<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>PyTorch on somewhere/nowhere</title>
    <link>https://www.scottpoulton.com/categories/pytorch/</link>
    <description>Recent content in PyTorch on somewhere/nowhere</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 30 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.scottpoulton.com/categories/pytorch/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Project Log 4</title>
      <link>https://www.scottpoulton.com/posts/project-log-004-tensors/</link>
      <pubDate>Mon, 30 Mar 2026 00:00:00 +0000</pubDate>
      
      <guid>https://www.scottpoulton.com/posts/project-log-004-tensors/</guid>
      <description>Tensors, Transfer Learning, and Apple Silicon In Log 3, I mapped out the problem: processing 3GB .svs Whole Slide Images to predict melanoma organ tropism. The reality? Trying to build the complex tiling logic and the neural network architecture at the exact same time on a local machine is a recipe for a crashed Mac and zero progress.
It was time for a strategic pivot.
The MVP Pivot: SPIDER-Skin Instead of wrestling gigapixel monsters, I bypassed the tiling phase entirely to unblock the MVP.</description>
    </item>
    
  </channel>
</rss>
