guanghuixu

I met the same problem， do you have any idea?

Thanks for sharing your code. I want to know how can I train a model in word_level? I found you code has the things like ( use_char = Ture, use_word...

电脑能跑了，原来只是太久了。 我可以定义新的风格？我执行conf没有的文件的话是会报错的耶，python train.py -c conf/guanghuixu.yml。 另外，我还想问一下，像我这样执行，使用VGG跟那个数据集，那它会生成一个yaml文件？里面包含风格？我都没有指定它生成什么风格。我要怎样子才会生成像我执行eval一样的那种yaml？ 问题有点多，新手，不好意思，，O(∩_∩)O

Do you want to run the TextCap model on COCO dataset? The COCO dataset doesn't contain the OCR annotations, so that we cannot build the `global_graph` on it. But you...

what's the "model path" ??

Can you provide the pretrain model ??? Thank you very much !!!