Skip to main content
NetApp Solutions
本繁體中文版使用機器翻譯,譯文僅供參考,若與英文版本牴觸,應以英文版本為準。

測試程序

貢獻者

本節說明完成驗證所需的工作。

先決條件

若要執行本節所述的工作、您必須安裝並設定下列工具、才能存取Linux或MacOS主機:

  • Kubectl(設定為存取現有的Kubernetes叢集)

  • 適用於Kubernetes的NetApp DataOps工具套件

案例1–JupyterLab的隨需推斷

  1. 為AI / ML推斷工作負載建立Kubernetes命名空間。

    $ kubectl create namespace inference
    namespace/inference created
  2. 使用NetApp DataOps Toolkit來配置持續磁碟區、以儲存您要在其中執行推斷的資料。

    $ netapp_dataops_k8s_cli.py create volume --namespace=inference --pvc-name=inference-data --size=50Gi
    Creating PersistentVolumeClaim (PVC) 'inference-data' in namespace 'inference'.
    PersistentVolumeClaim (PVC) 'inference-data' created. Waiting for Kubernetes to bind volume to PVC.
    Volume successfully created and bound to PersistentVolumeClaim (PVC) 'inference-data' in namespace 'inference'.
  3. 使用NetApp DataOps Toolkit建立新的JupyterLab工作區。使用「-mount-PVC'」選項來掛載上一步建立的持續磁碟區。使用「-nvidia-GPU」選項、視需要將NVIDIA GPU分配給工作區。

    在以下範例中、持續性磁碟區「推斷資料」會掛載到JupyterLab工作區容器、位於「/home/jovyan/data」。使用正式的Project Jupyter Container映像時、「/home/jovyan」會顯示為JupyterLab網路介面中的頂層目錄。

    $ netapp_dataops_k8s_cli.py create jupyterlab --namespace=inference --workspace-name=live-inference --size=50Gi --nvidia-gpu=2 --mount-pvc=inference-data:/home/jovyan/data
    Set workspace password (this password will be required in order to access the workspace):
    Re-enter password:
    Creating persistent volume for workspace...
    Creating PersistentVolumeClaim (PVC) 'ntap-dsutil-jupyterlab-live-inference' in namespace 'inference'.
    PersistentVolumeClaim (PVC) 'ntap-dsutil-jupyterlab-live-inference' created. Waiting for Kubernetes to bind volume to PVC.
    Volume successfully created and bound to PersistentVolumeClaim (PVC) 'ntap-dsutil-jupyterlab-live-inference' in namespace 'inference'.
    Creating Service 'ntap-dsutil-jupyterlab-live-inference' in namespace 'inference'.
    Service successfully created.
    Attaching Additional PVC: 'inference-data' at mount_path: '/home/jovyan/data'.
    Creating Deployment 'ntap-dsutil-jupyterlab-live-inference' in namespace 'inference'.
    Deployment 'ntap-dsutil-jupyterlab-live-inference' created.
    Waiting for Deployment 'ntap-dsutil-jupyterlab-live-inference' to reach Ready state.
    Deployment successfully created.
    Workspace successfully created.
    To access workspace, navigate to http://192.168.0.152:32721
  4. 使用「create jupyterlab」命令輸出中指定的URL存取JupyterLab工作區。資料目錄代表掛載到工作區的持續磁碟區。

    錯誤:缺少圖形影像

  5. 開啟「DATA」目錄、然後上傳要執行提示的檔案。檔案上傳至資料目錄時、會自動儲存在掛載至工作區的持續磁碟區上。若要上傳檔案、請按一下「上傳檔案」圖示、如下圖所示。

    錯誤:缺少圖形影像

  6. 返回最上層目錄並建立新的筆記本。

    錯誤:缺少圖形影像

  7. 在筆記本中加入推斷程式碼。下列範例顯示影像偵測使用案例的推斷代碼。

    錯誤:缺少圖形影像

    錯誤:缺少圖形影像

  8. 將Protopia混淆新增至您的推斷程式碼。Protopia直接與客戶合作、提供特定使用案例的文件、並不在本技術報告的範圍之內。以下範例顯示新增Protopia混淆功能時、影像偵測使用案例的推斷程式碼。

    錯誤:缺少圖形影像

    錯誤:缺少圖形影像

案例2:Kubernetes上的批次推斷

  1. 為AI / ML推斷工作負載建立Kubernetes命名空間。

    $ kubectl create namespace inference
    namespace/inference created
  2. 使用NetApp DataOps Toolkit來配置持續磁碟區、以儲存您要在其中執行推斷的資料。

