Fighting-JJ
Fighting-JJ
Have you solved it? I trained on dataset synth90k , and test accuracy never crossed 0.86. I dont know is there any promotion can be done.
> when I use 4 GPUs to train the model with batchsize 256 and learning rate 0.001, loss descent speed is very slow, but when using just single GPU with...
@hzli-ucas You can print out the wrong predictions, then you can see the model can not classify uppercase i and lowercase L and so on. as long as you remove...
看下readme 有讲解原理的网页链接
python 3.6 works well
> 用trace转模型,再用libtorch部署吧,亲测可用 trace 可以成功么?你训练的什么arch的模型? @BokyLiu
> > @zoufangyu1987 @kunyao2015 > > 实现步骤: > > 1、把模型转成caffemodel; > > 2、前后处理自己c++实现; > > 3、Done! > > 亲测可以,祝你好运! > > 转caffe时候的DCNV2怎么办?caffe又不是天然支持 请问,你解决了DCNv2的部署问题么?
> 我已经把pytorch全部剥离,在python上依赖numpy正常跑通了,下一步转C++,发现numpy有C++版本——"numcpp",搞得身心疲惫,希望后面少点坑! > I've stripped all pytorch and relied on numpy to run normally on python. Next, I turn to C++. I find that numpy has a version of C++...
> > > > 我已经把pytorch全部剥离,在python上依赖numpy正常跑通了,下一步转C++,发现numpy有C++版本——"numcpp",搞得身心疲惫,希望后面少点坑! > > I've stripped all pytorch and relied on numpy to run normally on python. Next, I turn to C++. I find that numpy has...