google-research/pix2seq
Google Research implementation of Pix2Seq, a TensorFlow 2 framework that converts RGB images into semantic sequences for object detection and other vision tasks.
Not currently ranked — collecting fresh signals.
star history
Pix2Seq is a multi-task computer vision framework that reformulates tasks like object detection as sequence generation problems. The codebase supports both autoregressive decoding and diffusion-based generative models (including FitTransformer, Bit Diffusion, and RIN). Built in TensorFlow 2 with efficient TPU/GPU support, it provides pretrained checkpoints for tasks like object detection on datasets like Objects365 and provides Colab notebooks for inference.
Frequently asked
- What is google-research/pix2seq?
- Google Research implementation of Pix2Seq, a TensorFlow 2 framework that converts RGB images into semantic sequences for object detection and other vision tasks.
- Is pix2seq open source?
- Yes — google-research/pix2seq is open source, released under the Apache-2.0 license.
- What language is pix2seq written in?
- google-research/pix2seq is primarily written in Jupyter Notebook.
- How popular is pix2seq?
- google-research/pix2seq has 945 stars on GitHub.
- Where can I find pix2seq?
- google-research/pix2seq is on GitHub at https://github.com/google-research/pix2seq.