This is a quantized ONNX version of the
POrg/ocsai-d-web model, optimized for web deployment with Transformers.js.
This model assesses originality/creativity in figural drawings. It's a fine-tuned BEiT-large model that outputs a regression score indicating the creativity level of the input drawing.
1import { pipeline } from '@xenova/transformers';
2
3// Load the model
4const classifier = await pipeline('image-classification', 'your-username/ocsai-d-web-onnx');
5
6// Run inference on an image
7const result = await classifier('path/to/drawing.jpg');
8console.log(result);
This model is specifically designed for creativity assessment of figural drawings. The output is a single regression score that needs to be post-processed according to the original paper's methodology.
Based on
POrg/ocsai-d-web - please refer to the original model for citation information and detailed usage instructions.
The quantized model provides significant size reduction (~4x smaller) while maintaining compatibility with Transformers.js for browser-based inference.
