JacobianTang
JacobianTang
在中文实验上很明显backbone(特征提取网络)增强之后,结果变好了。但是真是情况应该是中英文混合,或者整个测试集里面既有英文也有中文,以我的经验来看,感受野大了之后,对英文来说未必是好事。所以backbone的那一栏实验结果,不知道在混合数据集上表现如何? 方便透漏下个人邮箱吗?希望和你通过邮箱有进一步交流。
Hi: I have a question about side-refinement.Traing time,you regress the anchor's relative offset to bounding.Testing time,what do you do ? We can get the text proposal according the defalut anchor,...
I am so sorry.when i run this code ,i got a error! X Error of failed request: BadRequest (invalid request code or no such operation) Major opcode of failed request:...
hi,learning rate in the "MultiStageMeanfield" layer is smaller than same layer in the orginal project (https://github.com/torrvision/crfasrnn).I want to know the difference. thanks ! The learning rate of "Deconvolution" layer is...