L7

L7

  • Home
  • About
  • Contact

All Posts (by tag)

build-gpu-rig confident-learning deep-learning keras machine-learning noisy-labels pytorch

pytorch

A collection of 4 posts

March 28, 2021

Pervasive Label Errors in ML Datasets Destabilize Benchmarks

To our surprise, label errors are pervasive across 10 popular benchmark test sets used in most machine learning research, destabilizing benchmarks.

machine-learning confident-learning noisy-labels deep-learning pytorch

December 18, 2019

Benchmarking: Which GPU for Deep Learning?

We already know the best performance/cost GPUs for state-of-the-art deep learning and computer vision are RTX GPUs. So, which RTX GPU should you use? To help you decide, I benchmark the three premier GPUs: 2080 ti non-blower, 2080 ti blower,...

build-gpu-rig deep-learning pytorch

December 17, 2019

Double Deep Learning Speed by Changing the Position of your GPUs

This is short post to explain the impact that GPU positioning can have on training time and suggest how to position your GPUs for better performance when you mix blower-style and non-blower GPUs. Consider a deep learning workstation with the...

build-gpu-rig deep-learning pytorch

February 21, 2019

Towards Reproducibility: Benchmarking Keras and PyTorch

The Benchmarking Keras PyTorch GitHub project benchmarks every pre-trained model in PyTorch and Keras (Tensorflow). All benchmarks are reproducible.

deep-learning keras pytorch

Subscribe to the L7 newsletter.

Receive infrequent and minimal updates from L7 when new posts are released.

L7 © 2021. Curtis G. Northcutt. curtisnorthcutt.com
Learning is what makes us human.

Back to top