urancon

Hi @Manishsinghrajput98 , thanks for sharing your code, that's really nice of you. Could you provide as well the evaluation metrics of your models ?

Hello @ChidanandKumarKS and thank you for your interest in our work ! Just like you, I would also think intuitively that StereoSpike architecture would fit for image reconstruction. However, there...

Hello, thank you for pointing out this bug ! It is because the `drop_last` argument is set to `False` [in the train dataloader](https://github.com/urancon/StereoSpike/blob/b59f65121d618e1ed3039e41d37318917762ba22/train.py#L99). Set it to `True` and that should...

Hi, thanks for your paper and the repo ! Like @7LuoXi , I am interested in your training code and your implementation of the loss function too. Also, the version...

Oh, I'll check that, thanks so much for telling !

Hi, thanks for the great repo ! I have a similar question. How is it possible to optimize inputs of any shape ? For instance, I am working on a...

Thank you so much for your reply ! Looking forward to see that !

Hi @greentfrapp , thank you for your help, that's great ! So that fixes our problem for 3 dimensional images [N (batch), C, H, W] with C != 3. Can...

Ok, it seems much clearer to me now, thank you ! I definitely have to re-read this article. Yes, I think that supporting another dimension (e.g. a third spatial dimension...