wal.sh
home > research > deeplens · Jan 01, 2024

Custom Model Training for DeepLens using Caltech-256 Dataset

deeplensstand-alone cameramachine learning supportimage classificationpre-trained modelscustom modelcaltech-256 datasetnotebookresnetnetwork trainingobject categoriesimage dataset

Custom Model Training for DeepLens using Caltech-256 Dataset

Table of Contents

1. Background

DeepLens is a stand-alone camera with specialized ML support.

2. Image Classification

correct · pilot-annotation-pass · 2026-10-08

There are several pre-trained models for DeepLens. The goal of this project will be to provide a new trained model for used with DeepLens.

https://authors.library.caltech.edu/7694/1/CNS-TR-2007-001.pdf

We introduce a challenging set of 256 object categories containing a total of 30607 images

3. Workflow

  • create notebook
  • define containers
  • get caltech-256
  • define the network for training

3.1. Network

  {
          "type": "ResNet",
          "hyperparameters": {

          }
  }

4. Edge ML architecture

// AWS DeepLens (2017-2020) reference architecture -- train in SageMaker,
// package with Greengrass, serve on the device, stream inference back
// to AWS IoT for retraining and Lambda triggers.
digraph edge_ml_deeplens {
    rankdir=LR;
    graph [bgcolor="white", fontname="Helvetica", fontsize=11,
           pad="0.3", nodesep="0.3", ranksep="0.45"];
    node  [shape=box, style="rounded,filled", fontname="Helvetica",
           fontsize=10, fillcolor="#dbeafe", color="#888"];
    edge  [color="#aaa"];

    // Cloud side
    subgraph cluster_cloud {
        label="AWS cloud"; labeljust="l";
        color="#1d4ed8"; fontcolor="#1d4ed8"; style="rounded";
        sm    [label="SageMaker\n(train + tune)",
               fillcolor="#eaf2fb"];
        s3in  [label="S3\n(training data)",
               fillcolor="#eaf2fb"];
        s3out [label="S3\n(inference logs,\nframes)",
               fillcolor="#eaf2fb"];
        iot   [label="AWS IoT Core\n(MQTT broker)",
               fillcolor="#eaf2fb"];
        lam   [label="Lambda\n(triggers)",
               fillcolor="#eaf2fb"];
        s3in -> sm;
    }

    // Edge side
    subgraph cluster_edge {
        label="DeepLens device (Intel Atom + Movidius VPU)";
        labeljust="l"; color="#15803d"; fontcolor="#15803d"; style="rounded";
        gg    [label="Greengrass\nCore",
               fillcolor="#eaf5ea"];
        cam   [label="HD camera",
               fillcolor="#eaf5ea"];
        infer [label="MXNet runtime\n(on-device inference)",
               fillcolor="#eaf5ea"];
        cam -> infer;
    }

    // Model packaging + deploy
    sm -> gg [label="model artifact\n(deploy)", fontsize=9, color="#1d4ed8"];
    gg -> infer [label="load", fontsize=9, color="#15803d"];

    // Inference results back to cloud
    infer -> iot   [label="MQTT publish", fontsize=9, color="#15803d"];
    iot   -> s3out [label="rule",         fontsize=9];
    iot   -> lam   [label="rule",         fontsize=9];

    // Retraining feedback loop
    s3out -> sm [label="retrain",
                 style=dashed, color="#888", constraint=false];

    // Successors (the actual 2026 winners)
    subgraph cluster_post {
        label="What replaced it (2024+)"; labeljust="l";
        color="#a16207"; fontcolor="#a16207"; style="rounded,filled";
        bgcolor="#fefce8";
        coral   [label="Google Coral\n(Edge TPU)",
                 fillcolor="#fef9c3", color="#a16207", fontcolor="#a16207"];
        jetson  [label="NVIDIA Jetson\nNano / Orin",
                 fillcolor="#fef9c3", color="#a16207", fontcolor="#a16207"];
        pi_tfl  [label="Raspberry Pi 4/5\n+ TFLite / ONNX",
                 fillcolor="#fef9c3", color="#a16207", fontcolor="#a16207"];
        ane     [label="Apple Neural Engine\n(iPhone / iPad)",
                 fillcolor="#fef9c3", color="#a16207", fontcolor="#a16207"];
        smolvlm [label="Phi-3, Llama 3.2 1B/3B\n(small VLMs on device)",
                 fillcolor="#fff3c0"];
    }
}

diagram-edge-ml-deeplens.png

5. Related notes

  • 2019 machine learning pipelines – DeepLens was the cloud-trained / edge-deployed instantiation of the pipeline this note documented.
  • Kubeflow – server-side analogue; KubeRay + KServe took the same role on the cloud-orchestration side.
  • Fine-tuning ML models – small-model fine-tuning made on-device inference viable on commodity hardware after DeepLens.
  • scikit-learn – sibling 2019 note on the tabular side of the same era.

6. Postscript (2026)

attributed · pilot-annotation-pass · 2026-10-08

AWS discontinued DeepLens with the device service ending 31 January 2024. SageMaker Edge Manager, the 2020 successor pitched at the same edge-ML use case, was also deprecated effective 26 April 2024. The actual winners on edge ML were not all-in-one branded devices but components: Google's Coral Edge TPU (USB Accelerator + Dev Board), NVIDIA's Jetson Nano / Orin family, Raspberry Pi 4/5 paired with TensorFlow Lite or ONNX Runtime, and Apple's Neural Engine for iOS ML. The 2024-2025 pivot reframed "edge ML" away from CV-specific classifiers toward small multimodal LLMs running on commodity hardware – Microsoft's Phi-3 (April 2024), Meta's Llama 3.2 1B and 3B (September 2024), and Google's Gemma 2B all targeted on-device inference; the hardware story converged on whatever device the user already owned.