pytorch-widedeep
pytorch-widedeep copied to clipboard
jrzaurin
A flexible package for multimodal-deep-learning to combine tabular data with text and images using Wide and Deep models in Pytorch
* Environment : Google Colab Pro (Tesla P100 / T4, both tested) ## Error Massage Hi, I'm currently working with Kaggle competition which has not small dataset (about 1.5gb) Now...
* added quantize feature * I have to recheck if it si doing what I really want.. * no tests, yet; just initial commit
## Background: I noticed this while trying to use TabTransformer. When I run code with all categorical columns and no continuous columns, the code crashes. I think the error is...
I have tried to use torch1.11.0+torchvision0.12.0 and torch1.7.1+torchvision0.8.2, but report errors like "No module named 'torchvision.models._api'" and "cannot import name 'RandomInvert' from 'torchvision.transforms'". I guess it maybe the version of...
Hi! Awesome package! How to correctly cite it in papers? Do you have connected publication on arxiv.org or any doi? Thanks!
@jrzaurin I recall changing the math formulas from pictures to latex syntax in README.MD and docs/index.md .. why were they removed? (maybe just a copy/paste/merge issue?); the latex math syntax...
I was trying to use text processor as mentioned in the docs/examples, but I get this error. I couldn't find this attribute in the TextPreprocessor class.
Hello, I'm trying to classify events for a dark matter direct detection experiment which are tabulated in some optimal features (data are continuous). When I run both xgboost and lgbm...
I am attempting to run the following code: ``` x_test = pandas.read_csv('test(1).csv') x_test = text_preprocessor.transform(x_test) predictions= trainer.predict(X_text=x_test) ``` where x_test consists of a single column with text descriptions and I...
