Why does this line not instantiate a class?

Question

I am a python beginner going over a tutorial on neural networks and the PY torch module. I don't quite understand the behavior of this line.

import torch.nn as nn

loss = nn.MSELoss()

print(loss)

>>MSELoss()

Since nn.MSELoss is a class, why does calling it to the variable loss not instantiate it as a class object? What type of code is in the class MSELoss that allows it to achieve this behavior?

Answer 1

When you print some object you're actually calling its __str__ method in Python or if it isn't defined then __repr__ (from representation).

In your case, it's about normal class, but its __repr__ has been overriden:

def __repr__(self):
    # We treat the extra repr like the sub-module, one item per line
    extra_lines = []
    extra_repr = self.extra_repr()
    # empty string will be split into list ['']
    if extra_repr:
        extra_lines = extra_repr.split('\n')
    child_lines = []
    for key, module in self._modules.items():
        mod_str = repr(module)
        mod_str = _addindent(mod_str, 2)
        child_lines.append('(' + key + '): ' + mod_str)
    lines = extra_lines + child_lines

    main_str = self._get_name() + '('
    if lines:
        # simple one-liner info, which most builtin Modules will use
        if len(extra_lines) == 1 and not child_lines:
            main_str += extra_lines[0]
        else:
            main_str += '\n  ' + '\n  '.join(lines) + '\n'

    main_str += ')'
    return main_str