alcinos

In the setting where each node has a list of links, how would you deal with the same node belonging to several nets (simoultaneously) ?

@pavanky mmh it seems that it can rapidly become a mess, especially because each entity that wants to use a given node in a net has to resolve label conflicts...

Cool, I'm looking forward to take a look at it, and contribute if I have the opportunity

@futurely The code you are showing doesn't feature any encapsulation. This is a problem: - What if we want to change the number of hidden layers? - What if we...

Hi there, I have been giving this a bit of thought, and wanted to propose an alternative way of achieving this. Please let me know if this sounds like a...

Hi @mmaaz60 Thanks for your interest in MDETR. Could you provide the following information to help debug your error?: - Exact command line - Did you change anything to the...

Did you try the solution in #40, namely > Try setting the env variable "MDETR_CPU_REDUCE" to "1", this should help with memory during reduce

Appologies, I missed that. I’m a bit puzzled why this is happening for you. Maybe you can try forcing the predictions to cpu at the end of the postprocessors Specifically,...

This error most likely indicates divergence in your model. You can check by adding asserts like: ``` assert not boxes1.isnan().any().item(), "nan in boxes1" ``` in the `generalized_box_iou` function which is...

Hi @melongua The difference is as follows: - tokens_positive is the alignment that we use for computing the loss. It works in tandem with the boxes information: it is assumed...