I have two layers which each contain a single npm package. Neither are being recognized by Lambda as existing when testing the function. I get the error log:
The layers are
and "tensorflowJS" is a layer containing a zipped node package with tensorflowjs installed in the same runtime as the layer's function. Are there additional configurations I'm missing to run an ML model serverlessly?
What is the structure of the files within the zip you used for these layers?
The documentation shows some examples:
So make sure you have a nodejs
folder inside the zip, then a node_modules
folder within that, then your code within that.
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.