-
I' wondering why there is a maxpool operator in dynamic part?
-
Hi, I'm wondering if there is any implementation in Pytorch version?
I also do some research about segmentation and want to test SegCaps performance in our dataset
-
Sorry to bother you.I downloaded the dataset，and found it contains .mhd files and .raw files,are they belong to imgs?So what is masks should contain?
_Originally posted by @pomodoromjy in https://…
-
I really appreciate your project.
I have a question about the routing algorithm.
https://github.com/lalonderodney/SegCaps/blob/c6b3f9e3e86b6e80652a76408fd6840c1ebe999b/capsule_layers.py#L319-L3…
-
How did you create the label vector (y) when using the model on MSCOCO dataset? For each input (image), MSCOCO has multiple outputs (categories). How to create the dataset in this case (i.e. the input…
-
Hi,I just want to use the luna 16 data to get the same performance as yours.But I don't find how you deal the raw dataset to imgs.Would you like tell me a little about it?
-
I do not know what slice is. I understand that the slice information in the argument is in the shape of the network. If I want to apply your network to my image data, can I put the number of channels …
-
Hi lalonderodney,
Thanks for your awesome paper and programs.
I am working on a pipeline based on your codebase to let everyone can train their own SegCaps on 3D and 2D images (MS COCO dataset).
…
-
hi, I tried your model for a 2D dataset but I'm currently struggling.
I basically modified the Load_3D_data.py folder so that the 'generators' emit my data.
However it seems the out_seg_dice_hard is…
-
Hello, thanks for the code and documents, they are easy to understand.
When I train the model on my own dataset (dataset includes 16 512*512 2D grayscale png images, and masks are black-white), it …