Closed dust-removal closed 1 year ago
你可以修改 mmdet/utils/active_datasets.py
文件中的 update_X_L
函数(它在 tools/train.py
中被调用),令其返回 X_S
,此即为每一轮主动学习后筛选出不确定性较高的新增样本。
You can modify the update_X_L
function in mmdet/utils/active_datasets.py
called by tools/train.py
, make it return X_S
, which are the new selected samples with higher uncertainty after each cycle of active learning.
你可以修改
mmdet/utils/active_datasets.py
文件中的update_X_L
函数(它在tools/train.py
中被调用),令其返回X_S
,此即为每一轮主动学习后筛选出不确定性较高的新增样本。You can modify the
update_X_L
function inmmdet/utils/active_datasets.py
called bytools/train.py
, make it returnX_S
, which are the new selected samples with higher uncertainty after each cycle of active learning.
感谢,我现在发现mmdet2.3.0已经有了支持windows的版本,那是不是在win上运行就有可能了
是的,但我没有尝试过,你可以试一下。
Yes, but I have not tried it. You may have a try.
你好,我刚看完你的论文,我最近有一个应用场景需要使用主动学习,我想知道能够用你的方法仅仅帮我筛选图片,应该怎么做。