modified: .DS_Store
modified: checkpoints_final/task1_final/task1_final_model.pkl new file: checkpoints_final/task1_final/task1_tmd_adapter.pkl new file: scripts_4/README.md new file: scripts_4/__init__.py new file: scripts_4/__pycache__/adapter.cpython-314.pyc new file: scripts_4/adapter.py new file: scripts_4/predict_tmd_single.py new file: scripts_4/train_tmd_adapter.py
This commit is contained in:
45
scripts_4/README.md
Normal file
45
scripts_4/README.md
Normal file
@@ -0,0 +1,45 @@
|
||||
# scripts_4: TMD 小样本适配
|
||||
|
||||
本目录实现二阶段方案:
|
||||
|
||||
1. 基础模型(`Non_TMD` 训练得到的 `task1_final_model.pkl`)先给出基线预测;
|
||||
2. 用极少量 `TMD` 样本拟合频率相关比例系数 `k(f)`;
|
||||
3. 输出 `TMD` 预测:`y_tmd = k(f) * y_base`。
|
||||
|
||||
## 为什么这样做
|
||||
|
||||
- 仅 5 个 TMD 点直接重训主模型容易过拟合;
|
||||
- 保留基础模型泛化能力,只学习域偏移;
|
||||
- 通过 `shrinkage` 把校正系数向 `1.0` 收缩,降低小样本波动影响;
|
||||
- 频率外推时会自动向 `1.0` 回归,避免越界夸张。
|
||||
|
||||
## 脚本说明
|
||||
|
||||
- `train_tmd_adapter.py`:拟合并保存适配器,同时输出 LOOCV 报告。
|
||||
- `predict_tmd_single.py`:加载基础模型 + 适配器,对单个 TMD 文件推理。
|
||||
- `adapter.py`:频率校正器定义与序列化工具。
|
||||
|
||||
## 使用方法(请使用虚拟环境 Python)
|
||||
|
||||
```bash
|
||||
.venv/bin/python scripts_4/train_tmd_adapter.py
|
||||
```
|
||||
|
||||
```bash
|
||||
.venv/bin/python scripts_4/predict_tmd_single.py \
|
||||
--file downloads/TMD/val/harmonic_5mm_1.25Hz_TMD.csv
|
||||
```
|
||||
|
||||
可选参数示例:
|
||||
|
||||
```bash
|
||||
.venv/bin/python scripts_4/train_tmd_adapter.py \
|
||||
--shrinkage 0.25 \
|
||||
--extrapolation-decay-hz 0.3
|
||||
```
|
||||
|
||||
## 输出文件
|
||||
|
||||
- 适配器:`checkpoints_final/task1_final/task1_tmd_adapter.pkl`
|
||||
- 报告:`evaluation_outputs/task1_final/tmd_adapter_report.json`
|
||||
|
||||
Reference in New Issue
Block a user