TRACER

TRACER copied to clipboard

Adaptive pixel intensity loss

1

hi,thank you for your excellent work，I don't understand the following formula. Can you explain it for me？ 1、Why does equation 8 need to be multiplied by yij? This will cause...

liuzhihui2046

How would one export this model to ONNX? It keeps hanging for me while trying to export it

XavierGeerinck

U2Net benchmark comparison

3

Hey! Loved the paper. Have you tried doing a comparison to U2Net? As for now, it's considered the state-of-the-art in SOD. I was wondering if you tested against it.

roimulia2

Hi, There was a line where it was directly written as `.cuda()` to push the structure to GPU. I have changes it to `.to(device)`. Since the models were trained with...

deshwalmahesh

Can you upload the result file to test the effect?

2

Can you upload the result file for evaluating the performance?

user-wu

multi class question

4

Hello. Thank you for your wonderful research. I want to extend your methodology to multi-class classification. Is this possible? If possible, could you give me some implementation tips?

DeepHM

Error while trying to Train in a DataParallel setting on 4 GPUs

2

Hello, Thank you for your amazing work. I had an issue while trying to train the model on 4 GPUs. The trace is as shown below. I however was able...

smriti-19

Pretrained weight

1

Thank you for your great work. Can I know what dataset you used to train the weight that you are public?

petertran1811

Custom Data Train Error

1

Hi, when i try to train on a custom dataset I got this error. @Karel911 C:/cb/pytorch_1000000000000/work/aten/src/ATen/native/cuda/Loss.cu:102: block: [0,0,0], thread: [0,0,0] Assertion `input_val >= zero && input_val = zero && input_val...

Khinchine

Does not support negative images in training

3

I put some images which does not have label in it i.e completely black mask with respect to those images and the output of it is tensors having nan's instead...

rishabhfrinks123