weida wang

Is there any news ? I also want this feature !

> baidu yun: > deploy.prototxt > deploy.caffemodel > 链接：https://pan.baidu.com/s/1DK-FngprqYsmC46UrRSldg > 提取码：yv8q 你好，好像过期了，您能再传一遍吗 ？ 万分感谢 ！

@chuanqi305 作者您好，您能分享一下MobileNetv2-SSDLite的预训练模型caffemodel吗（放在README上也行），我这边还要装caffe比较麻烦（我是windows，没有装对应的老版本python），先谢谢了 ！

baidu_cloud download links seems still works, you can click this button to download: 

@nttstar I know there are two anchors for each grid, let me describe my question more detailedly with following image, it is one of the heads of the model: ...

I also guess it maybe related with dataset, the image sizes are veried, the dataset is [this](https://drive.google.com/file/d/1mAJcp9xpmz5kG1tL4MEB4vw6UtY5vT6d/view?usp=sharing). To reproduce this issue, this is the [colab notebook](https://colab.research.google.com/drive/1J7lb9Y1dmlizBpMNKcN0uqbI1FU6al_v?usp=sharing)

I just replace another customized corpus, this time `mfa align` work successfully, so i feel that the pretrained model is strict with the dataset corpus, so what is problem of...

Thanks for your tips ! But even i set `mfa align --beam=1000 --retry_beam=1000`，it still not works:  Meanwhile i tried to train and adapt the acoustic model to new dataset...

Hi, @abidlabs My gallery stores a list of images , I want when I click an image, I can get the image path just like one of list that passed...

Do you have any good solution now ？