A model is still running

A model is still running or downloading. Leaving will stop the current operation. Stay on this page to let it finish.

Skip to content
LocalAI.toolsBeta

Join the waitlist

Get an email when the new apps and model runs launch.

No account needed.

DETR ResNet-50-panoptic — Panoptic Segmentation

Separate common objects and background regions into complete class-labeled pixel masks.

Browser inferencePowered by WebAI · Private · Unlimited runs
About this model

Separate common objects and background regions into complete class-labeled pixel masks.

Created by
Meta
License
Apache-2.0
Model released
Unknown
Source repository created
Mar 2, 2022
Model weights · FP32
172.3 MB

Best for

  • Prototype object localization in photographs.
  • Compare browser detection backends and retrieval/image-indexing workflows.

Keep in mind

  • Small, occluded, blurred, unusual, or densely packed objects can be missed or mislocalized.
  • Only COCO category labels are supported; confidence is not a guarantee of correctness.
  • Predictions can encode dataset bias and must not be used for safety-critical, surveillance, identity, or high-impact decisions.
  • Small controlled person/dog/blank fixture suite only; broad COCO accuracy remains unverified.
  • Pinned runtime produces complete spatial predictions after one forward pass; no incremental streaming API.
  • New public sample publication, dependency backups and forced source recovery remain excluded and unverified; no full release certification.

Processed on your deviceInference runs in this browser. Input/output sharing requires consent for each run. Basic run logs include device information and approximate connection location. Model and runtime files download from external hosts. Saved downloads may be cleared by your browser.

Sources & technical details
Original model
facebook/detr-resnet-50-panoptic
Release verification
Unknown
Release evidence
Exact original checkpoint public release date has not been verified. Repository creation, training, paper, artifact conversion and update dates are not release evidence. Explicit user request for the original 2020 DETR family; format conversion dates are not original releases.
Source updated
Apr 10, 2024
Browser model files
Xenova/detr-resnet-50-panoptic
Files updated
Jun 30, 2025
Artifact revision
ea24b2d4e0bfae31f0a1299ba3fb892a2df064de

Input

IMAGE

Sample result

DETR ResNet-50-panoptic — Panoptic Segmentation

Settings

Adds a self-contained SVG presentation image alongside the unchanged native model fields. When enabled, draws model predictions or presents generated media and text. Adds CPU postprocessing time and image bytes. It does not change model predictions.
Advanced settings 1
Sets the cutoff used to keep a prediction or create a hard mask. Lower values keep more weak predictions or foreground pixels, with more possible false positives. Higher values are stricter and may miss details. Automatic/null preserves soft alpha edges when offered.

Output

Your result will appear here

Add input or try the sample, then run the model.

Benchmark evidence

Saved worker evidence is separate from benchmarks run on your device. It does not guarantee speed or quality on every browser.

DETR ResNet-50-panoptic — Panoptic Segmentation

15 configurations tested
Passed7
Failed8
TestedNov 11, 2026
RuntimeTransformers.js 4.2.0

Quality criteria

No explicit quality gate recorded. Review per-case evidence; full certification is pending.

