At this moment relu_layer op doesn't allow threshold configuration, and legacy RELU op allows that.
We should add configuration option to relu_layer.

• APEX optimization levels are “O1, O2, O3” and not “01, 02, 03”. We should fix this in code + docs.

Make sure it is clear from the docs that the use of Apex anymore and recommend that users use upstream native AMP available since PyTorch 1.6

Currently, when entering epic mode the README is frozen in the last level of the tower. When you're trying to fine-tune the score for a level other than the last one, it would be helpful if we had the README for that level available. The proposal is that when entering epic mode, the README is updated with all levels, one following the other.

Example:

# Starbolt - beginner

Documentation Is:

• Missing
• Needed
• Confusing
• Not Sure?

E

Hello spoooopyyy hackers 🎃

This is a Hacktoberfest only issue! 👻

This is also data-sciency!

The Problem

Our English dictionary contains words that aren't English, and does not contain common English words.

Examples of non-common words in the dictionary:

"hlithskjalf",
  "hlorrithi",
  "hlqn",
  "hm",
  "hny",
  "ho",
  "hoactzin",
  "hoactzine