Unverified 提交 d2e7ba2a authored 作者: Glenn Jocher's avatar Glenn Jocher 提交者: GitHub

val.py `--weights` and `--data` compatibility check (#7292)

Improved error messages for understanding of user error with val.py. May help https://github.com/ultralytics/yolov5/issues/7291
上级 5f97001e
......@@ -162,6 +162,10 @@ def run(
# Dataloader
if not training:
if pt and not single_cls: # check --weights are trained on --data
ncm = model.model.yaml['nc']
assert ncm == nc, f'{weights[0]} ({ncm} classes) trained on different --data than what you passed ({nc} ' \
f'classes). Pass correct combination of --weights and --data that are trained together.'
model.warmup(imgsz=(1 if pt else batch_size, 3, imgsz, imgsz)) # warmup
pad = 0.0 if task in ('speed', 'benchmark') else 0.5
rect = False if task == 'benchmark' else pt # square inference for benchmarks
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论