---
family: u2net
license: mit
model_id: cloth-segmentation-u2net
source_url: https://huggingface.co/litert-community/Cloth-Segmentation-U2Net-LiteRT
task: image-segmentation
---

# cloth-segmentation-u2net

| | |
|---|---|
| **Task** | image-segmentation |
| **Family** | u2net |
| **Source** | https://huggingface.co/litert-community/Cloth-Segmentation-U2Net-LiteRT |
| **License** | mit |

## Conversion

| | |
|---|---|
| **Tool** | litert-torch 0.10.0 (editable dev checkout 115a136 + local patches) |
| **Command** | `python clothseg/scripts/build_clothseg.py` |
| **Quantization** | none — fp32 (artifact tensors: 493 float32, no float16/int8) |

## Artifacts

| File | SHA-256 | Size (MB) |
|---|---|---|
| `83847c44a07121d89a4ef964b7b865961c05cbdaaebece13bf592dfff0e4b82a.tflite` | `71b488370fe0ed204a8f7c09332ae4e6e6562c40148caec543c75b4d5153b082` | 168.133 |

## Performance

No benchmark data yet.

## Browser (LiteRT.js)

Model-level sweep results — measured behavior of this exact `.tflite` in the browser, only meaningful together with the environment that produced it. Full records (failure class, error evidence, sweep config): `data/sweep/2.5.3/2026-08-11/cloth-segmentation-u2net.json`.

| Backend | Status | Full delegation | Output match | Max rel diff | Latency p50 (ms) | Environment | Date | Provenance |
|---|---|---|---|---|---|---|---|---|
| wasm_xnnpack | pass | - | - | - | 9313.855 | mac-studio-m4-max · chromium 151.0.7922.34 headless · macOS · @litertjs/core 2.5.3 | 2026-08-11 | measured |
| webgpu_mldrift | output_mismatch | yes | MISMATCH | 0.16794617052023122 | 114.715 | mac-studio-m4-max · chromium 151.0.7922.34 headless · macOS · @litertjs/core 2.5.3 | 2026-08-11 | measured |

## Device runs (NPU / LiteRT-LM)

Model-level on-device results — measured behavior of this exact artifact on the recorded device, only meaningful together with that environment. Throughput is conditional on the measured prompt length (Prompt (tokens); '-' = the source stated none): rows differing only there are different measurements, not re-runs. Full records (failure classes, log evidence): `data/device_runs/2.2.0.dev20260804/2026-08-31/cloth-segmentation-u2net__raspberry-pi-5.json`.

| Device | Accelerator | Status | Full delegation | Output match | Prompt (tokens) | Latency p50 (ms) | Prefill tok/s | Decode tok/s | TTFT (ms) | Peak mem (MB) | Environment | Date | Provenance |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| raspberry-pi-5 | cpu_xnnpack | pass | - | - | - | 6544.635 | - | - | - | 1822.56 | Raspberry Pi 5 Model B Rev 1.1 · litert 2.2.0.dev20260804 · Linux-6.18.34+rpt-rpi-2712-aarch64-with-glibc2.41 | 2026-08-31 | measured |

## Pitfalls

- Strip the 'module.' prefix when loading the upstream checkpoint (zoo README L584).

---

_Rendered by `edge-card` from `card.json` (the source of truth); edit the inputs, not this file._