Our great sponsors
-
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.
The other thing I thought about was posing the problem as a contrastive representation learning problem. So I thought I could try something like CLIP (but with two vision networks instead of a vision and a language network) and learn to map similar pairs of images to be close to each other in representation space. I tried this, modifying the code here, but found that the loss was only coming down incredibly slowly.
NOTE:
The number of mentions on this list indicates mentions on common posts plus user suggested alternatives.
Hence, a higher number means a more popular project.
Related posts
- Super Simple SDR Receiver (Using a Tayloe Quadrature Detector)
- CVPR 2024 Datasets and Benchmarks - Part 1: Datasets
- AI enthusiasm #7 - Build an AI-powered Telegram Bot!🤖
- Show HN: Auto Wiki v2 – Turn your codebase into a Wiki now with diagrams
- Show HN: Knee, OSS CLI tool to reduce time for infra orchestration