FixCaps

FixCaps copied to clipboard

Test Set

4

Hello, I just wanted to confirm that the results presented (96pct acc) were on the ham10000 test set, as opposed to a custom split of the training set? Thanks, Brett

bdytx5

https://github.com/Woodman718/FixCaps/blob/16d5adc6c165e6fd19a9dadb091bb8ea1ac5f6dd/README.md?plain=1#L8 How does the dataset offered there differ from the original? (Is it possible to set this page in English?) And can you also just provide the code so that...

saskra

@Woodman718 I see that the other datasets tested have their respective checkpoint (.pth) files. Do you have the checkpoint files for the HAM10000 dataset? I want to replicate your results

baxtrax

The number of parameters reported for each FixCaps model seems to be coming from [torchsummary](https://github.com/sksq96/pytorch-summary) (see cell. 6 in [FixCaps-DS notebook](https://github.com/Woodman718/FixCaps/blob/main/Module/FixCaps_DS.ipynb)). However, torchsummary parameter count is inaccurate for custom modules,...

Thity

Issue on how i find the files train525orig , 525_train , 501_train etc . . . .

1

Sir currently I am working on your project named FixCaps but i cant find some of the directories like 525_train , 501_train all some directories present in the code in...

SrinivasReddy2690

Hi I have a questions about experiments

6

First, Thanks for good research and i'm interested in skin cancer lession classification task. So i want try reproduce your experiments but i only got 94% accuracy on HAM10000 dataset....

Ha-Jungmin

Question about dynamic routing with BatchSize > 1 for HAM10000 FixCaps model

1

Hello! I am replicating your model for the HAM10000 for a course project. I had a question about the dynamic routing implementation inside your Digit Caps module. In `model.py` [line...

udiboy1209