Ensemble-Pytorch

Ensemble-Pytorch copied to clipboard

I use the following code to implement adversarial classifier on cifar100 ``` transform_train_cifar = transforms.Compose([ transforms.RandomCrop(32, padding=4), transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)), ]) traindataset = datasets.CIFAR10(root, transform_train_cifar)...

antonioo-c

number of estimators?

3

Hi Thanks for your good library. Can you tell me how multiple estimators made from one model in this library from one data? is there any function for specially for...

maxwell1386

custom built optimizer for `set_optimizer`

1

I am trying to run `BaggingRegressor` with a custom built optimizer. But it seems it's not currently supported. So, I am doing the following ``` import torch import torch.nn as...

hmishfaq

Supporting bootstrap sampling as in sklearn

3

I am trying to convert a sklearn based code that uses [sklearn.ensemble.BaggingRegressor](https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.BaggingRegressor.html) and am wondering if Ensemble-pytorch can have bootstrap argument as sklearn has.

hmishfaq

Using pretrained models directedly at decision level.

1

Is the a way to use the libaray for pretrained model? suppose that I have 4 alreay trained models, and I want to just ensemble them.. Is there a way...

opencomvis

How to ues the result "ckpt.pth"

3

I use the examples obtaining the modle parameters "ckpt.pth", how can i use it to test my datasets? thanks for your help.

wyxAshdila

Allow Continuation of Training

2

It appears that the `fit` method for ensembles is also where the estimators are instantiated. It would be convenient (for example for fine-tuning pretrained ensembles) if the instantiation and training...

jtpdowns

Hi, I am using VotingClassifier and logging out training and validation loss in TensorBoard to find out if my model is overfitting or underfitting. I had to modify the VotingClassifier...

singhabhinav

Ensembling Methods incompatible with snnTorch models

1

Hi, I have been trying to set up GradientBoosting for an snnTorch model I am working on it's mostly PyTorch in the background. However, I've run into a circular issue...

kgano-ucsd

`AdversarialTrainingClassifier` may not work properly

5

Hi I have trained several adversarial trained ensembles based on TorchEnsemble implementation. The results I got are very interesting and surprise me. To illustrate, I set the epsilon = 8/255,...

vietvo89