Rename MobileNetV3 to MobileNetV3Small in docs (#4240)
diff --git a/docs/developing_iree/e2e_benchmarking.md b/docs/developing_iree/e2e_benchmarking.md
index 607ef35..55450c8 100644
--- a/docs/developing_iree/e2e_benchmarking.md
+++ b/docs/developing_iree/e2e_benchmarking.md
@@ -40,10 +40,10 @@
# --data: the dataset (and corresponding image shapes) to create the model for
$ python ../iree/integrations/tensorflow/e2e/keras/applications/applications_test.py \
--target_backends=iree_vmla \
- --model=MobileNetV3 \
+ --model=MobileNetV3Small \
--data=imagenet
# View the generated artifacts:
-$ tree /tmp/iree/modules/MobileNetV3/
+$ tree /tmp/iree/modules/MobileNetV3Small/
```
Each test/module has a folder with the following artifacts (filtered to only
@@ -158,12 +158,12 @@
--flagfile="/tmp/iree/modules/MatrixOpsStaticModule/iree_vmla/traces/matmul_lhs_batch/flagfile"
```
-If you ran `applications_test.py` then you'll be able to benchmark `MobileNetV3`
+If you ran `applications_test.py` then you'll be able to benchmark `MobileNetV3Small`
on `imagenet` input shapes. For example:
```shell
$ ./bazel-bin/iree/tools/iree-benchmark-module \
- --flagfile="/tmp/iree/modules/MobileNetV3/imagenet/iree_vmla/traces/predict/flagfile"
+ --flagfile="/tmp/iree/modules/MobileNetV3Small/imagenet/iree_vmla/traces/predict/flagfile"
```
## 3. Benchmarking TFLite on desktop
