dssm icon indicating copy to clipboard operation
dssm copied to clipboard

DSSM and Multi-View DSSM

Results 14 dssm issues
Sort by recently updated
recently updated
newest added

用”siamese_bert“模型,在80万公司数据集上,1(正):4(负),跑出来的cos倒排,感觉完全不靠谱,发愁 auc: 0.64 准确率: 0.75

想请教一下,对bert输出的所有token做平均池化的代码是什么?如何添加呢?

![image](https://user-images.githubusercontent.com/19704825/62911752-15453500-bdb8-11e9-887e-266809937cd5.png) 如图,训练和测试样本都是5000个,随机从oppo_round1_train_20180929.txt中采样的

![image](https://user-images.githubusercontent.com/548443/127103641-8a56ad30-b5cb-406a-bc45-4a2aed7c7089.png) 在40%-80%之间跳。 是实现有bug?

训练集使用的oppo_round1_train_20180929.txt 验证使用的oppo_round1_vali_20180929.txt 请问有人遇到相似情况吗 ![image](https://user-images.githubusercontent.com/19704825/67648765-9ea8e400-f971-11e9-96fc-9e99dd5bcf88.png)

👋 Hello, @InsaneLife - a potential high severity Deserialization of Untrusted Data vulnerability in your repository has been disclosed to us. #### Next Steps 1️⃣ Visit **https://huntr.dev/bounties/1-other-InsaneLife/dssm** for more advisory...

你好,请问mac或者linux可以训练吗

multi_view_data_input.py 没找到。 可以发我一份吗?

请问有谁用全量数据训过吗?大概需要多大的内存空间?带GPU的呢?