Closed Royalvice closed 6 months ago
运行example.py得到如下结果 PointCould x Text: tensor([[8.5200e-04, 9.5644e-02, 5.8601e-01, 1.9369e-02, 2.9812e-01], [8.8911e-04, 1.7004e-01, 3.2570e-01, 1.1302e-02, 4.9207e-01], [2.9327e-04, 6.9276e-02, 4.6433e-01, 1.2254e-02, 4.5384e-01], [1.9555e-03, 7.8262e-02, 3.8027e-01, 5.8164e-02, 4.8135e-01], [3.0467e-04, 1.0489e-01, 4.9719e-01, 2.1044e-02, 3.7657e-01]], device='cuda:0')
你好,感谢指出错误。模型配置已经更新: link,请更新模型配置后重新运行example.py。
== Thanks for pointing this out. We have updated the model config here for the released vitlensL. You may pull the latest code and run example.py to get the expected result.
example.py
运行example.py得到如下结果 PointCould x Text: tensor([[8.5200e-04, 9.5644e-02, 5.8601e-01, 1.9369e-02, 2.9812e-01], [8.8911e-04, 1.7004e-01, 3.2570e-01, 1.1302e-02, 4.9207e-01], [2.9327e-04, 6.9276e-02, 4.6433e-01, 1.2254e-02, 4.5384e-01], [1.9555e-03, 7.8262e-02, 3.8027e-01, 5.8164e-02, 4.8135e-01], [3.0467e-04, 1.0489e-01, 4.9719e-01, 2.1044e-02, 3.7657e-01]], device='cuda:0')