沧海桑田 issues

Results 237 issues of


                                            沧海桑田

In the paper, what is the detail setting of supervised learning? Is SL has additional supervised data?

https://openreview.net/forum?id=8aHzds2uUyB Thank you very much!

A question bother me a long time: What is the difference between RL-for-text-generation and delete-0-reward-model-predictions?

For text gereration. Thank you very much!

Is each token (to-embedding) value an integer?

Is each token (before-embedding) value an integer? In practice, where is this done? The code `self.head = nn.Linear(self.num_features, num_classes)` seems not output integers? Thank you very much!

弱问下训练一个tokenizer的训练目标是什么？

多谢！

I use this command, but the word-cut results are same to space-split. Thank you very much.

`java -cp "stanford-corenlp-4.5.6/*" edu.stanford.nlp.international.arabic.process.ArabicTokenizer useUTF8Ellipsis,normArDigits,normArPunc,normAlif,normYa,removeDiacritics,removeTatweel,removeQuranChars,removeProMarker,removeSegMarker,removeMorphMarker,removeLengthening,atbEscaping < input.txt` Thank you very much @AngledLuffa @J38 @gangeli @rayder441 @angelxuanchang

How monocular depth estimation specifically guides subsequent processes such as robot navigation?

Thank you for examples. Thank you.

What is the principle, I can not understand. Why does the design of self-supervised loss functions achieve monocular depth estimation?

Thank you for explanation. Thank you.