Shaun ZhouandClaude Opus 5
b0d0dfffbb
- train.py: 先过 require_cuda() 守卫再建模型/数据，支持 --resume 与 --set 覆盖 - eval.py: 允许 CPU，输出定位与分类指标并可写 json - configs: model/dataset/train/eval 四类，通过 `_base_` 组合； classes 既可直接写列表，也可指向 YOLO data.yaml 由框架读 names Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
43 lines
931 B
YAML
43 lines
931 B
YAML
_base_:
|
|
- ../model/tiny_conv.yaml
|
|
- ../dataset/film_defect.yaml
|
|
|
|
work_dir: runs/baseline
|
|
seed: 42
|
|
deterministic: false
|
|
device: cuda # 训练只允许 Nvidia GPU，见 utils/device.py
|
|
|
|
train:
|
|
epochs: 100
|
|
amp: true
|
|
clip_grad: 5.0
|
|
log_interval: 20
|
|
monitor: f1 # 用于挑选 best.pth 的验证指标
|
|
|
|
optimizer:
|
|
name: adamw
|
|
lr: 0.001
|
|
weight_decay: 0.0001
|
|
|
|
scheduler:
|
|
name: cosine
|
|
|
|
loss:
|
|
heatmap_weight: 1.0
|
|
wh_weight: 0.1
|
|
offset_weight: 1.0
|
|
cls_weight: 1.0
|
|
|
|
eval:
|
|
score_threshold: 0.3
|
|
iou_threshold: 0.5
|
|
topk: 50
|
|
|
|
# 训练过程可视化（SwanLab）。未安装或 enabled=false 时自动跳过。
|
|
swanlab:
|
|
enabled: true
|
|
project: film-defect
|
|
name: null # 缺省用 work_dir 的目录名
|
|
mode: online # online(云端) | local(本地看板) | offline(仅存盘) | disabled
|
|
tags: [tiny_conv, center-head]
|