Shuai Zhang

Usually, we only consider recommending those items that the user has never seen. If an item is liked by the user, we don't want to repeatedly recommend it to him.

I see. let me know when it is ready to merge. Thanks!

We don't have a benchmark yet.

Hi @dragoonchang Thank you very much for your suggestion, I will take it into consideration.

I have revised the loss. self.loss = tf.reduce_sum((1 + 0.1 * self.y ) * tf.square(self.beta * (self.one - self.y) - self.pred_y))

oh, sorry about that, it should be 1.

@zijinchen it is a draft, so there are some redundant codes. You can just ignore it.

what is the current Cuda version on the server? @AnirudhDagar > @cheungdaven seems like paddle is not able to find CUDA device. Similar issue in #1103

> > We've both CUDA 11.2 and CUDA 10.2. > > hello，do you need a paddlepaddle engineer to solve the problem together? Hi @tngt , I am looking into this...

> Hi @tngt, > > @cheungdaven and I looked into the issue. The problem here is that `d2lbook` [intelligently](https://github.com/d2l-ai/d2l-book/blob/d933bfa91ce03ab6111db648045a1169060f99b7/d2lbook/resource.py#L30) only wants to assign GPUs to the notebooks which really demand...