#pytorch articles

CPChai Planetthe-tech-inside.hashnode.devJul 26 · 13 min read

How Neo Builds His Own Transformer: A Matrix Story

Act I: The Construct Inside the training construct, rain falls in sheets of green code. Neo stands before a floating terminal, his fingers hovering over glowing symbols. Trinity watches from the shado

0

WKWesam Khallafpytorchfromgroundup.hashnode.devJul 26 · 7 min read

What Does `keepdim` Do in PyTorch? (And the Silent Bug When You Forget It)

You wrote x.sum(dim=1) to get a row total, divided the original tensor by it, and either got RuntimeError: The size of tensor a (3) must match the size of tensor b (2) — or, worse, got no error at all

0

WKWesam Khallafpytorchfromgroundup.hashnode.devJul 22 · 8 min read

What Does `unsqueeze` Do in PyTorch? (And Why Your Model Keeps Asking For It)

You passed a single image to your model and got ValueError: expected 4D input (got 3D input). Someone on Stack Overflow said "just add .unsqueeze(0)" — and it worked. But nobody explained what it did,

0

MSManu Shuklaecorpit.hashnode.devJul 18 · 13 min read

PyTorch 2.13 on Apple Silicon: FlexAttention is up to 12x faster than SDPA

PyTorch 2.13 on Apple Silicon: FlexAttention is up to 12x faster than SDPA Summary. PyTorch 2.13, released around July 11, 2026, brings FlexAttention to Apple Silicon through the Metal (MPS) backend,

0

MSManu Shuklaecorpit.hashnode.devJul 18 · 12 min read

PyTorch 2.13 brings FlexAttention to Apple Silicon: a 12x sparse-attention speedup

PyTorch 2.13 brings FlexAttention to Apple Silicon: a 12x sparse-attention speedup Summary. PyTorch 2.13 shipped on July 8, 2026, and for anyone training or running models on a Mac the headline is one

0

WKWesam Khallafpytorchfromgroundup.hashnode.devJul 17 · 5 min read

Reshape vs View in PyTorch: What's the Difference (and When `view()` Breaks)

You called .view() on a tensor, got a RuntimeError: view size is not compatible with input tensor's size and stride, switched to .reshape(), and it just... worked. So what's actually going on — and wh

2

M

RRishikantrishiii2.hashnode.devJul 8 · 6 min read

AeroGuard AI: Transcending Convolutional Architectures in Drone Surveillance

Building an autonomous, military-grade drone surveillance system introduces a specific class of problems that standard computer vision tutorials rarely cover. The project, codenamed AeroGuard AI, was

0

RRishikantrishiii2.hashnode.devJul 3 · 8 min read

Revolutionizing 5G Networks with Intelligent Reconfigurable Surfaces and Deep Reinforcement Learning

The transition to fifth generation cellular networks marks one of the most significant leaps in telecommunications history. Unlike previous generations that relied heavily on sub six gigahertz frequen

0

SCSiddharth Chaudharyblog.siddharthchaudhary.com.npJul 2 · 14 min read

How Neural Networks Learned to Remember — RNNs, LSTMs, and GRUs

It’s an afternoon of a beautiful summer day. You just learnt about backpropagation, gradients and artificial neural networks and you think you’ve unlocked some forbidden treasure of knowledge granted

0

AGAlper GÖÇENinsideaimodels.hashnode.devJun 29 · 2 min read

Free from-scratch deep learning notes: tensors, attention, and a tiny GPT

I'm an AI PhD student, and I have started writing a free public notebook on how AI models work under the hood: https://insideaimodels.com/ The goal is to make the mechanics easier to reason about, wit

0

#pytorch

Search Hashnode