Top all-time · #1660
Paperspace by DigitalOcean Blog
Company blog · blog.paperspace.comaidataprogramming
Paperspace by DigitalOcean Blog is the company blog at blog.paperspace.com, writing about ai, data and programming. Since 2016, 44 different Hacker News readers have linked it 152 times, most often “Image Super-Resolution: A Comprehensive Review”. The last post was in 2024, but the archive is still widely read.
Too few sampled comments (14) to say how often HN recommends it.?
Why HN links it
HN readers link the Paperspace blog for machine learning and GPU cloud content, such as a YOLO object detection intro, Volta GPU instance news, and guides on PyTorch, DALL-E and model monitoring.
Summarised by Claude from a sample of 14 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Tutorials, sample apps, and more created by the Paperspace internal research team and community
Most-linked posts?
- Image Super-Resolution: A Comprehensive Review3 people · 3 mentions · first linked 2020-09-11
- Adversarial Autoencoders with Pytorch3 people · 3 mentions · first linked 2017-03-20
- How to implement a YOLO (v3) object detector from scratch in PyTorch3 people · 3 mentions · first linked 2018-04-19
- Interview with TikTok Deep Faker Jesse Richards2 people · 3 mentions · first linked 2020-08-28
- Channel Attention and Squeeze-and-Excitation Networks (SENet)2 people · 2 mentions · first linked 2020-09-21
- How JavaScript Libraries Are Training Neural Networks on Web Browsers2 people · 2 mentions · first linked 2020-11-06
- A 2020 Guide to Synthetic Media – DeepFakes, Virtual Avatars and More2 people · 2 mentions · first linked 2020-01-30
- Understanding Dimension Reduction with Principal Component Analysis2 people · 2 mentions · first linked 2017-12-14
- /tesla-v100-available-today/2 people · 2 mentions · first linked 2017-10-26
- Building a Double Deep Q-Network to Play Super Mario Bros2 people · 2 mentions · first linked 2020-09-03
What Hacker News says?
Having worked with YOLO, I really recommend this intro: https://blog.paperspace.com/how-to-implement-a-yolo-object-d... . And in general, YOLO is performant and at the same time, it has a simpler architecture than the Fast(er) R-CNN family. And in general, due to its head, it is WAY more readable in PyTorch than in TensorFlow; to the point, I use it as an example in Keras vs PyTorch example https://deepsense.ai/kera…
Comment linking /how-to-implement-a-yolo-object-detector-in-pytorch/
on “YOLO: Real-Time Object Detection”Submitted Shareable Jupyter Notebooks That Run on Free Cloud GPUs as a story · 199 points
HN discussionOne other thing: Your onboarding flow at the paperspace blog still points to parsec.tv. It made me wonder if you went out of business until I found the new download links. https://blog.paperspace.com/setting-up-your-cloud-gaming-rig...
Comment linking /setting-up-your-cloud-gaming-rig-with-paperspace-parsec/
on “Run your own high-end cloud gaming service on EC2 (2015)”Submitted Reproducible machine learning with PyTorch and Quilt as a story · 135 points
HN discussionLooks like Paperspace announced Volta support yesterday: https://blog.paperspace.com/tesla-v100-available-today/ One nice thing here is you can do monthly plans instead of reserved on AWS which is a minimum $8-17k upfront. Really great to see the cloud providers adopting modern GPUs.
Comment linking /tesla-v100-available-today/
on “Introducing Amazon EC2 P3 Instances”Submitted Building a State of the Art Bacterial Classifier with Fast.ai and Paperspace as a story · 112 points
HN discussionPaperspace offers such a service, though I've only ever used it with a Windows server and Linux client: https://blog.paperspace.com/setting-up-your-cloud-gaming-rig... I haven't checked recently, but the blog post claims it works with all games.
