Transformer Architecture -Assignment

Course Q&A Deep Learning Specialization Sequence Models
1

In the transformer network, I get error when running Decoder Layer. It says

“InvalidArgumentError : cannot compute Einsum as input #1(zero-based) was expected to be a int64 tensor but is a float tensor [Op:Einsum]”

I am unable to resolve this issue. I request some one in the group to give me some hint to solve.

Thanks
Usha

2

Was this issue resolved?

3

Hi,

Thank you for all the support. I have completed the Deep Learning Specialization course.
I want to back up my assignment work for my future reference and study. However, some of the files do not have the code I had written. It appears to be a new, fresh notebook and not the one I have worked on. How do I get back my program exercises? Since my 3 months schedule is still open, I thought I must be able to re-run my assignments for practice.

Thank you
Usha

4

When the assignment is updated, your previous notebook is saved in your workspace with a file name that includes a date code.

You can find this file using the “File → Open” option in the notebook toolbar.

5

Thank you. I am able to open my updated file.
How long will I be able to access these files? Will I be able to atleast open the files in the notebook after the subscription period is over?

Thank you once again for the quick response.
Usha

6

You should download all of your notebook files to your local computer before your subscription ends.