    $ netapp_dataops_k8s_cli.py create volume --namespace=inference --pvc-name=inference-data --size=50Gi
    Creating PersistentVolumeClaim (PVC) 'inference-data' in namespace 'inference'.
    PersistentVolumeClaim (PVC) 'inference-data' created. Waiting for Kubernetes to bind volume to PVC.
    Volume successfully created and bound to PersistentVolumeClaim (PVC) 'inference-data' in namespace 'inference'.
  3. 在新的持續磁碟區中填入您要執行推斷的資料。

    有多種方法可將資料載入至PVc。如果您的資料目前儲存在S3相容的物件儲存平台、例如NetApp StorageGRID 功能區或Amazon S3、您就可以使用 "NetApp DataOps Toolkit S3 Data Mover功能"。另一種簡單的方法是建立JupyterLab工作區、然後透過JupyterLab網頁介面上傳檔案、如「」一節中步驟3至5所述案例1–JupyterLab的隨需推斷。」

  4. 為批次推斷工作建立Kubernetes工作。下列範例顯示影像偵測使用案例的批次推斷工作。此工作會在一組映像中的每個映像上執行推斷、並將推斷準確度指標寫入stdout。

    $ vi inference-job-raw.yaml
    apiVersion: batch/v1
    kind: Job
    metadata:
      name: netapp-inference-raw
      namespace: inference
    spec:
      backoffLimit: 5
      template:
        spec:
          volumes:
          - name: data
            persistentVolumeClaim:
              claimName: inference-data
          - name: dshm
            emptyDir:
              medium: Memory
          containers:
          - name: inference
            image: netapp-protopia-inference:latest
            imagePullPolicy: IfNotPresent
            command: ["python3", "run-accuracy-measurement.py", "--dataset", "/data/netapp-face-detection/FDDB"]
            resources:
              limits:
                nvidia.com/gpu: 2
            volumeMounts:
            - mountPath: /data
              name: data
            - mountPath: /dev/shm
              name: dshm
          restartPolicy: Never
    $ kubectl create -f inference-job-raw.yaml
    job.batch/netapp-inference-raw created
  5. 確認推斷工作已成功完成。

    $ kubectl -n inference logs netapp-inference-raw-255sp
    100%|██████████| 89/89 [00:52<00:00,  1.68it/s]
    Reading Predictions : 100%|██████████| 10/10 [00:01<00:00,  6.23it/s]
    Predicting ... : 100%|██████████| 10/10 [00:16<00:00,  1.64s/it]
    ==================== Results ====================
    FDDB-fold-1 Val AP: 0.9491256561145955
    FDDB-fold-2 Val AP: 0.9205024466101926
    FDDB-fold-3 Val AP: 0.9253013871078468
    FDDB-fold-4 Val AP: 0.9399781485863011
    FDDB-fold-5 Val AP: 0.9504280149478732
    FDDB-fold-6 Val AP: 0.9416473519339292
    FDDB-fold-7 Val AP: 0.9241631566241117
    FDDB-fold-8 Val AP: 0.9072663297546659
    FDDB-fold-9 Val AP: 0.9339648715035469
    FDDB-fold-10 Val AP: 0.9447707905560152
    FDDB Dataset Average AP: 0.9337148153739079
    =================================================
    mAP: 0.9337148153739079
  6. 在推斷工作中加入Protopia混淆。您可以在本技術報告範圍之外的Protopia中、找到直接新增Protopia混淆的使用案例特定指示。下列範例顯示使用0.8的Alpha值新增Protopia模糊處理時、面偵測使用案例的批次推斷工作。此工作會先套用Protopia混淆、再對一組影像中的每個影像進行推斷、然後將推斷準確度指標寫入stdout。

    我們重複此步驟以取得Alpha值、包括0.05、0.1、0.2、0.4、0.6、 0.8、0.9及0.95。您可以在中看到結果 "「推斷準確度比較」。"

    $ vi inference-job-protopia-0.8.yaml
    apiVersion: batch/v1
    kind: Job
    metadata:
      name: netapp-inference-protopia-0.8
      namespace: inference
    spec:
      backoffLimit: 5
      template:
        spec:
          volumes:
          - name: data
            persistentVolumeClaim:
              claimName: inference-data
          - name: dshm
            emptyDir:
              medium: Memory
          containers:
          - name: inference
            image: netapp-protopia-inference:latest
            imagePullPolicy: IfNotPresent
            env:
            - name: ALPHA
              value: "0.8"
            command: ["python3", "run-accuracy-measurement.py", "--dataset", "/data/netapp-face-detection/FDDB", "--alpha", "$(ALPHA)", "--noisy"]
            resources:
              limits:
                nvidia.com/gpu: 2
            volumeMounts:
            - mountPath: /data
              name: data
            - mountPath: /dev/shm
              name: dshm
          restartPolicy: Never
    $ kubectl create -f inference-job-protopia-0.8.yaml
    job.batch/netapp-inference-protopia-0.8 created
  7. 確認推斷工作已成功完成。

