cingtiye / Transformer-pytorch
Transformer, pytorch, python
☆19Updated 4 years ago
Alternatives and similar repositories for Transformer-pytorch:
Users that are interested in Transformer-pytorch are comparing it to the libraries listed below
- Focal loss for multiple class classification☆82Updated 4 years ago
- 学习并复现经典的推荐系统多目标任务,如:SharedBottom、ESMM、MMoE、PLE☆35Updated 2 years ago
- ☆20Updated 4 years ago
- ☆78Updated 5 years ago
- Codes for "Learning Sparse Sharing Architectures for Multiple Tasks"☆93Updated 4 years ago
- ChallengeHub开源 的各大比赛baseline集合☆81Updated 3 years ago
- A Strong Baseline for Image Semantic Segmentation☆54Updated 3 years ago
- 2021 huawei DIGIX competition baseline☆69Updated 3 years ago
- 论文阅读以及笔记☆31Updated 4 years ago
- 旨在搭建一个分类问题在Pytorch框架下的通解,批量解决单任务多分类问题、多任务多分类问题。☆56Updated 5 years ago
- 这里是改进了pytorch的DataParallel, 用来平衡第一个GPU的显存使用量☆232Updated 4 years ago
- 机器学习竞赛信息聚合(Machine learning competition information aggregation)☆131Updated last year
- A pytorch implementation of Capsule Network.☆96Updated 9 months ago
- 科技战疫-大数据公益挑战赛-DataFountain重点区域人群密度预测 第1名方案☆38Updated 3 years ago
- The use examples of tensorboard on pytorch☆148Updated 6 years ago
- ☆44Updated 4 years ago
- ☆90Updated 3 years ago
- A Strong Baseline with Many Tricks for Image Classification☆47Updated 2 years ago
- 机器学习实战☆151Updated 2 years ago
- 2020腾讯广告算法大赛复赛rank11(lyu)☆27Updated 4 years ago
- ☆30Updated 5 years ago
- The repository is used to record some useful and reusable codes.☆45Updated 4 years ago
- 2021搜狐校园文本匹配算法大赛Top2方案☆36Updated last year
- ☆24Updated 2 years ago
- 关于Pytorch-Geometric的学习,包括官方文档的基本内容和部分API的使用方式,以及官方源码中的示例代码和Pytorch-Geometric的部分源码实现☆21Updated 4 years ago
- Bert-based text classification☆14Updated 5 years ago
- Open MMLab Detection Toolbox with PyTorch☆34Updated 5 years ago
- Tensorflow version implementation of focal loss for binary and multi classification☆110Updated 6 years ago
- 天池 新冠疫情相似句对判定大赛 top6方案☆76Updated 2 years ago
- 在sts数据集上用多头注意力机制上进行测试。 pytorch torchtext 代码简练,非常适合新手了解多头注意力机制的运作。不想transformer牵扯很多层 multi-head attention + one layer linear☆17Updated 6 months ago