-
Hello @kondratevakate
Thank you for the great effort. I am hoping to use your work in a detection system that am working on at the moment. Deformable convolution seems to be a good strategy for my …
-
After I train the network you provide and obtain the Resnet_dcn.caffemodel, I compiled the matlab interface and try to load the caffemodel. However, an error appeared (caffe.layerparameter has no fie…
-
Since both torchvision's deform_conv2d and this repo tend to replicate the deformable convolutional net,would like to know what seperates this implementation from the torch implementation.
-
the value will become very large, even 10^3 when i use deformable convolution in other network, i want to know what the meaning it is when getting so large?
-
## 📚 Documentation
From the documentation, I cannot get the exact meaning of 18(ie, 2*3*3) channels of the offset in a deformable convolution?
I want to visualize the offset of the deformable con…
-
Hi, and thank you for your work.
I'd like to understand better the `deformable_groups` parameter of the `ModulatedDeformConvPack` class.
To my understanding, based on [this](https://github.com/m…
-
Hi HuguesTHOMAS,
Thank you for your implementaion of KPConv and sharing with us. When I finish train and test about Object Classification on ModelNet40, I run visualization scripts for the kernel …
-
when I ran sh make.sh, the problem: raise TypeError ('disc must be a Distribution instance') from build_modulated.py is always showing up, could anyone tell me how to solve it or could u send me proce…
-
Hi, and thank you for your work.
I'd like to understand better the `deformable_groups` parameter of the `ModulatedDeformConvPack` class.
To my understanding, based on [this](https://github.com/m…
-
In Equation 4 in your paper, you specify an equation for the spatial-aware attention module which averages across the levels of the rescaled spatial pyramid. It appears this equation would map an elem…