File: criterions.py

package info (click to toggle)
pytorch-cuda 2.6.0%2Bdfsg-7
  • links: PTS, VCS
  • area: contrib
  • in suites: forky, sid, trixie
  • size: 161,620 kB
  • sloc: python: 1,278,832; cpp: 900,322; ansic: 82,710; asm: 7,754; java: 3,363; sh: 2,811; javascript: 2,443; makefile: 597; ruby: 195; xml: 84; objc: 68
file content (10 lines) | stat: -rw-r--r-- 212 bytes parent folder | download | duplicates (4) 
1
2
3
4
5
6
7
8
9
10
 
import torch.nn as nn


def cel(rank):
    r"""A function that creates a CrossEntropyLoss
    criterion for training.
    Args:
        rank (int): worker rank
    """
    return nn.CrossEntropyLoss().cuda(rank)