clip-as-service
electra
Our great sponsors
clip-as-service | electra | |
---|---|---|
15 | 3 | |
12,148 | 2,280 | |
0.7% | 0.4% | |
5.2 | 0.0 | |
2 months ago | 6 days ago | |
Python | Python | |
GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
clip-as-service
- Image Similarity Score using transfer learning
-
Google launched multisearch last week, here's how you can create your own multisearch
Multisearch allows people to search with both text and images. With Open-Source project CLIP-as-service, you can use CLIP (a deep learning model by OpenAI) to do the same. Ask me if you have any questions?
-
Natural text to image search(without captions), using CLIP model. Notebook in comment.
Are you scraping these images or using any dataset? Do share the link, would love to play around with it. Would love to hear your feedback for clip-as-service (what I use in my example)?
-
Released my 2nd best open-source project out of 170 projects shipped in the past 2 yrs to make AI powered search easy
And this latest project Clip as a service has just received 10k stars on GitHub, very close to my other project Jina which has 14k stars. Clip as a service providers an easy and intuitive way to create embeddings for text and images that can be used to create semantic text and image search.
electra
-
Fine-tuned model consistently producing Precision and Recall scores of 0 from start of training, any suggestions on how to improve?
If this is your own implementation of ELECTRA, hopefully you have previous versions you've demonstrated working, you could revert back to a working version, then apply the changes you made one-by-one. If it's open-source code you are using, such as this one, try and find a working example, run it yourself, carefully modify it, preserve it in a working (high performance) state, change it piece-by-piece until it works on your problem.
-
Help with aligned word embeddings
If you have at least a decent gaming gpu or want to bother with colab, you could get a relevant dataset and use electra https://github.com/google-research/electra
What are some alternatives?
BERTopic - Leveraging BERT and c-TF-IDF to create easily interpretable topics.
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
DeBERTa - The implementation of DeBERTa
rclip - AI-Powered Command-Line Photo Search Tool
spaCy - 💫 Industrial-strength Natural Language Processing (NLP) in Python
OpenPrompt - An Open-Source Framework for Prompt-Learning.
ludwig - Low-code framework for building custom LLMs, neural networks, and other AI models
scibert - A BERT model for scientific text.
tensorflow-open_nsfw - Tensorflow Implementation of Yahoo's Open NSFW Model
jina - ☁️ Build multimodal AI applications with cloud-native stack
ABSA-PyTorch - Aspect Based Sentiment Analysis, PyTorch Implementations. 基于方面的情感分析,使用PyTorch实现。
thinc - 🔮 A refreshing functional take on deep learning, compatible with your favorite libraries