我在训练时使用的是SSD512(图像网络预训练模型)和Faster_R-CNN(预训练),丢失和置信度显示为nan,验证为0。
[Basketball-ChainerCV](https://github.com/atom2k17/Basketball-ChainerCV/blob/master/basketballproject.py)。
在训练开始之前训练Faster R-CNN时,在第一组时间段的结果之前会显示以下内容:
/usr/local/lib/python3.6/dist-
packages/chainercv/links/model/faster_rcnn/utils/loc2bbox.py:65:
RuntimeWarning: overflow encountered in exp
h = xp.exp(dh) * src_height[:, xp.newaxis]
/usr/local/lib/python3.6/dist-
packages/chainercv/links/model/faster_rcnn/utils/loc2bbox.py:65:
RuntimeWarning: overflow encountered in multiply
h = xp.exp(dh) * src_height[:, xp.newaxis]
/usr/local/lib/python3.6/dist-
packages/chainercv/links/model/faster_rcnn/utils/loc2bbox.py:66:
RuntimeWarning: overflow encountered in exp
w = xp.exp(dw) * src_width[:, xp.newaxis]
/usr/local/lib/python3.6/dist-
packages/chainercv/links/model/faster_rcnn/utils/loc2bbox.py:66:
RuntimeWarning: overflow encountered in multiply
w = xp.exp(dw) * src_width[:, xp.newaxis]
/usr/local/lib/python3.6/dist-
packages/chainercv/links/model/faster_rcnn/utils/proposal_creator.py:126:
RuntimeWarning: invalid value encountered in greater_equal
我尝试过的事情:
注意:SSD300可以正常运行,但问题在于SSD512和Faster RCNN模型。所有模型都在ImageNet数据集上进行了预训练。
问题背后的问题是什么?谁能指出如何处理此类问题?