ADD-GCN

ADD-GCN copied to clipboard

Commented few lines as those are not required here

monjoybme

Affanabbbas

Inference pipeline

1

@Yejin0111 hi thanks for sharing the code base i had few queiers 1. There is no test / inference .py file to test on the image / video? can u...

abhigoku10

How get the visualization of category-specific activation maps ？ can you provide the code？

annni1

How get the visualization of dynamic matrix

3

Hello,Thank you for your work! How get the visualization of dynamic matrix , can you provide the code？

caopingping

AssertionError

2

Hello,Thank you for your work! question:assert os.path.exists(model_dir) == True AssertionError Often appear this problem, how to solve excuse me? Do you have a more detailed README.MD?What version of CUDA/TorchVision do...

annni1

ZeroDivisionError:float division by zero

2

file:util.py function:average_precision() question1:The problem of ZeroDiVisionError:float Division by Zero often occurs in the function that calculates the average precision of each class in the util.py file.Maybe because pos_count is always...

annni1

effect of identity matrix

1

Hi, what is the effect of the following operations? Why not just take the mean value of each class vector, like > out2=out2.mean(-1)  Thanks!

JiaweiZhao-git

When will code be released?

3

KiAkize

您好，论文中说‘we simply replace SAM with a Conv-LReLU block.’，X的形状是H * W * C，D-GCN需要的形状是C*D。只用卷积好像无法降低张量的维度，这里是怎么转换形状的呢？

szwlh-c