors: https://t.co/r1rfIw2uk6
4
16
79
لما نتكلم عن التعلم العميق (Deep Learning) فغالباً نتكلم عن الشبكات العصبية (NN) , ولكن حتى أغلبنا يستخدم شبكات عصبية جاهزة من مكتبات مثل PyTorch و Tensorflow . لكن تعرف أنه الأصل والبدايات والأفضل إذا كنت Software Developer أنك تبنيها بنفسك Node By Node والأفضل بلغة C++
8
16
352
Every time a new AI paper drops, he’s already halfway through its PyTorch repo. I think lucidrains has coded more papers than I’ve read.Truly goated 🐐
0
0
9
Taper is now performing 10x better than PyTorch for a simple CNN MNIST dataset training. It supports conv2d and maxpool now. M4 CPU only results - Taper(written in rust) - 96% accuracy in 660 seconds, 50 epochs. 13 second per epoch. ~4500 samples per epoch. PyTorch - ~500
11
26
315
I'm trying to implement an Autoencoder using PyTorch. I just spent 40 minutes figuring out why my code keeps giving me errors. Apparently the error was a stupid U I wrote in lowercase instead of uppercase. I don't think I'm ready for the developer life, how do you guys do it?!
4
0
11
Free Deep Learning with PyTorch Course to learn tensors, neural networks, CNNs, ResNets, and GANs etc. Link is in the comment.
2
10
87
lol i actually got fired from Tesla well the good news is i'm open for opportunities again :) at Tesla i was working on computer vision and RL. what i'm good at: - machine learning (pytorch, JAX..) - RL (GRPO, on VLAs and LLMs) - computer vision (openCV and 20 different closed
@crypt0x_0 Delete this before you get fired
403
213
6K
OpenAI創設メンバーで元TeslaのAI責任者だったKarpathyが、GPTをゼロから作る2時間の神動画を公開してるんだけど… 実際に小規模GPTをPyTorchで一から実装してて、しかも専門外の自分でもマジでかろうじて少しわかるように教えてくれる笑 これ詳しい人見たら大興奮なんだろうなー
1
314
3K
Pytorch is better than Tensorflow, I would recommend you to give it a try for Pytorch this is all you need:
0
0
4
#DeepLearning with PyTorch... 1) Cheat sheet [PDF]: https://t.co/TcRqfgqFOK 2) Learn fundamentals with hands-on coding [PDF]: https://t.co/IsXFjwVAhk 3) #GenerativeAI with Python and PyTorch: https://t.co/hfbERRk99u book v/ @PacktDataML
8
126
721
Computer Vision Projects. End-to-end project for healthcare imaging , using Pytorch and Monai . Link in comments 😎👇
4
98
717
Python’s power lies in its libraries. From NumPy and Pandas for data analysis, Matplotlib and Plotly for visualization, to TensorFlow, PyTorch, and Scikit-learn for machine learning—these tools turn ideas into real-world solutions. #Python #MachineLearning #DataScience #AI
4
1
5
pytorch consulting the math library heuristics which say transposing the matrix will yield a 30% speedup over the non-transposed case, deciding to transpose the matrix, and immediately running out of memory https://t.co/5fodHFSwFp
7
20
633
Today we are launching InferenceMAX! We have support from Nvidia, AMD, OpenAI, Microsoft, Pytorch, SGLang, vLLM, Oracle, CoreWeave, TogetherAI, Nebius, Crusoe, HPE, SuperMicro, Dell It runs every day on the latest software (vLLM, SGLang, etc) across hundreds of GPUs, $10Ms of
Going to be dropping something huge in 24 hours I think it'll reshape how everyone thinks about chips, inference, and infrastructure It's directly supported by NVIDIA, AMD, Microsoft, OpenAI, Together AI, CoreWeave, Nebius, PyTorch Foundation, Supermicro, Crusoe, HPE, Tensorwave,
104
129
2K