Oussamab21

how to use soft-nms with NMS from tensorflow

2

I am trying to integrate this implementation with TF.NMS implementation but I have no idea how to do so since TF implementation use tensors ?

Training + Evaluation time

2

How much the training and the evaluation time can take ?

thanks for sharing this code, I was wondering what should I change if I want to be able to use data that can be converted into images with an input...

Thanks for sharing the code , I was wondering if this code uses the pretrained version?

Hi, thanks for sharing the code I was wondering what should I change if I want to use a data set with data that can be converted into images of...

what should I change if I want to use a data set with images of 750* 184

1

Hi, thanks for sharing the code, I am using a dataset that can be converted to images of size 750* 184, I was wondering what should I change in this...

what is the exact meaning of iterating in the parameters ?

2

Hi , I just wanted to know what is the exact effect of these instructions: for p in list(model.parameters()): if hasattr(p,'org'): p.data.copy_(p.org) for p in list(model.parameters()): if hasattr(p,'org'): p.org.copy_(p.data.clamp_(-1,1))

when initialize the weight in a different range then the default case I get the node probability as NaN did any one experienced that ?

Thank you for your code I was wondering what I should change to use the nn.CrossEntropy loss instead of the loss stated in the paper ? Thank you

Using vision transformers for different image resolutions

1

Hi, I ma working on using vision transformers not only the vanilla ViT, but different models on UMDAA2 data set, this data set has an image resolution of 128*128 would...