Yizhou Wang comments

Results 8 comments of


                                            Yizhou Wang

[ERROR] pip install -e .

@chenhengwei1999 Can you double-check if your cuda is properly installed or version is correct? Thanks @MaximilianArnold ! I will test it later. @chenhengwei1999 , you can also try @MaximilianArnold 's...

running prepare_data.py can not get .pkl,run without error ,can you help me to solve this question?

Have you solved this issue? If not, could you please provide more detailed information on that?

Compile pip install -e . with error

Could you please provide the full error message? I cannot know the reason for your error from this screenshot.

Compile pip install -e . with error

Are you using the TDC module or not? If you are using TDC, please use CUDA=10.1 and pytorch=1.4 as mentioned in readme.

Compile pip install -e . with error

From the log you sent me through email, you were compiling TDC. Please make sure you follow the steps. BTW, we previously did not set up the environment in Windows,...

Compile pip install -e . with error

I think the configurations and environment are mentioned in the readme. We only tested on ubuntu 16, 18, and 20.

`batch_size>1` is not working in the testing phase

Sorry, we didn't try multiple GPUs before. But the performance should not downgrade using multiple GPUs. You may need to tune some parameters or monitor the loss during the training.

`batch_size>1` is not working in the testing phase

I double-checked the inference code. Seems the batch size is hardcoded as 1. We will fix this bug in the future. But for now, you can just use `batch_size =...