jrieke / traingenerator Goto Github PK

Hi there!

I´m planning to make a text classification template using scikit-learn. Just let me know whether this task adapts to the goal of the project.

Once I get the ok, I´ll start working on it.

RNN (LSTM) , CNN

I tried a couple of times and every time your web socket failed to get a connection (browser: safari)

@jrieke

Hi, everybody, I'm looking forward to contributing this project can I add

1. Semantic Segmentation
2. Generative Adversarial Networks
3. Image Caption
4. Style Transfer

as I think this would greatly help beginners who are starting out their deep learning journey and want to do interesting things like these.

PS: can I also work on object detection using the YOLO-v5 achritexture.

Thanks a lot please reply as soon as possible

Thanks for the great work.
It would be great to add Aim to train generator as an experiment logger option.

Aim is the most advanced open source experiment comparison tool available at the moment.

I started to work on semantic segmentation with TF/Keras. i will mainly use segmentation models library, if you have any suggestions or if you want to help feel free to contact me!

Opening up this issue to coordinate work on a new keras/tensorflow template – @jaymody and @EteimZ have shown interest in this. Guys, please feel free to share here if/how you want to work on this and coordinate :)

The template could probably take a lot of the code from the existing pytorch template and sklearn template for image classification and just train tensorflow models. I guess keras will be the easiest (and most useful) option.

Hello!
I am planning to add an option to declare number of classes for image classification model. This also helps for transfer learning.

If you guys think there might be an interest in that I would like to offer my contribution for a text classifier in TensorFlow.

First of all thanks for the project, it's an interesting way to take a stab at reducing the amount of boilerplate needed even for fairly simple models. Secondly, it would be interesting to implement experiment/run tracking using MLflow.

Have a working example on the Image classification_PyTorch/ template, happy to submit a PR if you consider this of any interest.