Francesco Pochetti

Results 50 comments of Francesco Pochetti

Yep, same here. It is incredible stuff and I am interested in the training code too, please.

Interested in this one too, please.

Thanks a lot for the prompt reply and for clarifying!

@PatrickBue just to make sure, is this the correct link? https://cvbp.blob.core.windows.net/public/datasets/object_detection/odFridgeObjects.zip I am trying and it doesn't seem to work. ![image](https://user-images.githubusercontent.com/1206519/107233841-4b9e5780-6a23-11eb-983f-0fa9ddfedbf6.png) If not, what is the new location please? Thanks...

Also, would you see as reasonable the possibility of hosting the dataset ourselves on our repo? I didn't find the license, which is why I was not sure we were...

@fstroth @potipot you guys both worked on COCOMetric. Is this possible? Frederik, maybe with your dashboard?

Great. Closing this one, then. @tugot17 please refer to the [IceVision Dashboard](https://github.com/fstroth/icevision_dashboards) built by @fstroth for more info.

> There is an option to test a trained model. Assuming its weights are already loaded you can use for fastai: > > ```python > learner.validate(test_dl) > ``` > >...

Yes I agree. Keeping it here open as a reminder

@ai-fast-track maybe we can add a cell or two showing how to do this to the `inference.ipynb`