PrecisionDeviceResult
FP16GPU · WebGPUAcceleratedPassedModerate
FP32GPU · WebGPUAcceleratedPassedModerate
FP32GPU · WebGPUAcceleratedPassedModerate
FP32GPU · WebGPUAcceleratedPassedModerate
FP32GPU · WebGPUAcceleratedPassedModerate
FP16GPU · WebGPUAcceleratedPassedModerate
FP16GPU · WebGPUAcceleratedPassedModerate
Q8CPU · WASMFailed—
Q8CPU · WASMFailed—
Q8CPU · WASMFailed—
Q8GPU · WebGPUFailed—
Q8GPU · WebGPUFailed—
Q8GPU · WebGPUFailed—
FP32CPU · WASMFailed—
FP16CPU · WASMFailed—
Test setup & sample details
Quality gate
No explicit quality gate recorded. Review the per-case quality evidence; full certification is pending.
Tested
2026-11-11T23:27:30.040Z
Environment
{ "os": "macos", "osVersion": "27.2", "hardware": "Apple M3 Max", "browser": "157.0.8103.40", "runtime": "Transformers.js4.2.0", "transport": "Real public WebAI API in isolated module workers; original repository URLs redirect to checksum-verified local pinned snapshots. Not network download speed or source-recovery certification." }
Runtime
Transformers.js 4.2.0
Artifact revision
ea24b2d4e0bfae31f0a1299ba3fb892a2df064de
Fixture
{
  "file": "model-samples/desktop/mobilenet-dog.jpg",
  "size": 83281,
  "sha1": "f1d042827c2f2154a6d8043b8e8f07c1be612941",
  "sha256": "d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1",
  "url": "https://assets.localai.tools/samples/v1/files/d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1/mobilenet-dog.jpg"
}
Rerun when
Artifact/runtime revision; Preprocessing/postprocessing/visualization; Fixture/quality gate; Browser/backend behavior
Per-case quality & failure details
[
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "interiorPointPassed": [
        true,
        true,
        true
      ],
      "completeMasks": true,
      "passed": true,
      "exactStuffFusionPassed": true
    },
    "runtime": {
      "inferenceMs": 1187,
      "loadMs": 5108.9000000059605,
      "totalMs": 6295.9000000059605,
      "imagesPerSecond": 0.8424599831508003,
      "grade": "moderate",
      "version": "4.2.0",
      "fallback": false,
      "actualDevice": "webgpu",
      "acceleration": "partial",
      "gpuForwardQueueObserved": true,
      "accelerationDetails": "Instrumented GPUQueue.submit observes actual generation dispatch; CPU image preprocessing/postprocessing remain. Not a claim that every graph node runs on GPU.",
      "artifactRevision": "ea24b2d4e0bfae31f0a1299ba3fb892a2df064de",
      "browser": "157.0.8103.40",
      "loadTimingScope": "Public init with pinned local original-source snapshot, not Internet transfer."
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "interiorPointPassed": [
        true,
        true,
        true
      ],
      "completeMasks": true,
      "passed": true,
      "exactStuffFusionPassed": true
    },
    "runtime": {
      "inferenceMs": 1083.0999999940395,
      "loadMs": 5108.9000000059605,
      "totalMs": 6192,
      "imagesPerSecond": 0.9232757824813066,
      "grade": "moderate",
      "version": "4.2.0",
      "fallback": false,
      "actualDevice": "webgpu",
      "acceleration": "partial",
      "gpuForwardQueueObserved": true,
      "accelerationDetails": "Instrumented GPUQueue.submit observes actual generation dispatch; CPU image preprocessing/postprocessing remain. Not a claim that every graph node runs on GPU.",
      "artifactRevision": "ea24b2d4e0bfae31f0a1299ba3fb892a2df064de",
      "browser": "157.0.8103.40",
      "loadTimingScope": "Public init with pinned local original-source snapshot, not Internet transfer."
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "interiorPointPassed": [],
      "completeMasks": true,
      "passed": true,
      "exactStuffFusionPassed": true
    },
    "runtime": {
      "inferenceMs": 1065.5999999940395,
      "loadMs": 5108.9000000059605,
      "totalMs": 6174.5,
      "imagesPerSecond": 0.9384384384436876,
      "grade": "moderate",
      "version": "4.2.0",
