| """Generate deterministic RemoteCLIP-format image-text pairs.""" |
|
|
| from pathlib import Path |
|
|
| import numpy as np |
| import yaml |
|
|
|
|
| ROOT = Path(__file__).resolve().parents[1] |
|
|
|
|
| def make_split(count, config, seed): |
| rng = np.random.default_rng(seed) |
| data = config["data"] |
| size = data["image_size"] |
| classes = data["num_classes"] |
| images = np.empty((count, 3, size, size), dtype=np.float32) |
| tokens = np.zeros((count, data["context_length"]), dtype=np.int64) |
| labels = np.arange(count, dtype=np.int64) % classes |
| y, x = np.mgrid[0:size, 0:size].astype(np.float32) / max(size - 1, 1) |
| for index, label in enumerate(labels): |
| image = np.zeros((3, size, size), dtype=np.float32) |
| image[label % 3] = 0.55 + 0.35 * np.sin((label + 1) * np.pi * x) |
| image[(label + 1) % 3] += 0.25 * np.cos((label + 1) * np.pi * y) |
| images[index] = np.clip(image + rng.normal(0, 0.02, image.shape), 0, 1) |
| tokens[index, :4] = [label + 1, 16 + label, 32 + label, 48 + label] |
| return images, tokens, labels |
|
|
|
|
| def main(): |
| with (ROOT / "conf" / "config.yaml").open(encoding="utf-8") as handle: |
| config = yaml.safe_load(handle) |
| train = make_split(config["data"]["train_samples"], config, config["seed"]) |
| test = make_split(config["data"]["test_samples"], config, config["seed"] + 1) |
| output = ROOT / config["data"]["path"] |
| output.parent.mkdir(parents=True, exist_ok=True) |
| np.savez_compressed( |
| output, |
| train_images=train[0], |
| train_tokens=train[1], |
| train_labels=train[2], |
| test_images=test[0], |
| test_tokens=test[1], |
| test_labels=test[2], |
| data_source=np.asarray("synthetic"), |
| protocol=np.asarray(config["data"]["protocol"]), |
| ) |
| print( |
| f"generated={output.relative_to(ROOT)} train={len(train[0])} test={len(test[0])} " |
| f"data_source=synthetic protocol={config['data']['protocol']}" |
| ) |
|
|
|
|
| if __name__ == "__main__": |
| main() |
|
|
