ZhouYanzhao

Yes. For an ORConv operation, the size of inputs is `[nBatch x nInputChannel x nOrientation x H x W]`, the size of ARFs is `[nOutputChannel x nInputChannel x nOrientation x...

@ljhandlwt , In ORN, feature maps and filters (ARFs) are vector fields that explicitly encode orientation information. **Coordinate Rotation** and **Orientation Spin** are steps in rotating a vector field. Here...

@ljhandlwt ARFs are viewed as N-directional points on a grid (vector fields). For each arrow, the length represents its value (a number), and the angle indicates the corresponding orientation channel.

Hi @dingjiansw101 The OR-CNN defined in demo.py is used in our MNIST experiments. For CIFAR10/100 experiments, please refer to this [model definition](https://gist.github.com/ZhouYanzhao/c7f75cd8ea3c92e2044d71ac7bc30fab/raw/or-wrn.lua).

Hi @dingjiansw101, 1) I can port the CIFAR experiment after I upgrade the pytorch implementation. But it won't be available in the near future. 2) No. The models we used...

Hi, @ymcasky Thanks! The code does look a bit dated. I'm going to give it an upgrade next month to support the latest version of pytorch.

@sawsenrezig Hi, the main point of ORConvs is to enable CNNs to explicitly encode orientation information into its weights (ARFs) as well as feature maps. Therefore in ORN, we can...

HI @842430478 , The `peak response mapping` module expects a list of binary masks (numpy ndarray, shape of Image Height x Image Width) as the proposal input. You can convert...

Sorry for missing your reply, we are swamped with some project deadlines for the time being. If you need to discuss or want me to help diagnose your code, please...

Hi @JaringAu, please check [FAQs](https://yzhou.work/faqs/prm.html).