Willirene comments

Results 8 comments of


                                            Willirene

After training by the default args, the result isn't good

Thanks, it works! 還想再請教另外一個問題，在training時，我發現到 loss 會往負數的方向不斷下降，變到負的兩三萬以上，請問這樣是否代表 loss 不會收斂呢? 因為似乎可以永無止盡地降下去

Question about the propagation in matrix form

Same question here, and I have another questions: `bi_embeddings = tf.multiply(ego_embeddings, side_embeddings)` whats dose bi mean? I didn't see it in the paper.

why stop_gradient

Same question here

FileNotFoundError: [Errno 2] No such file or directory: 'saved_model/best_imdb_DMGI_MAM,MDM.pkl'

Same problem here, did you solved it?

Code in .ino?

@xiaoyu2016 So....Could you explain how to run this code on Arduino, please?

Auxiliary losses implementations

> Hi, Guadalupe is right that it was cross entropy loss for link pred loss. The reason is that since the assignment prediction contains values between [0,1], cross entropy is...

Cannot use GPU when output.shape[1] * nnz(a) > 2^31

Same problem here.

Cannot use GPU when output.shape[1] * nnz(a) > 2^31

> You can cast the sparse matrix to dense matrix and use tf.matmul But if we have a large matrix with most of zero, we would like to use sparse...