Hugging Face's logo

Spaces:
Ammar-alhaj-ali
/
LayoutLMv3-Invoice
Runtime error

App Files Community
LayoutLMv3-Invoice
File size: 4,105 Bytes 
63a9bd9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8587e07
63a9bd9
 
 
 
 
 
 
8587e07
63a9bd9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
069dc6d
4dd4b40
63a9bd9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
 
import os
os.system('pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu')
os.system('pip install -q git+https://github.com/huggingface/transformers.git')
os.system('pip install pytesseract')



import gradio as gr
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


processor = AutoProcessor.from_pretrained("Ammar-alhaj-ali/LayoutLMv3-Fine-Tuning-Invoice", apply_ocr=True)
model = AutoModelForTokenClassification.from_pretrained("Ammar-alhaj-ali/LayoutLMv3-Fine-Tuning-Invoice")



# define id2label, label2color
labels = ['O', 'B-ABN', 'B-BILLER', 'B-BILLER_ADDRESS', 'B-BILLER_POST_CODE', 'B-DUE_DATE', 'B-GST', 'B-INVOICE_DATE', 'B-INVOICE_NUMBER', 'B-SUBTOTAL', 'B-TOTAL', 'I-BILLER_ADDRESS']
id2label = {v: k for v, k in enumerate(labels)}
label2color = {
    "B-ABN": 'blue',
    "B-BILLER": 'red',
    "B-BILLER_ADDRESS": 'green',
    "B-BILLER_POST_CODE": 'orange',
    "B-DUE_DATE": "blue",
    "B-GST": 'green',
    "B-INVOICE_DATE": 'violet',
    "B-INVOICE_NUMBER": 'orange',
    "B-SUBTOTAL": 'green',
    "B-TOTAL": 'red',
    "I-BILLER_ADDRESS": 'blue',
    "O": 'orange'
  }  

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]) #label2color[predicted_label]
        draw.text((box[0]+10, box[1]-10), text=predicted_label, fill=label2color[predicted_label], font=font) #label2color[predicted_label]
    
    return image


title = "Extracting information from invoice Dataset using the LayoutLMv3 "
description = "I Fine tuned LayoutLMv3 on Invoice Dataset [darentang/generated] "

article="<b>References</b><br>[1] Y. Xu et al., “LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking.” 2022. <a href='https://arxiv.org/abs/2204.08387'>Paper Link</a><br>[2]" 

examples =[['img1.png'],['img2.png'],['img3.png']]

css = """.output_image, .input_image {height: 600px !important}"""

iface = gr.Interface(fn=process_image, 
                     inputs=gr.inputs.Image(type="pil"), 
                     outputs=gr.outputs.Image(type="pil", label="annotated image"),
                     title=title,
                     description=description,
                     article=article,
                     examples=examples,
                     css=css,
                     analytics_enabled = True, enable_queue=True)

iface.launch(inline=False, share=False, debug=False)