Comment linking /setting-up-your-cloud-gaming-rig-with-paperspace-parsec/
on “GeForce Now: A Review”Submitted Building a CT Scan Covid-19 Classifier Using PyTorch as a story · 66 points
HN discussionWow LFE is really cool, thanks for showing me another new thing! Admittedly I got pretty depressed about the lack of progress on this stuff and kinda checked out over the years. So my knowledge has gaps since the 90s. - I'll use this as an excuse to talk about another learning model besides NNs and GAs: Boltzmann Machines (BMs). For anyone unfamiliar with them, they can be thought of as a temperature minimization or…
Comment linking /beginners-guide-to-boltzmann-machines-pytorch/
on “WebMonkeys: parallel GPU programming in JavaScript (2016)”Submitted How to Train a Scaled-YOLOv4 Object Detection Model as a story · 44 points
HN discussionTransfer learning to emulate artistic style [0] has been around for the better part of a decade and has had zero impact on artists’ livelihoods. People consume art because they enjoy admiring the human talent that creates it, celebrating that some individuals are capable of extraordinary feats the vast majority of people are incapable of. It’s the same reason people watch sports—they enjoy admiring the top echelon o…
Comment linking /art-style-transfer-neural-networks/
on “As an artist I am concerned about AI image generation”Submitted Understanding GauGAN Part 1 as a story · 40 points
HN discussionWhat makes a thing funny? At its core, humor seems to be all about incongruity. Comic situations set up a context where something is marked or out of place. This oddness, far different to what we were led to expect or what we blithely assume is normal, is what makes things funny. [...] Dad jokes play with incongruity largely through linguistics and wordplay, rather than subject matter. The much-maligned pun is a mai…
Comment linking /measuring-text-similarity-using-levenshtein-distance/
on “The Dubious Art of the Dad Joke”Submitted Using AI to Gain Context for Scientific Research as a story · 34 points
HN discussionPaperspace also announced NVidia Volta VMs available today. As well as a contest for 100 compute hours credit ;) https://blog.paperspace.com/tesla-v100-available-today/
Comment linking /tesla-v100-available-today/
on “Nvidia GPU Cloud”Submitted Understanding GauGAN: Model Evaluation Techniques and Comparative Performance as a story · 24 points
HN discussionVery cool! We (Paperspace) just posted a tutorial on Detecting Pneumonia from X-ray scans using PyTorch for anyone interested in building some more intuitions around this type of Deep Learning: https://blog.paperspace.com/detecting-and-localizing-pneumon...
Comment linking /detecting-and-localizing-pneumonia-from-chest-x-ray-scans-with-pytorch/
on “AI Helps Classify Lung Cancer at the Pathologist Level”Submitted How to Use CycleGAN for Age and Race Conversion as a story · 17 points
HN discussionDillon from Paperspace here. If anyone is interested, this is actually part of a longer multi-part series covering GauGAN in-depth. Here's the link to the full series: https://blog.paperspace.com/tag/series-gaugan/
Comment linking /tag/series-gaugan/
on “Understanding GauGAN: Model Evaluation Techniques and Comparative Performance”Submitted Channel Attention and Squeeze-and-Excitation Networks (SENet) as a story · 16 points
HN discussion> the only way to fix them... This kind of claim is almost always suspect. There was a time that rotating or other manipulations caused issues for the models and those were largely taimed. Hinton's work with Capsule Networks [1] produced much more resilient models, though they are computationally much more intensive. It's also interesting that this is coming from Japan, where they also have a law regarding copyright…
Comment linking /capsule-networks/
on “Japan: Using Nightshade, etc. tools to disrupt AI training is illegal”Submitted Train ML Models on Free Cloud GPUs as a story · 12 points
HN discussionLooking at today, the Tensor-TFLOPS is the unit of measurement that Nvidia is trying to push as the relevant benchmark for hardware performance with ML models. https://blog.paperspace.com/understanding-tensor-cores/amp/
Comment linking /understanding-tensor-cores/amp/
on “What Is a Flop?”Submitted Adversarial Autoencoders with Pytorch as a story · 11 points
HN discussionThis tutorial examines the DALL-E family of image generation frameworks from OpenAI - https://blog.paperspace.com/dall-e-image-generator/
Comment linking /dall-e-image-generator/
on a deleted threadSubmitted GhostNet (CVPR 2020) in PyTorch and TensorFlow as a story · 10 points
HN discussionOur latest guide details setting up Arize AI's ML observability platform with Gradient Deployments. Follow this guide to learn how to integrate Arize within Gradient Deployments to monitor data drift, traffic, and other model monitoring metrics. http://blog.paperspace.com/monitoring-deployments-with-arize...
Comment linking /monitoring-deployments-with-arize-ai/
on a deleted threadSubmitted Interview with TikTok Deep Faker Jesse Richards as a story · 8 points
HN discussionSubmitted Object Localization using PyTorch, Part 2 as a story · 7 points
HN discussionSubmitted Tutorial: Image Compression Using Autoencoders in Keras as a story · 7 points
HN discussion
