Santosh Gupta

It looks like we just need to put the source, followed by the summary in each line, separated by a unique token?

it looks like the tensorflow uses a different function to calculate loss compared to the keras version, so the two are not comparable.

So far, I put this in my user setting, which is working decently. "workbench.colorCustomizations": { "editor.selectionBackground": "#4d057b" //Current selected text }  The color is from Amethyst's editor.selectionBackground color. https://github.com/eamodio/vscode-amethyst-theme/blob/master/themes/amethyst-theme.json#L39...

Are there any plans for an entire goodreads user review dataset? I started a script here, but it needs some work https://colab.research.google.com/drive/1uOyVlKaT4QFtce9yQpKj9hRtj5z8Uyta It downloads reviews directly from rss feeds, so...

Hi xscjun, That is very confusing. I am investigating by trying to recreate the issue. So far I am unable to re-create the issue in Colab. Here's the code I...

Glad you were able to get it working. I am wondering what the cause is; I did all my testing in Python 3.

I noticed Colab has Python 3.6.8 by default, so perhaps there is something off about 3.7. Are you able to recreate the issue in Colab? Is the 'data.npy' the same...

> I got OOM error, how can I deel with it? BTY, how can I load multiple data in one container？ > `gadgetGPU = SpeedTorch.DataGadget(target_mel) gadgetGPU.gadgetInit() Traceback (most recent call...

It looks like the data format is incorrect. It looks like there's an issue with how you're saving the data, and/or how your zipping the file. Checkout this notebook, which...

Yup, I forgot the exact commands, but you can access your embedding data and mount them to CPU, in numpy form. It looks something like this YourModel.YourEmbeddingVariable.Weight.data.cpu().numpy() details https://discuss.pytorch.org/t/how-to-transform-variable-into-numpy/104/5