aboutsummaryrefslogtreecommitdiff
path: root/README.md
diff options
context:
space:
mode:
authorJonny Svärd <jonny.svaerd@arm.com>2023-06-12 13:06:05 +0200
committerJonny Svärd <jonny.svaerd@arm.com>2023-06-12 13:06:05 +0200
commit114c2379d746ff30aa12f5977fb4c2e2abc51fd8 (patch)
treee1141c0b2532b8aa936149dcc341c5a477460498 /README.md
parent87c0cce274abf4766400049f372019f86e6ab96d (diff)
downloadethos-u-114c2379d746ff30aa12f5977fb4c2e2abc51fd8.tar.gz
Minor README formatting fix
Change-Id: I4239e7d4862115d6124900ee5b24688e01ea8c3b
Diffstat (limited to 'README.md')
-rw-r--r--README.md9
1 files changed, 6 insertions, 3 deletions
diff --git a/README.md b/README.md
index 29441e5..1168b8b 100644
--- a/README.md
+++ b/README.md
@@ -108,9 +108,12 @@ There's a discrepancy in tensorflow/lite/micro/cortex_m_corstone_300/README.md f
## TensorFlow Lite for Microcontrollers Out of Memory Error during Runtime
During runtime the TensorFlow Lite for Microcontrollers framework might report
-the following fatal error:
-`Failed to resize buffer. Requested: X, available: Y, missing: Z`, where X, Y
-and Z are numbers of bytes and X = Y + Z.
+the following fatal error:
+
+```Failed to resize buffer. Requested: X, available: Y, missing: Z```
+
+where X, Y and Z are numbers of bytes and X = Y + Z.
+
There can be several reasons for running out of memory during an inference but
one cause is that too much memory was allocated to the Ethos-U during the
offline compilation phase of the `.tflite` file using Vela. This can result in