Marcus Fraaß

Thank you for mentioning, @fred-ldrs! @falloutdurham Could you please undo commit f71617202124ebce020d34887f19255e82b33143? I wanted to get rid of the meta information which Pycharm adds automatically, but it seems that it...

Issue should be fixed after merge is done. @falloutdurham Could you please check whether the file opens properly now. Issue may be closed then.

Thank you for mentioning! Just as a hint - it's always really helpful to share the stack trace when encountering an error. :) ### Stack trace Running `Chapter 2.ipynb` on...

Hi @FoxxUI! Could you please share the versions you had installed? I just ran it on Google Colab and it works fine. Versions installed: ``` torch: 1.12.1+cu113 torchvision: 0.13.1+cu113 PIL:...

Hi, you can use the function like ``` your_tweet = "I really liked it!" classify_tweet(your_tweet) ``` But I think you are right. Since `model` is set to eval() mode, it...

Thanks for mentioning and your suggestion, @franzko03! True, the definition as `TWEET = data.Field(tokenize='spacy', lower=True)` raises an exception after upgrading to torchtext 0.8.1. But I think here are two things...

I had the same problems - 0 byte images and logos (despite images with broken url links). I managed it by deleting the affected ones manually, just as a quick...

@falloutdurham Again thinking about this issue with the zero byte images - this shouldn't be a problem as long we use the is_valid_file=check_image argument in the ImageFolder class, does it?...

Yes, there have been a few typos in the book release which have corrected meanwhile, e.g. `train_iterator` not defined. Additionaly the PyTorch API has had some changed which were leading...

Could you please elaborate a bit more on this problem? It might help if you show us the stacktrace and the versions you used. If you use torch < 1.8.x...