Downloads · 30 days
21
33% of all-time downloads
rshelby17/fashion-clip-onnx
fashion-clip-onnx is a zero-shot image classification model from rshelby17. Use it for the zero-shot image classification task on the model card, and read the license before you ship it in a product. It is set up for transformers.js. The card lists the license as mit.
ONNX export of patrickjohncyh/fashion-clip for in-browser use with transformers.js. Used by ReWear to classify garment attributes (color, material, pattern, style) client-side.
Downloads · 30 days
21
33% of all-time downloads
All-time downloads
64
Public
Repo size
236 MB
Likes
0
Public
Click a slice to open those files.
.onnx236 MB · 98%
From the Hugging Face model README
ONNX export of patrickjohncyh/fashion-clip for in-browser use with transformers.js. Used by ReWear to classify garment attributes (color, material, pattern, style) client-side.
onnx/model_quantized.onnx — int8 weights (MatMul-only quantization, so it
runs in onnxruntime-web; Conv layers kept float to avoid the unsupported
ConvInteger op). ~225 MB.import { pipeline } from "@huggingface/transformers";
const clf = await pipeline("zero-shot-image-classification", "<user>/fashion-clip-onnx", { dtype: "q8" });
const out = await clf(imageUrl, ["a photo of a blue colored garment", "a photo of a red colored garment"]);