使用训练后的模型无法检测出框,不知道什么原因,谁有遇到相似的问题吗?
wangwangww opened this issue · comments
wangwangww commented
liangyaoyao commented
同问,遇上同样的问题,我用了预训练的模型参数初始化模型,再用数据训练的时候损失一下子飙升到两万多。最后也无法检测出框。
AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on EAST, and the significant improvement was also made, which make long text predictions more accurate.https://github.com/huoyijie/raspberrypi-car
wangwangww opened this issue · comments
同问,遇上同样的问题,我用了预训练的模型参数初始化模型,再用数据训练的时候损失一下子飙升到两万多。最后也无法检测出框。