aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/docs_src/mobile
diff options
context:
space:
mode:
authorGravatar A. Unique TensorFlower <gardener@tensorflow.org>2017-12-22 12:42:59 -0800
committerGravatar TensorFlower Gardener <gardener@tensorflow.org>2017-12-22 12:46:28 -0800
commite4532d20973c4c00854492362665317551661c18 (patch)
tree398527e29bd30d39237adb4785be5069fdb646fa /tensorflow/docs_src/mobile
parent673641c2d6a27fa97ee05453d671853731a4c602 (diff)
Merge changes from github.
PiperOrigin-RevId: 179953488
Diffstat (limited to 'tensorflow/docs_src/mobile')
-rw-r--r--tensorflow/docs_src/mobile/tflite/index.md2
1 files changed, 1 insertions, 1 deletions
diff --git a/tensorflow/docs_src/mobile/tflite/index.md b/tensorflow/docs_src/mobile/tflite/index.md
index 49d93669a2..6c4589d693 100644
--- a/tensorflow/docs_src/mobile/tflite/index.md
+++ b/tensorflow/docs_src/mobile/tflite/index.md
@@ -155,7 +155,7 @@ retraining for both floating point and quantized inference.
The following diagram shows the architectural design of TensorFlow Lite:
-<img src = "/images/tflite-architecture.jpg">
+![tensorflow lite architecture](https://www.tensorflow.org/images/tflite-architecture.jpg)
Starting with a trained TensorFlow model on disk, you'll convert that model to
the TensorFlow Lite file format (`.tflite`) using the TensorFlow Lite