freecui

paddle_infer.create_predictor(config) 预测报错

7

### bug描述 Describe the Bug 环境：版本 python3.8.0 cuda10.1.105; cudnn 7.6.5 ； paddlepaddle 2.3.1 用了gpu和cpu版本； 跑的是https://github.com/PaddlePaddle/ERNIE 项目中的task有 text_generation 和text_matching, 这两个task 训练的时候都是可以正常运行的，但是infer的时候就出错了，代码段是在erniekit/controller/inference.py 中的predictor = paddle_infer.create_predictor(config) 这段代码就会出现错：不管用cpu还是gpu都会报同样的问题 ![Uploading image.png…]() ### 其他补充信息 Additional Supplementary...

Error Message Summary---ernie_gen

5

-------------------------------------- C++ Traceback (most recent call last): -------------------------------------- 0 paddle_infer::Predictor::Predictor(paddle::AnalysisConfig const&) 1 std::unique_ptr paddle::CreatePaddlePredictor(paddle::AnalysisConfig const&) 2 paddle::AnalysisPredictor::Init(std::shared_ptr const&, std::shared_ptr const&) 3 paddle::AnalysisPredictor::PrepareProgram(std::shared_ptr const&) 4 paddle::framework::NaiveExecutor::CreateVariables(paddle::framework::ProgramDesc const&, int, bool, paddle::framework::Scope*) ----------------------...

https://medium.com/@aloofness54/fix-google-seq2seq-installation-errors-4a1155b13f73

声音有点抖，有点沙哑

25

请听一下我的这个结果，听着某些词或者字有点抖有点沙哑，特别是抖，不知道原因是什么？ [1350.zip](https://github.com/fatchord/WaveRNN/files/4219508/1350.zip)

wav2lip:The lip color is darker than a original video

2

The problem is that the lip's color of a video from wav2lip.py is darker than a original video This is original video: 

How to weight loss function

9

I have an extreme imbalanced dataset for muticlass task . To handle the imbalance, I want to weight loss function