-
Notifications
You must be signed in to change notification settings - Fork 1.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
why optimize throws java.lang.ArithmeticException(divide by zero) #2278
Comments
The error is thrown by CachedDistriDataSet, when SampleMiniBatch call
Seems @Justontheway May I ask how did you get this error message? Which example are you running? |
The original data format like this
|
@Justontheway |
And then I do the following transformations
Clear? |
@Justontheway |
I just use the similar model, but dataset is different. The real dataset is about N x 600 x 800, and non-zero element is about 100 more or less for each 2D matrix. |
@Justontheway The non-zero elements will increase |
@qiuxin2012 SpatialConvolution needs 3D tensor, while SparseTensor only support 2D. Also, I have transformed SparseTensor to DenseTensor before trainning in order to get 3D tensor. Maybe it is great to pvovide something like np.stack tf.stack scipy.sparse.coo_matrix.toarray. |
@Justontheway I'm so sorry, I forget this issue after Spring Festival. How is everything on going? |
@qiuxin2012 go back to tensorflow ~ ~ ~ |
@Justontheway I had a similar error, was solved by increasing dataset size and batch size. No idea why |
I think it's the size of dataset is too small, as bigdl will split the dataset(random split, don't ensure perfectly uniform size) into num-executor paritions, one of the partition's lenght maybe empty. After you increase the dataset size, the empty parition has data. |
Env Info
BigDL - v0.4.0
Spark - 1.6.3
Error Info
The text was updated successfully, but these errors were encountered: