[Fix] Support bce loss without batch augmentations

[KeiChiTse]

A quick fix to issue #1520. refer to https://discuss.pytorch.org/t/multi-label-binary-classification-result-type-float-cant-be-cast-to-the-desired-output-type-long/117915

[CLAassistant]

All committers have signed the CLA.

[codecov]

Codecov Report

Patch coverage has no change and project coverage change: +0.54 🎉

Comparison is base (c9a0cb0) 84.37% compared to head (006c4cf) 84.91%.

❗ Current head 006c4cf differs from pull request most recent head e085bcd. Consider uploading reports for the commit e085bcd to get more accurate results

Additional details and impacted files

@@            Coverage Diff             @@
##              dev    #1525      +/-   ##
==========================================
+ Coverage   84.37%   84.91%   +0.54%     
==========================================
  Files         142      230      +88     
  Lines        9925    17555    +7630     
  Branches     1621     2758    +1137     
==========================================
+ Hits         8374    14907    +6533     
- Misses       1277     2130     +853     
- Partials      274      518     +244     

Flag	Coverage Δ
unittests	84.91% <ø> (+0.54%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

see 372 files with indirect coverage changes

☔ View full report in Codecov by Sentry.
📢 Do you have feedback about the report comment? Let us know in this issue.

[Ezra-Yu]

LGTM.