From 45934f1ad273e52b236cca65f774856f4bd1a32c Mon Sep 17 00:00:00 2001
From: freschri <117075521+freschri@users.noreply.github.com>
Date: Thu, 14 Mar 2024 15:24:08 +0100
Subject: [PATCH] added neuron resource (#39)

---
 .../neuron/pytorch-inference-resnet50.yml     | 96 +++++++++++++++++++
 1 file changed, 96 insertions(+)
 create mode 100644 artifacts/k8s-deployment-manifest-templates/neuron/pytorch-inference-resnet50.yml

diff --git a/artifacts/k8s-deployment-manifest-templates/neuron/pytorch-inference-resnet50.yml b/artifacts/k8s-deployment-manifest-templates/neuron/pytorch-inference-resnet50.yml
new file mode 100644
index 0000000..d5870d9
--- /dev/null
+++ b/artifacts/k8s-deployment-manifest-templates/neuron/pytorch-inference-resnet50.yml
@@ -0,0 +1,96 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: pytorch-resnet50-script
+data:
+  pytorch-resnet50.sh: |
+    #!/usr/bin/env python
+    import torch
+    import numpy as np
+    import os
+    import torch_neuron
+    from torchvision import models, transforms, datasets
+    import time
+    from urllib import request
+    import json
+
+    image = torch.zeros([1, 3, 224, 224], dtype=torch.float32)
+
+    ## Load a pretrained ResNet50 model
+    model = models.resnet50(pretrained=True)
+
+    ## Tell the model we are using it for evaluation (not training)
+    model.eval()
+    model_neuron = torch.neuron.trace(model, example_inputs=[image])
+
+    ## Create an image directory containing a small kitten
+    os.makedirs("./torch_neuron_test/images", exist_ok=True)
+    request.urlretrieve("https://raw.githubusercontent.com/awslabs/mxnet-model-server/master/docs/images/kitten_small.jpg",
+                        "./torch_neuron_test/images/kitten_small.jpg")
+
+    ## Fetch labels to output the top classifications
+    request.urlretrieve("https://s3.amazonaws.com/deep-learning-models/image-models/imagenet_class_index.json","imagenet_class_index.json")
+    idx2label = []
+
+    with open("imagenet_class_index.json", "r") as read_file:
+        class_idx = json.load(read_file)
+        idx2label = [class_idx[str(k)][1] for k in range(len(class_idx))]
+
+    ## Import a sample image and normalize it into a tensor
+    normalize = transforms.Normalize(
+        mean=[0.485, 0.456, 0.406],
+        std=[0.229, 0.224, 0.225])
+
+    eval_dataset = datasets.ImageFolder(
+        os.path.dirname("./torch_neuron_test/"),
+        transforms.Compose([
+        transforms.Resize([224, 224]),
+        transforms.ToTensor(),
+        normalize,
+        ])
+    )
+
+    image, _ = eval_dataset[0]
+    image = torch.tensor(image.numpy()[np.newaxis, ...])
+
+    ## Predict
+    while True:
+        results = model_neuron( image )
+        time.sleep(0.1)
+---
+apiVersion: v1
+kind: Pod
+metadata:
+  name: pytorch-inference-resnet50
+spec:
+  tolerations:
+  - key: node-role.kubernetes.io/control-plane
+    operator: Exists
+    effect: NoSchedule
+  - key: node-role.kubernetes.io/master
+    operator: Exists
+    effect: NoSchedule
+  containers:
+  - name: pytorch
+    image: 763104351884.dkr.ecr.us-west-2.amazonaws.com/pytorch-inference-neuron:1.13.1-neuron-py310-sdk2.13.2-ubuntu20.04
+    command: ["/script/pytorch-resnet50.sh"]
+    volumeMounts:
+      - name: script
+        mountPath: "/script"
+    resources:
+      limits:
+        cpu: 4
+        memory: 4Gi
+        aws.amazon.com/neuron: 1
+      requests:
+        cpu: "1"
+        memory: 1Gi
+    securityContext:
+      capabilities:
+        add:
+          - IPC_LOCK
+  volumes:
+  - name: script
+    configMap:
+      name: pytorch-resnet50-script
+      defaultMode: 0777