      "fallback": false,
      "actualDevice": "webgpu",
      "acceleration": "partial",
      "gpuForwardQueueObserved": true,
      "accelerationDetails": "Instrumented GPUQueue.submit observes actual generation dispatch; CPU image preprocessing/postprocessing remain. Not a claim that every graph node runs on GPU.",
      "artifactRevision": "ea24b2d4e0bfae31f0a1299ba3fb892a2df064de",
      "browser": "157.0.8103.40",
      "loadTimingScope": "Public init with pinned local original-source snapshot, not Internet transfer."
    }
  },
  {
    "precision": "fp16",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "interiorPointPassed": [
        true,
        true,
        true
      ],
      "completeMasks": true,
      "passed": true,
      "exactStuffFusionPassed": true
    },
    "runtime": {
      "inferenceMs": 1579,
      "loadMs": 5137.199999988079,
      "totalMs": 6716.199999988079,
      "imagesPerSecond": 0.6333122229259025,
      "grade": "slow",
      "version": "4.2.0",
      "fallback": false,
      "actualDevice": "webgpu",
      "acceleration": "partial",
      "gpuForwardQueueObserved": true,
      "accelerationDetails": "Instrumented GPUQueue.submit observes actual generation dispatch; CPU image preprocessing/postprocessing remain. Not a claim that every graph node runs on GPU.",
      "artifactRevision": "ea24b2d4e0bfae31f0a1299ba3fb892a2df064de",
      "browser": "157.0.8103.40",
      "loadTimingScope": "Public init with pinned local original-source snapshot, not Internet transfer."
    }
  },
  {
    "precision": "fp16",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "interiorPointPassed": [
        true,
        true,
        true
      ],
      "completeMasks": true,
      "passed": true,
      "exactStuffFusionPassed": true
    },
    "runtime": {
      "inferenceMs": 1377.5,
      "loadMs": 5137.199999988079,
      "totalMs": 6514.699999988079,
      "imagesPerSecond": 0.7259528130671506,
      "grade": "moderate",
      "version": "4.2.0",
      "fallback": false,
      "actualDevice": "webgpu",
      "acceleration": "partial",
      "gpuForwardQueueObserved": true,
      "accelerationDetails": "Instrumented GPUQueue.submit observes actual generation dispatch; CPU image preprocessing/postprocessing remain. Not a claim that every graph node runs on GPU.",
      "artifactRevision": "ea24b2d4e0bfae31f0a1299ba3fb892a2df064de",
      "browser": "157.0.8103.40",
      "loadTimingScope": "Public init with pinned local original-source snapshot, not Internet transfer."
    }
  },
  {
    "precision": "fp16",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "interiorPointPassed": [],
      "completeMasks": true,
      "passed": true,
      "exactStuffFusionPassed": true
    },
    "runtime": {
      "inferenceMs": 951.6999999880791,
      "loadMs": 5137.199999988079,
      "totalMs": 6088.899999976158,
      "imagesPerSecond": 1.0507512871834883,
      "grade": "moderate",
      "version": "4.2.0",
      "fallback": false,
      "actualDevice": "webgpu",
      "acceleration": "partial",
      "gpuForwardQueueObserved": true,
      "accelerationDetails": "Instrumented GPUQueue.submit observes actual generation dispatch; CPU image preprocessing/postprocessing remain. Not a claim that every graph node runs on GPU.",
      "artifactRevision": "ea24b2d4e0bfae31f0a1299ba3fb892a2df064de",
      "browser": "157.0.8103.40",
      "loadTimingScope": "Public init with pinned local original-source snapshot, not Internet transfer."
    }
  },
  {
    "precision": "q8",
    "device": "wasm",
    "status": "fail",
    "quality": {
      "interiorPointPassed": [
        false,
        false,
        false
      ],
      "completeMasks": true,
      "passed": false,
      "exactStuffFusionPassed": true
    },
    "runtime": {
      "inferenceMs": 19803,
      "loadMs": 4958.800000011921,
      "totalMs": 24761.80000001192,
      "imagesPerSecond": 0.050497399383931725,
