Merge pull request #5 from aws/jth_edits

Cleanup plus documenting fix for TF conda update
aws-neuron · Dec 2, 2019 · 561f933 · 561f933
2 parents 4cd3da0 + 2b09a29
commit 561f933
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 3 deletions.
diff --git a/docs/mxnet-neuron/tutorial-compile-infer.md b/docs/mxnet-neuron/tutorial-compile-infer.md
@@ -72,11 +72,11 @@ mx.test_utils.download(path+'resnet/50-layers/resnet-50-0000.params')
 mx.test_utils.download(path+'resnet/50-layers/resnet-50-symbol.json')
 sym, args, aux = mx.model.load_checkpoint('resnet-50', 0)
 
- # Compile for Inferentia using Neuron
+# Compile for Inferentia using Neuron
 inputs = { "data" : mx.nd.ones([1,3,224,224], name='data', dtype='float32') }
 sym, args, aux = mx.contrib.neuron.compile(sym, args, aux, inputs)
 
- #save compiled model
+#save compiled model
 mx.model.save_checkpoint("resnet-50_compiled", 0, sym, args, aux)
 ```
 

diff --git a/docs/tensorflow-neuron/tutorial-compile-infer.md b/docs/tensorflow-neuron/tutorial-compile-infer.md
@@ -142,7 +142,7 @@ infa_rslts = predictor_inferentia(model_feed_dict);
 print(resnet50.decode_predictions(infa_rslts["output"], top=5)[0])
 ```
 
-3.5. Unzip the mode, download the example image and run the inference:
+3.5. Unzip the model, download the example image and run the inference:
 ```bash
 unzip resnet50_neuron.zip
 curl -O https://raw.githubusercontent.com/awslabs/mxnet-model-server/master/docs/images/kitten_small.jpg

diff --git a/release-notes/dlami-release-notes.md b/release-notes/dlami-release-notes.md
@@ -26,6 +26,8 @@ tensorflow-model-server-neuron=1.15.0.1.0.663.0
 
 ## Known Issues
 
+In TensorFlow-Neuron conda environment (aws_neuron_tensorflow_p36), a wrong numpy version prevents update to latest conda package version. Please do "conda install numpy=1.17.2" before "conda update tensorflow-neuron".
+
 Please update all packages to most recent release:
 
 *  Ubuntu:
@@ -49,5 +51,6 @@ sudo yum install tensorflow-model-server-neuron
 source activate aws_neuron_mxnet_p36
 conda update mxnet-neuron
 source activate aws_neuron_tensorflow_p36
+conda install numpy=1.17.2
 conda update tensorflow-neuron
 ```