84 lines
2.7 KiB
Python
84 lines
2.7 KiB
Python
from huggingface_hub import hf_hub_download
|
|
from transformers import AutoImageProcessor, TableTransformerForObjectDetection
|
|
import torch
|
|
from PIL import Image
|
|
import gradio as gr
|
|
from gradio.themes.utils import sizes
|
|
import matplotlib.pyplot as plt
|
|
import io
|
|
|
|
|
|
|
|
theme = gr.themes.Default(radius_size=sizes.radius_none).set(
|
|
block_label_text_color = '#4D63FF',
|
|
block_title_text_color = '#4D63FF',
|
|
button_primary_text_color = '#4D63FF',
|
|
button_primary_background_fill='#FFFFFF',
|
|
button_primary_border_color='#4D63FF',
|
|
button_primary_background_fill_hover='#EDEFFF',
|
|
)
|
|
|
|
|
|
# visualization
|
|
COLORS = [
|
|
[0.000, 0.447, 0.741],
|
|
[0.850, 0.325, 0.098],
|
|
[0.929, 0.694, 0.125],
|
|
[0.494, 0.184, 0.556],
|
|
[0.466, 0.674, 0.188],
|
|
[0.301, 0.745, 0.933]
|
|
]
|
|
|
|
# Draw the bounding boxes on image.
|
|
def fig2img(fig):
|
|
buf = io.BytesIO()
|
|
fig.savefig(buf)
|
|
buf.seek(0)
|
|
img = Image.open(buf)
|
|
return img
|
|
|
|
|
|
def visualize_prediction(pil_img, results):
|
|
plt.figure(figsize=(16, 10))
|
|
plt.imshow(pil_img)
|
|
ax = plt.gca()
|
|
colors = COLORS * 100
|
|
for score, (xmin, ymin, xmax, ymax), color, label in zip(results["scores"].tolist(), results["boxes"].tolist(), colors, results["labels"]):
|
|
ax.add_patch(plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, fill=False, color=color, linewidth=3))
|
|
ax.text(xmin, ymin, f"{model.config.id2label[label.item()]}: {score:0.2f}", fontsize=15, bbox=dict(facecolor="yellow", alpha=0.5))
|
|
plt.axis("off")
|
|
return fig2img(plt.gcf())
|
|
|
|
|
|
image_processor = AutoImageProcessor.from_pretrained("microsoft/table-transformer-detection")
|
|
model = TableTransformerForObjectDetection.from_pretrained("microsoft/table-transformer-detection")
|
|
|
|
|
|
def table_detect(image):
|
|
inputs = image_processor(images=image, return_tensors="pt")
|
|
outputs = model(**inputs)
|
|
|
|
# convert outputs (bounding boxes and class logits) to COCO API
|
|
target_sizes = torch.tensor([image.size[::-1]])
|
|
results = image_processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[0]
|
|
|
|
return visualize_prediction(image, results)
|
|
|
|
with gr.Blocks(theme=theme, css="footer {visibility: hidden}") as demo:
|
|
gr.Markdown("""
|
|
<div align='center' ><font size='60'>表格检测</font></div>
|
|
""")
|
|
with gr.Row():
|
|
with gr.Column():
|
|
box1 = gr.Image(label="图片", type="pil")
|
|
with gr.Row():
|
|
button = gr.Button("提交", variant="primary")
|
|
box2 = gr.Image(label="图片")
|
|
|
|
button.click(fn=table_detect, inputs=box1, outputs=box2)
|
|
examples = gr.Examples(examples=[['test.png']], inputs=[box1], label="例子")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
demo.queue(concurrency_count=3).launch(server_name = "0.0.0.0")
|