File size: 4,724 Bytes
f1d8127
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
import matplotlib.pyplot as plt
import matplotlib.patches as patches
from matplotlib.patches import Patch
import io
from PIL import Image

from transformers import TableTransformerImageProcessor, AutoModelForObjectDetection
import torch

import gradio as gr

# load table detection model
processor = TableTransformerImageProcessor(max_size=800)
model = AutoModelForObjectDetection.from_pretrained("microsoft/table-transformer-detection", revision="no_timm")


# for output bounding box post-processing
def box_cxcywh_to_xyxy(x):
    x_c, y_c, w, h = x.unbind(-1)
    b = [(x_c - 0.5 * w), (y_c - 0.5 * h), (x_c + 0.5 * w), (y_c + 0.5 * h)]
    return torch.stack(b, dim=1)


def rescale_bboxes(out_bbox, size):
    img_w, img_h = size
    b = box_cxcywh_to_xyxy(out_bbox)
    b = b * torch.tensor([img_w, img_h, img_w, img_h], dtype=torch.float32)
    return b


def outputs_to_objects(outputs, img_size, id2label):
    m = outputs.logits.softmax(-1).max(-1)
    pred_labels = list(m.indices.detach().cpu().numpy())[0]
    pred_scores = list(m.values.detach().cpu().numpy())[0]
    pred_bboxes = outputs['pred_boxes'].detach().cpu()[0]
    pred_bboxes = [elem.tolist() for elem in rescale_bboxes(pred_bboxes, img_size)]

    objects = []
    for label, score, bbox in zip(pred_labels, pred_scores, pred_bboxes):
        class_label = id2label[int(label)]
        if not class_label == 'no object':
            objects.append({'label': class_label, 'score': float(score),
                            'bbox': [float(elem) for elem in bbox]})

    return objects


def fig2img(fig):
    """Convert a Matplotlib figure to a PIL Image and return it"""
    buf = io.BytesIO()
    fig.savefig(buf)
    buf.seek(0)
    img = Image.open(buf)
    return img


def visualize_detected_tables(img, det_tables):
    plt.imshow(img, interpolation="lanczos")
    fig = plt.gcf()
    fig.set_size_inches(20, 20)
    ax = plt.gca()

    for det_table in det_tables:
        bbox = det_table['bbox']

        if det_table['label'] == 'table':
            facecolor = (1, 0, 0.45)
            edgecolor = (1, 0, 0.45)
            alpha = 0.3
            linewidth = 2
            hatch='//////'
        elif det_table['label'] == 'table rotated':
            facecolor = (0.95, 0.6, 0.1)
            edgecolor = (0.95, 0.6, 0.1)
            alpha = 0.3
            linewidth = 2
            hatch='//////'
        else:
            continue

        rect = patches.Rectangle(bbox[:2], bbox[2]-bbox[0], bbox[3]-bbox[1], linewidth=linewidth,
                                    edgecolor='none',facecolor=facecolor, alpha=0.1)
        ax.add_patch(rect)
        rect = patches.Rectangle(bbox[:2], bbox[2]-bbox[0], bbox[3]-bbox[1], linewidth=linewidth,
                                    edgecolor=edgecolor,facecolor='none',linestyle='-', alpha=alpha)
        ax.add_patch(rect)
        rect = patches.Rectangle(bbox[:2], bbox[2]-bbox[0], bbox[3]-bbox[1], linewidth=0,
                                    edgecolor=edgecolor,facecolor='none',linestyle='-', hatch=hatch, alpha=0.2)
        ax.add_patch(rect)

    plt.xticks([], [])
    plt.yticks([], [])

    legend_elements = [Patch(facecolor=(1, 0, 0.45), edgecolor=(1, 0, 0.45),
                                label='Table', hatch='//////', alpha=0.3),
                        Patch(facecolor=(0.95, 0.6, 0.1), edgecolor=(0.95, 0.6, 0.1),
                                label='Table (rotated)', hatch='//////', alpha=0.3)]
    plt.legend(handles=legend_elements, bbox_to_anchor=(0.5, -0.02), loc='upper center', borderaxespad=0,
                    fontsize=10, ncol=2)
    plt.gcf().set_size_inches(10, 10)
    plt.axis('off')

    return fig


def detect_table(image):
    # prepare image for the model
    pixel_values = processor(image, return_tensors="pt").pixel_values

    # forward pass
    with torch.no_grad():
        outputs = model(pixel_values)

    # postprocess to get detected tables
    id2label = model.config.id2label
    id2label[len(model.config.id2label)] = "no object"
    detected_tables = outputs_to_objects(outputs, image.size, id2label)

    # visualize
    fig = visualize_detected_tables(img, detected_tables)
    image = fig2img(fig)

    return image
    

title = "Demo: table detection with Table Transformer"
description = "Demo for the Table Transformer (TATR)."
examples =[['example_pdf.jpg']]

interface = gr.Interface(fn=detect_table, 
                     inputs=gr.Image(type="pil"), 
                     outputs=gr.Image(type="pil", label="Detected table"),
                     title=title,
                     description=description,
                     examples=examples,
                     enable_queue=True)
interface.launch(debug=True)