Tristacheng

Results 5 issues of Tristacheng

您好,请问下MultimodalVideoTag是基于哪个数据集训练的模型呢,可够放一下参考链接呢,非常感谢!

![488452559](https://cloud.githubusercontent.com/assets/12381965/24861862/cecf8bb6-1e2c-11e7-96cb-fd3aab2bda27.jpg) ![841787571](https://cloud.githubusercontent.com/assets/12381965/24861864/d1f7e3ec-1e2c-11e7-8efc-6a97e05d12bc.jpg) ![1657741171](https://cloud.githubusercontent.com/assets/12381965/24861870/d4378afe-1e2c-11e7-951b-d6b98b4696af.jpg) I finetuned vgg-16 on my datasets, it works correctly, but when I turns to ResNet50, just changed the model and the weights, but it reports error like...

你好,我用自己制作的数据集约六万行文字图片训练densenet+CTC,大概20个epoch后训练准确率接近99%,但是模型测试出现问题,只预测一个字或者为空,即使是预测训练集的样本也会出现同样的现象,请教为什么会出现这样的问题呢? ![image](https://user-images.githubusercontent.com/12381965/50765476-fa09c880-12b0-11e9-8e30-2c3660c03028.png) ![image](https://user-images.githubusercontent.com/12381965/50765508-13127980-12b1-11e9-95d8-78d03444d3cf.png)

Hi, I want to implement your code to train on my data but meet some hinders, I'd appreciate if you release the code about how to train you model. Also,...

hi, thank you for your great contribution, but when I test the transferred model,the results are different? do you know why?