# \#neural-network

**URL:** https://ask.cyberinfrastructure.org/tag/neural-network/163.md

[Latest](https://ask.cyberinfrastructure.org/latest.md) · [Categories](https://ask.cyberinfrastructure.org/categories.md) · [Tags](https://ask.cyberinfrastructure.org/tags.md)

---

## [Optimizing very large neural network that is greater than size of GPU memory](https://ask.cyberinfrastructure.org/t/optimizing-very-large-neural-network-that-is-greater-than-size-of-gpu-memory/427)

<div class="topic-metadata">

**Author:** [@wirawan0](https://ask.cyberinfrastructure.org/u/wirawan0)\
**Replies:** 3\
**Last updated:** [August 17, 2023, 3:10pm UTC](https://ask.cyberinfrastructure.org/t/optimizing-very-large-neural-network-that-is-greater-than-size-of-gpu-memory/427 "2023-08-17T15:10:30Z")

</div>

I encountered a problem with extremely large neural network that was created in KERAS, using Tensorflow backend. The memory footprint in one of the layer is already bigger than the size of current GPU memory (it has just…