stanwinata commented 3 years ago

Prerequisites

Please answer the following question for yourself before submitting an issue.

[x] I checked to make sure that this feature has not been requested already.

1. The entire URL of the file you are using

https://github.com/tensorflow/models/tree/master/official/vision/beta/projects/pix2seq

2. Describe the feature you request

We'd like to implement pix2seq's detector model and training + inference framework. Which is a object detector that is based of Language Modelling networks that can output bounding boxes and class labels coordinates as sequence of tokens.

3. Additional context

I'd be working together with @nithinsubbiah

4. Are you willing to contribute it? Yes

Would love to work and contribute this to TF, with the TF team's blessing of course 😃

stanwinata commented 3 years ago

So do we have the blessing to go ahead and if yes is the official/vision/beta/projects the place to be in 🙂

sineeli commented 1 year ago

A PR has been opened for the PR #10965

laxmareddyp commented 1 year ago

Hi @stanwinata,

The PR has been closed and closing this as completed.

Thanks

tensorflow / models

Pix2Seq paper implementation #10289

Prerequisites

1. The entire URL of the file you are using

2. Describe the feature you request

3. Additional context

4. Are you willing to contribute it? Yes