SparK

Public

[ICLR'23 Spotlight?] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"

bert cnn convnet convolutional-neural-networks deep-learning iclr iclr2023 instance-segmentation mae mask-rcnn

Creat：2023-01-05T21:19:34

Update：2025-03-26T21:31:55

https://arxiv.org/abs/2301.03580

Stars

Stars Increase

Related projects

Transformers

Hot

bert

? Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

153615

2年前

+136today

AI For Beginners

12 Weeks, 24 Lessons, AI for All!

44127

1年前

+44today

EasyOCR

cnn

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

28519

1年前

+10today

Haystack

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

23563

1年前

+32today