import os os.system('pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu') import warnings warnings.filterwarnings("ignore") import numpy as np from transformers import AutoModelForTokenClassification from datasets.features import ClassLabel from transformers import AutoProcessor from datasets import Features, Sequence, ClassLabel, Value, Array2D, Array3D import torch from datasets import load_metric from transformers import LayoutLMv3ForTokenClassification from transformers.data.data_collator import default_data_collator from transformers import AutoModelForTokenClassification from datasets import load_dataset from PIL import Image, ImageDraw, ImageFont import pytesseract #from imgprocessing import processed_image processor = AutoProcessor.from_pretrained("kaydee/layoutlmv3-wildreceipt", apply_ocr=True) model = AutoModelForTokenClassification.from_pretrained("kaydee/layoutlmv3-wildreceipt") dataset = load_dataset("kaydee/wildreceipt", split="test") labels = dataset.features['ner_tags'].feature.names id2label = {v: k for v, k in enumerate(labels)} label2color = { "Date_key": 'red', "Date_value": 'green', "Ignore": 'orange', "Others": 'orange', "Prod_item_key": 'red', "Prod_item_value": 'green', "Prod_price_key": 'red', "Prod_price_value": 'green', "Prod_quantity_key": 'red', "Prod_quantity_value": 'green', "Store_addr_key": 'red', "Store_addr_value": 'green', "Store_name_key": 'red', "Store_name_value": 'green', "Subtotal_key": 'red', "Subtotal_value": 'green', "Tax_key": 'red', "Tax_value": 'green', "Tel_key": 'red', "Tel_value": 'green', "Time_key": 'red', "Time_value": 'green', "Tips_key": 'red', "Tips_value": 'green', "Total_key": 'red', "Total_value": 'blue' } def unnormalize_box(bbox, width, height): return [ width * (bbox[0] / 1000), height * (bbox[1] / 1000), width * (bbox[2] / 1000), height * (bbox[3] / 1000), ] def iob_to_label(label): return label def process_image(image): print(type(image)) width, height = image.size # encode encoding = processor(image, truncation=True, return_offsets_mapping=True, return_tensors="pt") offset_mapping = encoding.pop('offset_mapping') # forward pass outputs = model(**encoding) # get predictions predictions = outputs.logits.argmax(-1).squeeze().tolist() token_boxes = encoding.bbox.squeeze().tolist() # only keep non-subword predictions is_subword = np.array(offset_mapping.squeeze().tolist())[:,0] != 0 true_predictions = [id2label[pred] for idx, pred in enumerate(predictions) if not is_subword[idx]] true_boxes = [unnormalize_box(box, width, height) for idx, box in enumerate(token_boxes) if not is_subword[idx]] # draw predictions over the image draw = ImageDraw.Draw(image) font = ImageFont.load_default() for prediction, box in zip(true_predictions, true_boxes): predicted_label = iob_to_label(prediction) draw.rectangle(box, outline=label2color[predicted_label]) draw.text((box[0]+10, box[1]-10), text=predicted_label, fill=label2color[predicted_label], font=font) return image def main(img): image = process_image(img) return image