Alan Bi

Maybe [this](https://pytorch.org/docs/stable/tensorboard.html) tutorial can help? With Detecto's Model class, you can call the `get_internal_model` method to get the actual PyTorch model, which you can then pass to the SummaryWriter as...

Update: a progress bar has been added in [v1.1.2](https://github.com/alankbi/detecto/releases/tag/v1.2.0) :)

That's not supported, but if you wanted to do something like that, perhaps you could just iterate through each of the images in your validation set and manually construct the...

I think there are two options: 1. Write a custom fit method that does what you need (you can modify the existing code as a template). 2. Call `fit` one...

That's a good catch. Two possible solutions: 1. Filter out the predictions to keep only the top scoring label per image. This only works if your validation dataset has one...

I can't provide the exact code or anything, but you should look into pandas. If you iterate through the nested list of labels/boxes and append each set as a tuple...

Could you share the code leading to your memory error? Also, this is not in the official API, but `model._get_raw_predictions` is a method that returns the pure int values rather...

It may be that you're trying to load in too many images at once by calling `predict` with a list of images. Maybe try looping through the images and passing...

Is there any other optimizer that you had in mind to use? Also, the default batch size is 1 (see [here](https://pytorch.org/docs/stable/data.html#torch.utils.data.DataLoader) for other defaults).

To be completely honest, there wasn't a major reason for choosing SGD over Adam (possibly because [this](https://pytorch.org/tutorials/intermediate/torchvision_tutorial.html) tutorial chose SGD which is why I chose it as well haha). For...