Our great sponsors
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
label-errors
🛠️ Corrected Test Sets for ImageNet, MNIST, CIFAR, Caltech-256, QuickDraw, IMDB, Amazon Reviews, 20News, and AudioSet
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
In fairness you can run MNIST through UMAP and get near perfect seperation. I'm of the belief that you have to try pretty hard not to do well on MNIST these days.
https://github.com/lmcinnes/umap_paper_notebooks/blob/master...
If you'd like to play around with MNIST yourself, I wrote a PyTorch training implementation that gets ~95.45%+ in <13.6 seconds on a V100, est. < 6.5 seconds on an A100. Made to be edited/run in Colab: https://github.com/tysam-code/hlb-CIFAR10
It's originally kitted for CIFAR10, but I've found the parameters to be quite general. The code is very easy to read and well-commented, and is a great starting place for exploration.
Min-cut deltas to run MNIST:
`.datasets.CIFAR10('` -> `.datasets.MNIST('` (both occurences)
ben recht's kernel method implementation in 10 lines hits 98%
https://github.com/benjamin-recht/mnist_1_pt_2/tree/main
Sadly,there are several errors in the labeled data, so no one should get 100%.
See https://labelerrors.com/