    $ kubectl -n inference logs netapp-inference-protopia-0.8-b4dkz
    100%|██████████| 89/89 [01:05<00:00,  1.37it/s]
    Reading Predictions : 100%|██████████| 10/10 [00:02<00:00,  3.67it/s]
    Predicting ... : 100%|██████████| 10/10 [00:22<00:00,  2.24s/it]
    ==================== Results ====================
    FDDB-fold-1 Val AP: 0.8953066115834589
    FDDB-fold-2 Val AP: 0.8819580264029936
    FDDB-fold-3 Val AP: 0.8781107458462862
    FDDB-fold-4 Val AP: 0.9085731346308461
    FDDB-fold-5 Val AP: 0.9166445508275378
    FDDB-fold-6 Val AP: 0.9101178994188819
    FDDB-fold-7 Val AP: 0.8383443678423771
    FDDB-fold-8 Val AP: 0.8476311547659464
    FDDB-fold-9 Val AP: 0.8739624502111121
    FDDB-fold-10 Val AP: 0.8905468076424851
    FDDB Dataset Average AP: 0.8841195749171925
    =================================================
    mAP: 0.8841195749171925

案例3–NVIDIA Triton Inference Server

  1. 為AI / ML推斷工作負載建立Kubernetes命名空間。

    $ kubectl create namespace inference
    namespace/inference created
  2. 使用NetApp DataOps Toolkit來配置持續磁碟區、以作為NVIDIA Triton Inference Server的模型儲存庫。

    $ netapp_dataops_k8s_cli.py create volume --namespace=inference --pvc-name=triton-model-repo --size=100Gi
    Creating PersistentVolumeClaim (PVC) 'triton-model-repo' in namespace 'inference'.
    PersistentVolumeClaim (PVC) 'triton-model-repo' created. Waiting for Kubernetes to bind volume to PVC.
    Volume successfully created and bound to PersistentVolumeClaim (PVC) 'triton-model-repo' in namespace 'inference'.
  3. 將您的模型儲存在中的新持續磁碟區上 "格式" NVIDIA Triton Inference伺服器也能辨識這點。

    有多種方法可將資料載入至PVc。簡單的方法是建立JupyterLab工作區、然後透過JupyterLab網路介面上傳檔案、如「」中的步驟3至5所述案例1–JupyterLab的隨需推斷。」

  4. 使用NetApp DataOps Toolkit部署新的NVIDIA Triton Inference Server執行個體。

    $ netapp_dataops_k8s_cli.py create triton-server --namespace=inference --server-name=netapp-inference --model-repo-pvc-name=triton-model-repo
    Creating Service 'ntap-dsutil-triton-netapp-inference' in namespace 'inference'.
    Service successfully created.
    Creating Deployment 'ntap-dsutil-triton-netapp-inference' in namespace 'inference'.
    Deployment 'ntap-dsutil-triton-netapp-inference' created.
    Waiting for Deployment 'ntap-dsutil-triton-netapp-inference' to reach Ready state.
    Deployment successfully created.
    Server successfully created.
    Server endpoints:
    http: 192.168.0.152: 31208
    grpc: 192.168.0.152: 32736
    metrics: 192.168.0.152: 30009/metrics
  5. 使用Triton用戶端SDK執行推斷工作。下列Python程式碼摘錄使用Triton Python用戶端SDK、針對面偵測使用案例執行推斷工作。此範例會呼叫Triton API、並傳入影像以供參考。然後Triton Inference伺服器會收到要求、啟動模型、並傳回推斷輸出、做為API結果的一部分。

    # get current frame
    frame = input_image
    # preprocess input
    preprocessed_input = preprocess_input(frame)
    preprocessed_input = torch.Tensor(preprocessed_input).to(device)
    # run forward pass
    clean_activation = clean_model_head(preprocessed_input)  # runs the first few layers
    ######################################################################################
    #          pass clean image to Triton Inference Server API for inferencing           #
    ######################################################################################
    triton_client = httpclient.InferenceServerClient(url="192.168.0.152:31208", verbose=False)
    model_name = "face_detection_base"
    inputs = []
    outputs = []
    inputs.append(httpclient.InferInput("INPUT__0", [1, 128, 32, 32], "FP32"))
    inputs[0].set_data_from_numpy(clean_activation.detach().cpu().numpy(), binary_data=False)
    outputs.append(httpclient.InferRequestedOutput("OUTPUT__0", binary_data=False))
    outputs.append(httpclient.InferRequestedOutput("OUTPUT__1", binary_data=False))
    results = triton_client.infer(
        model_name,
        inputs,
        outputs=outputs,
        #query_params=query_params,
        headers=None,
        request_compression_algorithm=None,
        response_compression_algorithm=None)
    #print(results.get_response())
    statistics = triton_client.get_inference_statistics(model_name=model_name, headers=None)
    print(statistics)
    if len(statistics["model_stats"]) != 1:
        print("FAILED: Inference Statistics")
        sys.exit(1)
    
