Junchao Yan comments

Results 8 comments of


                                            Junchao Yan

Train over new data

Wish to get the reply from the author as soon as possible. I wonder how to fine tune the model using my own dataset.

[Bug]: NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.

meet the same issue either.

I've trained mlstm network with tensorflow using part of the amazon reviews used in this paper[Learning to Generate Reviews and Discovering Sentiment](https://arxiv.org/abs/1704.01444)，but I have not found any senitment neuron. Have...

Embeddings of all nodes are not obtained

I have met the same problem, while I use the data of BlogCatalog, the embedding should be 10312,but line only returns a number of 10263.

Embeddings of all nodes are not obtained

In my case, the issue occur the same. when I use `wc -l line.emb` ,I got 27420 and 27501 in two runs of LINE with the same parameters.

Embeddings of all nodes are not obtained

@mongooma have you change the graph as undirected one ? I have made the change, like this. ``` 1 2 3 5 ``` then, ``` 1 2 2 1 3...

Embeddings of all nodes are not obtained

@mongooma I have found what caused the issue. when you read the edges from file, you must give a weight. ``` fscanf(fin, "%s %s %lf", name_v1, name_v2, &weight); ``` see,...

Embeddings of all nodes are not obtained

@mongooma I don't know either, but I have followed the ReadData() function, when I use the unweighted graph as input, like ``` 1 2 2 1 3 1 1 3...