Unverified 提交 ffbce385 authored 作者: HighMans's avatar HighMans 提交者: GitHub

Fix confidence threshold for ClearML debug images (#9174)

* Fix confidence threshold The confidence is converted to a percentage on line 144, but it is being compared to a default conf_threshold value of a decimal value instead of percent value. Signed-off-by: 's avatarHighMans <42877729+HighMans@users.noreply.github.com> * Revert "Fix confidence threshold" This reverts commit f84a09967f83d70626ca8dfe7625dce60fb0102e. * Fix confidence comparison Fix the confidence percentage is being compared to a decimal value. Signed-off-by: 's avatarHighMans <42877729+HighMans@users.noreply.github.com>
上级 cff9717d
......@@ -141,10 +141,10 @@ class ClearmlLogger:
color = colors(i)
class_name = class_names[int(class_nr)]
confidence = round(float(conf) * 100, 2)
label = f"{class_name}: {confidence}%"
confidence_percentage = round(float(conf) * 100, 2)
label = f"{class_name}: {confidence_percentage}%"
if confidence > conf_threshold:
if conf > conf_threshold:
annotator.rectangle(box.cpu().numpy(), outline=color)
annotator.box_label(box.cpu().numpy(), label=label, color=color)
......
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