      "grade": "slow",
      "version": "4.2.0",
      "fallback": false,
      "actualDevice": "wasm",
      "acceleration": "cpu",
      "gpuForwardQueueObserved": false,
      "accelerationDetails": "Instrumented GPUQueue.submit observes actual generation dispatch; CPU image preprocessing/postprocessing remain. Not a claim that every graph node runs on GPU.",
      "artifactRevision": "ea24b2d4e0bfae31f0a1299ba3fb892a2df064de",
      "browser": "157.0.8103.40",
      "loadTimingScope": "Public init with pinned local original-source snapshot, not Internet transfer."
    }
  },
  {
    "precision": "q8",
    "device": "wasm",
    "status": "fail",
    "quality": {
      "interiorPointPassed": [
        true,
        true,
        true
      ],
      "completeMasks": true,
      "passed": true,
      "exactStuffFusionPassed": true
    },
    "runtime": {
      "inferenceMs": 15396.09999999404,
      "loadMs": 4958.800000011921,
      "totalMs": 20354.90000000596,
      "imagesPerSecond": 0.06495151369505181,
      "grade": "slow",
      "version": "4.2.0",
      "fallback": false,
      "actualDevice": "wasm",
      "acceleration": "cpu",
      "gpuForwardQueueObserved": false,
      "accelerationDetails": "Instrumented GPUQueue.submit observes actual generation dispatch; CPU image preprocessing/postprocessing remain. Not a claim that every graph node runs on GPU.",
      "artifactRevision": "ea24b2d4e0bfae31f0a1299ba3fb892a2df064de",
      "browser": "157.0.8103.40",
      "loadTimingScope": "Public init with pinned local original-source snapshot, not Internet transfer."
    }
  },
  {
    "precision": "q8",
    "device": "wasm",
    "status": "fail",
    "quality": {
      "interiorPointPassed": [],
      "completeMasks": true,
      "passed": true,
      "exactStuffFusionPassed": true
    },
    "runtime": {
      "inferenceMs": 19143.30000001192,
      "loadMs": 4958.800000011921,
      "totalMs": 24102.100000023842,
      "imagesPerSecond": 0.05223759748838378,
      "grade": "slow",
      "version": "4.2.0",
      "fallback": false,
      "actualDevice": "wasm",
      "acceleration": "cpu",
      "gpuForwardQueueObserved": false,
      "accelerationDetails": "Instrumented GPUQueue.submit observes actual generation dispatch; CPU image preprocessing/postprocessing remain. Not a claim that every graph node runs on GPU.",
      "artifactRevision": "ea24b2d4e0bfae31f0a1299ba3fb892a2df064de",
      "browser": "157.0.8103.40",
      "loadTimingScope": "Public init with pinned local original-source snapshot, not Internet transfer."
    }
  },
  {
    "precision": "q8",
    "device": "webgpu",
    "status": "fail",
    "quality": {
      "interiorPointPassed": [
        false,
        false,
        false
      ],
      "completeMasks": true,
      "passed": false,
      "exactStuffFusionPassed": true
    },
    "runtime": {
      "inferenceMs": 20442.40000000596,
      "loadMs": 5603.300000011921,
      "totalMs": 26045.70000001788,
      "imagesPerSecond": 0.04891793527177379,
      "grade": "slow",
      "version": "4.2.0",
      "fallback": false,
      "actualDevice": "webgpu",
      "acceleration": "partial",
      "gpuForwardQueueObserved": true,
      "accelerationDetails": "Instrumented GPUQueue.submit observes actual generation dispatch; CPU image preprocessing/postprocessing remain. Not a claim that every graph node runs on GPU.",
      "artifactRevision": "ea24b2d4e0bfae31f0a1299ba3fb892a2df064de",
      "browser": "157.0.8103.40",
      "loadTimingScope": "Public init with pinned local original-source snapshot, not Internet transfer."
    }
  },
  {
    "precision": "q8",
    "device": "webgpu",
    "status": "fail",
    "quality": {
      "interiorPointPassed": [
        true,
        true,
        true
      ],
      "completeMasks": true,
      "passed": true,
      "exactStuffFusionPassed": true
    },
    "runtime": {
      "inferenceMs": 15775.09999999404,
