actpred: 代码审计(16项发现全部修复)+ 文档更新

审计报告: docs/reviews/actpred_CODE_AUDIT_20260808.md
- P0(2项): episode索引错位(dataset.py)、推理归一化静默失败(predict.py)
- P1(6项): 空训练集校验、图像自然排序、空样本防御、形状校验、
  MobileNet下载错误提示、stats路径校验
- P2(8项): README示例修正、公共属性、glob优化、版本约束、
  单元测试(17项)、GPU安装说明、BooleanOptionalAction、ONNX验证

新增文件: actpred/test_actpred.py (17项单元测试, 全部通过)
更新文档: README.md配置表扩充、INDEX.md、审计报告修复总结
This commit is contained in:
qing committed 2026-08-08 16:05:01 +00:00
1 parent 1e34348d6c
commit 3d03f7a1ce
19 files changed
+850 -177

No files matched your search

+10 -1
View File
@@ -30,7 +30,16 @@ class MobileNetEncoder(nn.Module):
def __init__(self, feature_dim: int = 128):
super().__init__()
from torchvision.models import mobilenet_v2, MobileNet_V2_Weights
backbone = mobilenet_v2(weights=MobileNet_V2_Weights.DEFAULT)
try:
backbone = mobilenet_v2(weights=MobileNet_V2_Weights.DEFAULT)
except Exception as e:
raise RuntimeError(
"MobileNetV2 预训练权重下载失败,可能是网络受限。"
"请在联网环境中预下载权重"
"(运行 torchvision.models.mobilenet_v2(weights='IMAGENET1K_V1')),"
"并将 ~/.cache/torch/hub/checkpoints/ 下的权重文件"
"拷贝到目标机器同路径。"
) from e
self.features = backbone.features
self.pool = nn.AdaptiveAvgPool2d(1)
self.proj = nn.Linear(1280, feature_dim)