Spaces:
Running
Running
File size: 2,130 Bytes
ca97aa9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
import { AutoTokenizer, AutoProcessor, load_image, CLIPVisionModelWithProjection, CLIPTextModelWithProjection } from "../../../src/transformers.js";
import { MAX_TEST_EXECUTION_TIME, DEFAULT_MODEL_OPTIONS } from "../../init.js";
export default () => {
const models_to_test = ["hf-internal-testing/tiny-random-CLIPModel"];
it(
`CLIPTextModelWithProjection`,
async () => {
const model_id = models_to_test[0];
// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id, DEFAULT_MODEL_OPTIONS);
// Run tokenization
const texts = ["a photo of a car", "a photo of a football match"];
const text_inputs = tokenizer(texts, { padding: true, truncation: true });
// Compute embeddings
const { text_embeds } = await text_model(text_inputs);
// Ensure correct shapes
const expected_shape = [texts.length, text_model.config.projection_dim];
const actual_shape = text_embeds.dims;
expect(expected_shape).toEqual(actual_shape);
await text_model.dispose();
},
MAX_TEST_EXECUTION_TIME,
);
it(
`CLIPVisionModelWithProjection`,
async () => {
const model_id = models_to_test[0];
// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id, DEFAULT_MODEL_OPTIONS);
// Read image and run processor
const image = await load_image("https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/football-match.jpg");
const image_inputs = await processor(image);
// Compute embeddings
const { image_embeds } = await vision_model(image_inputs);
// Ensure correct shapes
const expected_shape = [1, vision_model.config.projection_dim];
const actual_shape = image_embeds.dims;
expect(expected_shape).toEqual(actual_shape);
await vision_model.dispose();
},
MAX_TEST_EXECUTION_TIME,
);
};
|