Malte Büttner

@endernewton just a follow up on the requests. I am really interested in your implementation as it is very relevant for my thesis. Thanks :) See also #10 #6

@fg91 sorry for the mess. I know it is hard to review, because it combines quite a lot of changes in one PR. Should I make several pull requests out...

I finally addressed your proposed changes :tada: : - `filtervisualizer.py` is now in root. See 12ebf75 - `Calculate_mean_activation_per_filter_in_specific_layer_given_an_image.ipynb` now uses `filtervisualizer.py`. See 9b4b794 - `train_tfms` and `val_tfms` are now instance...

@fg91 If there is anything else you want me to change, just let me know.

On a similar note, I would like to use the occlusion techniques on a network where `model.input` shape is `(?, 3, 224, 224)`, `model.output` shape is `(?, 1000)`. This of...

This would be a very welcomed feature 😊. As of now, I use a somewhat hacky approach for JSON errors. Certainly not perfect but maybe this helps someone in the...

Check out[ Label Studio](https://labelstud.io/)!

I second this request! Would be amazing if the weights and codes were released as it will certainly accelerate research. :blush: Anyhow, thanks for your amazing work @liminghao1630 !

Thanks a lot @liminghao1630 ! Greatly appreciated 👍

Totally agree that this is a interesting feature. Would be super nice to have something standardized here (mentioned something similar [here](https://github.com/vllm-project/vllm/issues/8636)). We are currently leveraging Ray and the [LLMClass](https://docs.vllm.ai/en/v0.6.2/dev/offline_inference/llm.html) `llm.chat()`...