Learning入门

Results 34 comments of Learning入门

> > _No description provided._ > > 取出最后一层的bert输出,然后后面接你要加入的其他模型即可,具体可以看其他代码 这个是微调吧。。。想把bert的词表embedding裁剪或者增加到自己的词表,,,这个您知道怎么操作么

hello, do you know 'python3 model.py --dataset dataset/$1-character/dataset.pkl' where is the 'dataset'

> docker image: ![CleanShot 2023-12-15 at 11 12 25](https://private-user-images.githubusercontent.com/6077601/290714659-38ba1382-ff83-456c-bb6c-b69abc313209.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MTY3MDkxOTUsIm5iZiI6MTcxNjcwODg5NSwicGF0aCI6Ii82MDc3NjAxLzI5MDcxNDY1OS0zOGJhMTM4Mi1mZjgzLTQ1NmMtYmI2Yy1iNjlhYmMzMTMyMDkucG5nP1gtQW16LUFsZ29yaXRobT1BV1M0LUhNQUMtU0hBMjU2JlgtQW16LUNyZWRlbnRpYWw9QUtJQVZDT0RZTFNBNTNQUUs0WkElMkYyMDI0MDUyNiUyRnVzLWVhc3QtMSUyRnMzJTJGYXdzNF9yZXF1ZXN0JlgtQW16LURhdGU9MjAyNDA1MjZUMDczNDU1WiZYLUFtei1FeHBpcmVzPTMwMCZYLUFtei1TaWduYXR1cmU9NjdhMWQ0YWM4Nzg3MWE2MTUxNjYyNjk0NDhkMThmMTEyZDY4NTI0ODYwN2M2MmJkOWRlOTZhOGM5ZTI0ZjNhZSZYLUFtei1TaWduZWRIZWFkZXJzPWhvc3QmYWN0b3JfaWQ9MCZrZXlfaWQ9MCZyZXBvX2lkPTAifQ.5FPWJZWp9mPFoXs-V3lia5FJXOT4h0QBiEr66YTw5kU) > > ![image](https://private-user-images.githubusercontent.com/6077601/290714620-982762b3-b6a1-404b-a896-b725034e9762.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.h9d1bkWaAk1cQhzzuKKdVkAwbwWQSEtyz0hkIULfhMk) how to reslove it , pls

你的target_tensor是 ``` target_img = generate_img(target_word, target_font_file, font_size=60) target_tensor = totensor(target_img).unsqueeze(0) ``` 这么得到的,送入到网络forward ``` def forward(self, lx, rx): rout = self.right(rx) ... de_0 = self.deconv1(torch.cat([lout_5, rout_5], dim=1)) ... return de... ```...

请问你的训练数据是什么,多大

私有化模型是指本地部署的xinference ,提供的模型吗

诚心请教下 0.2.10 版本怎么修改并发

用户权限管理、知识库管理这种,请问后续有考虑新增吗? 还是说不会继续更新新功能了