forked from ccf-ai-infra/GPUCodeForces
29 lines
894 B
Python
29 lines
894 B
Python
|
import torch
|
|||
|
|
import torch.nn as nn
|
|||
|
|
import torch.nn.functional as F
|
|||
|
|
|
|||
|
|
BATCH_SIZE = 4096
|
|||
|
|
NUM_CLASSES = 1000 # 假设分类类别数
|
|||
|
|
FEATURE_DIM = NUM_CLASSES # CrossEntropyLoss输入最后一维为类别数
|
|||
|
|
|
|||
|
|
class Model(nn.Module):
|
|||
|
|
|
|||
|
|
def __init__(self):
|
|||
|
|
super().__init__()
|
|||
|
|
# CrossEntropyLoss 会自动包含 LogSoftmax + NLLLoss
|
|||
|
|
self.criterion = nn.CrossEntropyLoss(reduction='mean')
|
|||
|
|
|
|||
|
|
def forward(self, input: torch.Tensor, target: torch.Tensor) -> torch.Tensor:
|
|||
|
|
return self.criterion(input, target)
|
|||
|
|
|
|||
|
|
def get_inputs():
|
|||
|
|
# CrossEntropyLoss 输入：logits [N, C]
|
|||
|
|
input_scores = torch.randn(BATCH_SIZE, FEATURE_DIM, dtype=torch.float32)
|
|||
|
|
|
|||
|
|
# 目标标签：每个样本一个类别索引（0 ~ C-1）
|
|||
|
|
target = torch.randint(0, FEATURE_DIM, (BATCH_SIZE,), dtype=torch.long)
|
|||
|
|
|
|||
|
|
return [input_scores, target]
|
|||
|
|
|
|||
|
|
def get_init_inputs():
|
|||
|
|
return []
|