Skip to content

corrected multiclass to multilabel #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
safersephy wants to merge 1 commit into
base: master
Choose a base branch
from
Open

corrected multiclass to multilabel #4

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion notebooks/2_convolutions/01_losses.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -457,7 +457,7 @@
"\n",
"- For regression models, typically use a MSE\n",
"- For classification, use CrossEntropyLoss (note: this might be implemented different in other libraries like Tensorflow!)\n",
"- For multiclass, use BinaryCrossEntropy\n",
"- For multilabel, use BinaryCrossEntropy\n",
"\n",
"There are other, more complex losses for more complex usecases but these three will cover 80% of your needs."
]
Expand Down