Skip to content

issues Search Results · repo:cedrickchee/capsule-net-pytorch language:Python

Filter by

15 results
 (88 ms)

15 results

incedrickchee/capsule-net-pytorch (press backspace or delete to remove)

cedrickchee/capsule-net-pytorch
bug

thanks for this very good code! But I got a problem here，when I try to Test a pre-trained model, I use the bash python main.py --is-training 0 --weights results/trained_model/model_epoch_5.pth as README ...
  • Saray-0
  • Opened 
    on Mar 15, 2023
  • #15

cedrickchee/capsule-net-pytorch
may be primary_unit_size=8， in_unit=1152

# [1 x primary_unit_size x num_classes x output_unit_size x num_primary_unit] # == [1 x 8 x 10 x 16 x 1152]
  • zhangjcqq
  • Opened 
    on Jan 19, 2019
  • #14

cedrickchee/capsule-net-pytorch
Deviations of this implementation from the original paper

I have come across the following main deviation between the paper(https://arxiv.org/abs/1710.09829) and the implementation of this repo: In the paper: there are 32 primary capsule layer with 6x6 capsules ...
  • InnovArul
  • 2
  • Opened 
    on Aug 19, 2018
  • #13

cedrickchee/capsule-net-pytorch
Activation functions on FC decoder layers

First, thanks for this very good code! The original paper proposes a decoder with three fully connected layers: FC+ReLU - FC+ReLU - FC+Sigmoid. But your decoder code seens to do FC - FC - FC - ReLU ...
  • ygorcanalli
  • 2
  • Opened 
    on Jul 12, 2018
  • #12

cedrickchee/capsule-net-pytorch
Test error results reported are actually loss figures and are not comparable with paper reported accuracies.

Thanks for a very nicely presented implementation of Capsule Networks. I especially appreciate the tensorboard plots. Unfortunately I believe you have mixed up ** test error ** with ** test loss ** when ...
  • geefer
  • 3
  • Opened 
    on Jun 13, 2018
  • #11

cedrickchee/capsule-net-pytorch
Support PyTorch 0.4.0

Migrate existing code to work in PyTorch version 0.4.0. PyTorch 0.4.0 introduced a major core changes that changed the previous API version. Status: I have started work on this and making code changes ...
enhancement
  • cedrickchee
  • Opened 
    on May 9, 2018
  • #10

cedrickchee/capsule-net-pytorch
Memory required explodes when the CapsLayer instance is called

@cedrickchee The memory required by the network increases from 3 GB to about 25 GB after the finishing of the Primary caps layer and after Capslayer is called. I wonder why so. I m not able to solve this ...
  • arshiyaaggarwal
  • 1
  • Opened 
    on Apr 3, 2018
  • #9

cedrickchee/capsule-net-pytorch
Continue training?

Train CapsulesNet is known as time-consuming and not yet optimized. So, I want an option of loading pre-trained weights (e.g. provided file path) and continue training.
enhancement
help wanted
  • hiepph
  • 2
  • Opened 
    on Feb 12, 2018
  • #8

cedrickchee/capsule-net-pytorch
Test model on other dataset like CIFAR10

In the spirit of learning by experimenting, we should try CapsNet using other datasets. Please refer to the paper under section 7 Other datasets for things to change to support CIFAR10 dataset. I am ...
enhancement
  • cedrickchee
  • 1
  • Opened 
    on Jan 24, 2018
  • #7

cedrickchee/capsule-net-pytorch
Issue of squash dimension

Is the squash operation applied on dimension 8 or 1152? return utils.squash(unit, dim=2) # dim 2 is the third dim (1152D array) in our tensor It seems like the squash is applied on dim=2, namely 1152D ...
question
  • caolusg
  • 5
  • Opened 
    on Jan 20, 2018
  • #6
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue search results · GitHub