-
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
-
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.
You may find jina.ai and their finetuner package useful: https://github.com/jina-ai/finetuner.
Clip like learning method : https://github.com/openai/CLIP turns out to learn pretty well, I have finetuned on question dataset ( quora ) using the same crossentropy loss by clip and the results is better than other embedding I tried ( universal sentence embedding and bert ).
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
-
How do you think search will change with technology like ChatGPT, Bing’s new AI search engine and the upcoming Google Bard?
-
Combining multiple lists into one, meaningfully
-
speech_recognition not able to convert the full live audio to text. Please help me to fine-tune it.
-
Questions about fine-tuned results. Should the completion results be identical to fine-tune examples?
-
[D] Looking for an open source Downloadable model to run on my local device.