I'm trying to package my trained Keras classifier models (Theano backend) and their HDF5 weights as AWS Lambda functions that process classification requests coming from an API. Lambda has a 50MB limit for the zip file that contains the function code and dependencies, so I'm wondering whether any of the dependencies needed for training are not needed for prediction, so that I can leave them out of the Lambda zip file. Right now I'm just squeaking by at ~45MB with all dependencies (numpy, scipy, etc.), but I'd like to drop any dead weight if possible.
Add a comment |
This question is in a collective: a subcommunity defined by tags with relevant content and experts.
- The Overflow Blog
-
-
- Featured on Meta
-
-
-
Related
Hot Network Questions
- Why are they called Terafim?
- Did Indy need to access the map room?
- Can you scatter caltrops into a space controlled by an enemy?
- How do we define active symmetries on gauge fields in theories on general manifolds?
- Can a number have the same digit sum and digit product?
- Basic questions about starting an individual PhD in Germany that I haven't found answers to
- Should I standardize or only center "Age" in an ordinal semiparametric regression model?
- Do you die sooner if you retire later?
- Cambridge to Utrecht with less carbon than flying
- Why can std::string only create a constexpr object if it's a static variable?
- Does there exist a number such that the first 16 numbers of its Collatz sequence mod 4 contain four 1s, 2s, 3s, and 4s?
- Are quantum wavefunctions required to be analytic?
- What is the difference between the classical decision theoretic setting and the decision theoretic setting in ML and statistical learning?
- Is Financial Services Protection limit relevant for Pensions?
- Why did the 8087's constant ROM contain the value ln(2)/3?
- Section title with \star
- On an interesting product involving Jacobi sums over a finite field
- Question on a calculation in Weisskopf's 1939 paper on the electron self-energy
- Definition of tightness
- SQL Server with Latin1_General_CI_AS collation migrating to Postgres 18
- Are Old Methusalah-type Stars in Faraway Galaxies?
- Do higher damage bows shoot farther?
- How do I generate +4.5 V and -4.5 V from a 9 V battery using an opamp?
- PSE Advent Calendar 2025 (Day 2): Decorating in the Midst of Purple Skies
lang-py