EfficientNet for Semantic Segmentation in TensorFlow

[mradul2]

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://arxiv.org/abs/1606.02147

2. Describe the feature you request

I want to contribute a new research paper code for the work: ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

3. Additional context

Efficient Net is a neural network architecture particularly for real-time semantic segmentation, and I plan to implement the model in Tensorflow 2, and also reproduce the baseline results the original paper provides on the CityScapes dataset. Along with publishing the pre-trained model on TensorFlow Hub.

4. Are you willing to contribute it? (Yes or No)

Yes

[innat]

It would be better to have these models within the high-level API like keras-CV. This tensorflow/models is too messy to work with (IMHO).

[mradul2]

Sure, can you guide me through that? I could not find appropriate contribution guidelines for keras-CV.

[innat]

@mradul2 Please check this update list about contributions. AFAIK, we may get some updates about keras-cv soon, source. IMO, if you maintain ENet in your own repo and contribute to keras.application when the time comes, that would be really good.

[laxmareddyp]

Hi @mradul2,

Thank you for opening this issue. Since this issue has been open for a long time, the code/debug information for this issue may not be relevant with the current state of the code base. The TF models official team is constantly improving the framework by fixing bugs and adding new features. We suggest you try the latest TensorFlow version with the latest compatible hardware configuration which could potentially resolve the issue. If you are still facing the issue, please create a new GitHub issue with your latest findings, with all the debugging information which could help us investigate. Please follow the release notes to stay up to date with the latest developments which are happening in the TF models official space.

[github-actions[bot]]

This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.

[github-actions[bot]]

This issue was closed due to lack of activity after being marked stale for past 7 days.