docs: fix mismatch between forward method and docstring of NTXentLoss

[adosar]

Under the Examples section of NTXentLoss, the calculation of loss:

>>> # initialize loss function without memory bank
>>> loss_fn = NTXentLoss(memory_bank_size=0)
>>>
>>> # generate two random transforms of images
>>> t0 = transforms(images)
>>> t1 = transforms(images)
>>>
>>> # feed through SimCLR or MoCo model
>>> batch = torch.cat((t0, t1), dim=0)
>>> output = model(batch)
>>>
>>> # calculate loss
>>> loss = loss_fn(output)   # Correct: loss_fn(out0, out1)

doesn't match the function signature of forward, which requires two input tensors:

def forward(self, out0: Tensor, out1: Tensor) -> Tensor:

Suggested change:

>>> # initialize loss function without memory bank
>>> loss_fn = NTXentLoss(memory_bank_size=0)
>>>
>>> # generate two random transforms of images
>>> t0 = transforms(images)
>>> t1 = transforms(images)
>>>
>>> # feed through SimCLR or MoCo model
>>> out0, out1 = model(t0), model(t1)
>>>
>>> # calculate loss
>>> loss = loss_fn(out0, out1)

[guarin]

Thanks for the fix!

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 85.24%. Comparing base (a1d755d) to head (2a1ed02).
Report is 1 commits behind head on master.

Additional details and impacted files

@@           Coverage Diff           @@
##           master    #1789   +/-   ##
=======================================
  Coverage   85.24%   85.24%           
=======================================
  Files         163      163           
  Lines        6833     6833           
=======================================
  Hits         5825     5825           
  Misses       1008     1008           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.