PyTorchCML

PyTorchCML copied to clipboard

`one of the variables needed for gradient computation has been modified by an inplace operation:` This is the error I am getting after running the cml jupyter notebook in the...

kunalsonalkar

Any way to get user-user, item-item and user-item embeddings back from trained model?

1

Hello, like LightFM algorithm, is it possible to retrieve user-user, item-item and user-item embeddings back from the trained model?

shivamtundele

- add devcontainer - add get_topk_item method to model - raise error when the length of weights is illegal - fix tqdm to tqdm.auto

hand10ryo

Early stop for overfitting?

1

I tried find a method inside the model and trainer methods for early stopping. Is there a way?

shivamtundele

Fix tqdm for notebooks

2

Please change all occurences of tqdm from `from tqdm import tqdm` to `from tqdm.auto import tqdm`. Otherwise, model fit is printing a new line of progress bar for every update...

shivamtundele

TwoStageSampler is giving Simplex() error

3

Following error is happening no matter if I am using pos or neg weights ``` epoch1 avg_loss:1.206: 0%| | 1/256 [00:00 18 trainer.fit(n_batch=256, n_epoch=10) ~/.local/lib/python3.7/site-packages/PyTorchCML/trainers/BaseTrainer.py in fit(self, n_batch, n_epoch, valid_evaluator,...

shivamtundele