We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
For example I guess this is one way?
from experiment import VAEXperiment config = yaml.safe_load(open('configs/vae.yaml')) ckpt = torch.load('logs/VanillaVAE/version_1/checkpoints/last.ckpt') experiment = VAEXperiment(model, config['exp_params']) experiment.load_state_dict(ckpt['state_dict'])
Then one can access the model via experiment.model
experiment.model
It took me a while to figure this out. Maybe add such instructions to the README?
The text was updated successfully, but these errors were encountered:
Hello! What model did you pass to the experiment?
experiment
Sorry, something went wrong.
Nevermind, it works with:
from experiment import VAEXperiment import yaml import torch from models import * config = yaml.safe_load(open('./configs/bbvae.yaml')) model = vae_models[config['model_params']['name']](**config['model_params']) ckpt = torch.load('./logs/BetaVAE/version_0/checkpoints/last.ckpt') experiment = VAEXperiment(model, config['exp_params']) experiment.load_state_dict(ckpt['state_dict'])
where I used the BetaVAE model.
BetaVAE
No branches or pull requests
For example I guess this is one way?
Then one can access the model via
experiment.model
It took me a while to figure this out. Maybe add such instructions to the README?
The text was updated successfully, but these errors were encountered: