def _has_inf_or_nan()

in apex/apex/fp16_utils/loss_scaler.py [0:0]

• 11 lines of code
• 10 McCabe index (conditional complexity)

    def _has_inf_or_nan(x):
        try:
            # if x is half, the .float() incurs an additional deep copy, but it's necessary if 
            # Pytorch's .sum() creates a one-element tensor of the same type as x 
            # (which is true for some recent version of pytorch).
            cpu_sum = float(x.float().sum())
            # More efficient version that can be used if .sum() returns a Python scalar
            # cpu_sum = float(x.sum())
        except RuntimeError as instance:
            # We want to check if inst is actually an overflow exception.
            # RuntimeError could come from a different error.
            # If so, we still want the exception to propagate.
            if "value cannot be converted" not in instance.args[0]:
                raise
            return True
        else:
            if cpu_sum == float('inf') or cpu_sum == -float('inf') or cpu_sum != cpu_sum:
                return True
            return False