Mingkun Yang

I think I have solved this bug. It is caused by the parallel for loop. While using the openMP for parallel computing, [this line](https://github.com/ZhouYanzhao/ORN/blob/pytorch/install/orn/src/generic/ActiveRotatingFilter.c#L32) and [this line](https://github.com/ZhouYanzhao/ORN/blob/pytorch/install/orn/src/generic/ActiveRotatingFilter.c#L74) can not be...

Do you know some examples about STN used as attention mechanism？

Thanks. But I am still confused. For example, the topic id of the first line in the train.info.full.txt is 4132, but the line 4132 of train.model is 1 49:1. What's...

I see train.model has a more leading line than .vocab. Do them have the same index? For example, the line 4134 in the train.model corresponds to the word of line...

But I only have 100 topics. So the number of columns of train.model is less than or equal to 100. I can't get the 4132-th column?

But the author got a 0.661 mAP on VOC07 while the origin paper got a 0.699 mAP. The author said we may need to tune the loss function defined in...

论文里面介绍过，分别对应的是[SynthText (ST)](http://www.robots.ox.ac.uk/~vgg/data/scenetext/) and [MJSynth (MJ)](http://www.robots.ox.ac.uk/~vgg/data/text/)

For details can be found [here](https://github.com/ayumiymk/aster.pytorch/blob/master/lib/utils/labelmaps.py#L12). If your special characters are out of vocabulary, the pretrained model can't handle. Therefore, you need to re-train a new model with your self-defined...

没了解过，如果你弄好了的话，可以提一个PR

> > 没了解过，如果你弄好了的话，可以提一个PR > > 我之前尝试了一下。失败了，后来把模型分成矫正和识别两部分，矫正的部分转成功了，识别的部分还是失败。只对转换所使用的那张图片有用，对其他图片没用。 识别部分失败的原因是啥？是因为LSTM吗