      "loadMs": 5603.300000011921,
      "totalMs": 21378.40000000596,
      "imagesPerSecond": 0.06339104031038649,
      "grade": "slow",
      "version": "4.2.0",
      "fallback": false,
      "actualDevice": "webgpu",
      "acceleration": "partial",
      "gpuForwardQueueObserved": true,
      "accelerationDetails": "Instrumented GPUQueue.submit observes actual generation dispatch; CPU image preprocessing/postprocessing remain. Not a claim that every graph node runs on GPU.",
      "artifactRevision": "ea24b2d4e0bfae31f0a1299ba3fb892a2df064de",
      "browser": "157.0.8103.40",
      "loadTimingScope": "Public init with pinned local original-source snapshot, not Internet transfer."
    }
  },
  {
    "precision": "q8",
    "device": "webgpu",
    "status": "fail",
    "quality": {
      "interiorPointPassed": [],
      "completeMasks": true,
      "passed": true,
      "exactStuffFusionPassed": true
    },
    "runtime": {
      "inferenceMs": 19491.19999998808,
      "loadMs": 5603.300000011921,
      "totalMs": 25094.5,
      "imagesPerSecond": 0.051305204399965706,
      "grade": "slow",
      "version": "4.2.0",
      "fallback": false,
      "actualDevice": "webgpu",
      "acceleration": "partial",
      "gpuForwardQueueObserved": true,
      "accelerationDetails": "Instrumented GPUQueue.submit observes actual generation dispatch; CPU image preprocessing/postprocessing remain. Not a claim that every graph node runs on GPU.",
      "artifactRevision": "ea24b2d4e0bfae31f0a1299ba3fb892a2df064de",
      "browser": "157.0.8103.40",
      "loadTimingScope": "Public init with pinned local original-source snapshot, not Internet transfer."
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "fail",
    "quality": {
      "passed": false,
      "reason": "Initialization/runtime failed; no inference or quality pass."
    },
    "runtime": "Not embedded",
    "failure": "Error: page.evaluate: Target page, context or browser has been closed"
  },
  {
    "precision": "fp16",
    "device": "wasm",
    "status": "fail",
    "quality": {
      "passed": false,
      "reason": "Initialization/runtime failed; no inference or quality pass."
    },
    "runtime": "Not embedded",
    "failure": "Error: page.evaluate: Error: [WorkerError:runtime_error] init: Can't create a session. ERROR_CODE: 1, ERROR_MESSAGE: /mnt/vss/_work/1/s/onnxruntime/core/graph/graph_utils.cc:30 int onnxruntime::graph_utils::GetIndexFromName(const Node &, const std::string &, bool) itr != node_args.end() was false. Attempting to get index by a name which does not exist:InsertedPrecisionFreeCast_/decoder/layers.5/encoder_attn_layer_norm/Constant_output_0for node: /encoder/layers.0/self_attn_layer_norm/Mul/SimplifiedLayerNormFusion/\n\n    at createError (http://127.0.0.1:59037/dist/index.mjs:13:17)\n    at createWorkerError (http://127.0.0.1:59037/dist/index.mjs:29:10)\n    at WorkerManager.parseWorkerError (http://127.0.0.1:59037/dist/index.mjs:713:12)\n    at Worker.handleMessage (http://127.0.0.1:59037/dist/index.mjs:687:42)"
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "completeMasks": true,
      "negativePersonDogPassed": true,
      "scope": "Small control only; no broad accuracy claim."
    },
    "runtime": {
      "inferenceMs": 1337.5,
      "loadMs": 5435.4000000059605,
      "totalMs": 6772.9000000059605,
      "imagesPerSecond": 0.7476635514018691,
      "grade": "moderate",
      "version": "4.2.0",
      "actualDevice": "webgpu",
      "fallback": false,
      "artifactRevision": "ea24b2d4e0bfae31f0a1299ba3fb892a2df064de"
    }
  }
]

Something not quite right?

Tell us what happened with DETR. Loading, results, or the page itself—we’re here for all of it.

Attachments Optional

Up to 3 files · 50 MB each

Browser, OS, CPU/GPU, memory, screen, storage, and network details are included automatically. Model inputs, results, and browsing history are not collected.