A History of CLIP Model Training Data Advances
In this post, we’re going to cover five of the most important data-centric advances in contrastive language-image…
Tag: CLIP
How to Visualize Your Data with Dimension Reduction Techniques
Learn how to visualize embeddings using PCA, t-SNE & UMAP. And learn strengths & weaknesses of each.
Concept Traversal Plugin for FiftyOne
Traverse the space of concepts in your dataset. Select an initial image and iteratively add concepts in different…
The Computer Vision Interface for Vector Search
Vector search is essential in modern ML toolkits. FiftyOne integrates directly with LanceDB, Milvus, Qdrant, &…
Conquering ControlNet
ControlNet has been one of the biggest success stories in ML in 2023. Build a high quality dataset so you can train…
Visualizing Defects in Amazon’s ARMBench Dataset Using Embeddings and OpenAI’s CLIP Model
Learn how to visualize & explore Amazon’s ARMBench dataset using embeddings, CLIP, and FiftyOne.
FiftyOne Computer Vision Embeddings Tips and Tricks – Mar 31, 2023
New computer vision tips & tricks focused on using embeddings in open source FiftyOne!
A Google Search Experience for Computer Vision Data
How to use vector search engines (Pinecone & Qdrant) & OpenAI’s CLIP model natively in FiftyOne to perform similarity…
Finding Images with Words
Learn how to add natural language image search to your computer vision pipelines with FiftyOne, Pinecone, and OpenAI’s…