Spaces:
Runtime error
Runtime error
File size: 2,379 Bytes
2e1d4b5 |
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 60 61 62 63 64 65 66 67 68 |
import argparse
import os.path
from texify.inference import batch_inference
from texify.model.model import load_model
from texify.model.processor import load_processor
from PIL import Image
from texify.settings import settings
from texify.util import is_valid_image
import json
def inference_single_image(image_path, json_path, model, processor):
image = Image.open(image_path)
text = batch_inference([image], model, processor)
write_data = [{"image_path": image_path, "text": text[0]}]
with open(json_path, "w+") as f:
json_repr = json.dumps(write_data, indent=4)
f.write(json_repr)
def inference_image_dir(image_dir, json_path, model, processor, max=None):
image_paths = [os.path.join(image_dir, image_name) for image_name in os.listdir(image_dir)]
image_paths = [ip for ip in image_paths if is_valid_image(ip)]
if max:
image_paths = image_paths[:max]
write_data = []
for i in range(0, len(image_paths), settings.BATCH_SIZE):
batch = image_paths[i:i+settings.BATCH_SIZE]
images = [Image.open(image_path) for image_path in batch]
text = batch_inference(images, model, processor)
for image_path, t in zip(batch, text):
write_data.append({"image_path": image_path, "text": t})
with open(json_path, "w+") as f:
json_repr = json.dumps(write_data, indent=4)
f.write(json_repr)
def main():
parser = argparse.ArgumentParser(description="OCR an image of a LaTeX equation.")
parser.add_argument("image", type=str, help="Path to image or folder of images to OCR.")
parser.add_argument("--max", type=int, help="Maximum number of images to OCR if a folder is passes.", default=None)
parser.add_argument("--json_path", type=str, help="Path to JSON file to save results to.", default=os.path.join(settings.DATA_DIR, "results.json"))
args = parser.parse_args()
image_path = args.image
model = load_model()
processor = load_processor()
json_path = os.path.abspath(args.json_path)
os.makedirs(os.path.dirname(json_path), exist_ok=True)
if os.path.isfile(image_path):
inference_single_image(image_path, json_path, model, processor)
else:
inference_image_dir(image_path, json_path, model, processor, args.max)
print(f"Wrote results to {json_path}")
if __name__ == "__main__":
main()
|