    loc_numpy = results.as_numpy("OUTPUT__0")
    pred_numpy = results.as_numpy("OUTPUT__1")
    ######################################################################################
    # postprocess output
    clean_pred = (loc_numpy, pred_numpy)
    clean_outputs = postprocess_outputs(
        clean_pred, [[input_image_width, input_image_height]], priors, THRESHOLD
    )
    # draw rectangles
    clean_frame = copy.deepcopy(frame)  # needs to be deep copy
    for (x1, y1, x2, y2, s) in clean_outputs[0]:
        x1, y1 = int(x1), int(y1)
        x2, y2 = int(x2), int(y2)
        cv2.rectangle(clean_frame, (x1, y1), (x2, y2), (0, 0, 255), 4)
  6. 將Protopia混淆新增至您的推斷程式碼。您可以找到直接從Protopia新增Protopia混淆的使用案例特定指示、不過此程序不在本技術報告的範圍之內。以下範例顯示與前述步驟5相同的Python程式碼、但新增了Protopia混淆功能。

    請注意、Protopia混淆會套用至映像、然後再傳遞至Triton API。因此、不模糊的影像永遠不會離開本機機器。只有模糊的映像會透過網路傳送。此工作流程適用於在信任區域內收集資料、但需要在信任區域外傳遞資料以進行推斷的使用案例。如果沒有Protopia混淆、就無法在不敏感資料離開信任區域的情況下實作這類工作流程。

    # get current frame
    frame = input_image
    # preprocess input
    preprocessed_input = preprocess_input(frame)
    preprocessed_input = torch.Tensor(preprocessed_input).to(device)
    # run forward pass
    not_noisy_activation = noisy_model_head(preprocessed_input)  # runs the first few layers
    ##################################################################
    #          obfuscate image locally prior to inferencing          #
    #          SINGLE ADITIONAL LINE FOR PRIVATE INFERENCE           #
    ##################################################################
    noisy_activation = noisy_model_noise(not_noisy_activation)
    ##################################################################
    ###########################################################################################
    #          pass obfuscated image to Triton Inference Server API for inferencing           #
    ###########################################################################################
    triton_client = httpclient.InferenceServerClient(url="192.168.0.152:31208", verbose=False)
    model_name = "face_detection_noisy"
    inputs = []
    outputs = []
    inputs.append(httpclient.InferInput("INPUT__0", [1, 128, 32, 32], "FP32"))
    inputs[0].set_data_from_numpy(noisy_activation.detach().cpu().numpy(), binary_data=False)
    outputs.append(httpclient.InferRequestedOutput("OUTPUT__0", binary_data=False))
    outputs.append(httpclient.InferRequestedOutput("OUTPUT__1", binary_data=False))
    results = triton_client.infer(
        model_name,
        inputs,
        outputs=outputs,
        #query_params=query_params,
        headers=None,
        request_compression_algorithm=None,
        response_compression_algorithm=None)
    #print(results.get_response())
    statistics = triton_client.get_inference_statistics(model_name=model_name, headers=None)
    print(statistics)
    if len(statistics["model_stats"]) != 1:
        print("FAILED: Inference Statistics")
        sys.exit(1)
    
    loc_numpy = results.as_numpy("OUTPUT__0")
    pred_numpy = results.as_numpy("OUTPUT__1")
    ###########################################################################################
    
    # postprocess output
    noisy_pred = (loc_numpy, pred_numpy)
    noisy_outputs = postprocess_outputs(
        noisy_pred, [[input_image_width, input_image_height]], priors, THRESHOLD * 0.5
    )
    # get reconstruction of the noisy activation
    noisy_reconstruction = decoder_function(noisy_activation)
    noisy_reconstruction = noisy_reconstruction.detach().cpu().numpy()[0]
    noisy_reconstruction = unpreprocess_output(
        noisy_reconstruction, (input_image_width, input_image_height), True
    ).astype(np.uint8)
    # draw rectangles
    for (x1, y1, x2, y2, s) in noisy_outputs[0]:
        x1, y1 = int(x1), int(y1)
        x2, y2 = int(x2), int(y2)
        cv2.rectangle(noisy_reconstruction, (x1, y1), (x2, y2), (0, 0, 255), 4)