ResNet-50 ImageNet-1k classification
Browser-ready import artifacts for image-classification, produced by SkillSafe's
reproducible converter (models/ in skillsafe.ai)
from a pinned upstream source. Every byte here is derivable from that source plus
the recipe below; nothing was edited by hand.
Provenance
| Upstream | https://huggingface.co/Xenova/resnet-50/tree/a16f29143f08c4e5c5a4a89f6f185d8edac4b6af |
| Upstream SHA-256 / commit | a16f29143f08c4e5c5a4a89f6f185d8edac4b6af |
| Recipe | recipes/resnet-50.yaml — sha256 30c6af463f3b5e93cc825e5f3e14e02b716c640b4388755d3a1c40b6cdfe3bfc |
| Toolchain | Python 3.12.13, torch 2.10.0, onnx 1.23.0, onnxruntime 1.30.0 on Darwin 25.6.0 arm64 |
| Converted | 2026-09-22T21:54:11+00:00 |
Files
| file | class | size | SHA-256 |
|---|---|---|---|
config.json |
bundle | 0.07 MB | 47c111a56be828e8b0c4b7860be8279abf78aae0287c9baf5981dc813bf43606 |
onnx/model.onnx |
registry (fp32) | 97.43 MB | 7e6fd9fa712c93139c2dab22fe109232d9fb760e3ddea117110f72de9d4f665a |
onnx/model_quantized.onnx |
registry (q8) | 24.59 MB | 5cece77e014d3ff4b7175767614d448fc50b7804e9e8d47d192f69e357fdb232 |
preprocessor_config.json |
bundle | 0.00 MB | c5dad07e638b787156e18cdeb9bfc46032aa596e1c336f8a1229b7c4c6a62216 |
registry files are parameter files served from models.skillsafe.ai once vetted;
bundle files ship inside an app; registry-shared is a runtime library reused by
every model of the same architecture.
Verification
Imported as published upstream (no conversion). Each file is pinned by SHA-256 to its source; every ONNX file passed onnx.checker and a CPU smoke run under onnxruntime with zero-filled inputs at the declared shapes:
| file | inputs | outputs | ms |
|---|---|---|---|
onnx/model.onnx |
pixel_values[1, 3, 224, 224] | logits[1, 1000] | 12.1 |
onnx/model_quantized.onnx |
pixel_values[1, 3, 224, 224] | logits[1, 1000] | 10.4 |
Use in the browser
import * as ort from "onnxruntime-web";
const session = await ort.InferenceSession.create("https://huggingface.co/skillsafe-ai/resnet-50/resolve/main/onnx/model.onnx", { executionProviders: ["webgpu", "wasm"] });
Contract (onnx/model.onnx): input pixel_values float32 ['batch_size', 'num_channels', 'height', 'width'] → output logits float32 ['batch_size', 1000]. Opset 11.
Licence and attribution
ResNet-50: Microsoft (He et al.), Apache License 2.0 (https://huggingface.co/microsoft/resnet-50); ONNX export by Xenova.
Licence: Apache-2.0 — notice: https://huggingface.co/microsoft/resnet-50/blob/main/README.md. The conversion recipe and this model card are part of the SkillSafe repository and carry its licence; the weights remain under the upstream licence above.
The full manifest.json in this repo records the recipe, sources, toolchain
(including the uv.lock hash) and per-file verification numbers.
- Downloads last month
- 8