File size: 3,091 Bytes
68f2d06 |
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 |
import gradio as gr
import torch
from PIL import Image
import numpy as np
from transformers import AutoModel, AutoConfig
from model import Pix2TextModel, Pix2TextConfig
import os
# Model yükleme fonksiyonu
def load_model():
try:
# Hugging Face'den model yükle
config = AutoConfig.from_pretrained("./", trust_remote_code=True)
model = AutoModel.from_pretrained("./", trust_remote_code=True)
return model
except Exception as e:
print(f"Model yükleme hatası: {e}")
# Yerel model oluştur
config = Pix2TextConfig()
model = Pix2TextModel(config)
return model
model = load_model()
def predict_text(image):
"""Görüntüden metin çıkarma fonksiyonu"""
try:
if image is None:
return "Lütfen bir görüntü yükleyin."
# PIL Image'a çevir
if isinstance(image, np.ndarray):
image = Image.fromarray(image)
# Model ile tahmin yap
result = model.predict(image)
return f"Çıkarılan Metin: {result}"
except Exception as e:
return f"Hata oluştu: {str(e)}"
def create_demo():
"""Gradio demo arayüzü oluştur"""
with gr.Blocks(title="Pix2Text - Görüntüden Metin Çıkarma") as demo:
gr.Markdown("# 🔤 Pix2Text Model Test Arayüzü")
gr.Markdown("Görüntü yükleyerek metin çıkarma işlemini test edebilirsiniz.")
with gr.Row():
with gr.Column():
image_input = gr.Image(
label="Görüntü Yükleyin",
type="pil",
height=400
)
predict_btn = gr.Button("Metni Çıkar", variant="primary")
with gr.Column():
output_text = gr.Textbox(
label="Çıkarılan Metin",
lines=10,
placeholder="Sonuç burada görünecek..."
)
# Event handlers
predict_btn.click(
fn=predict_text,
inputs=[image_input],
outputs=[output_text]
)
# Örnek görüntüler
gr.Examples(
examples=[
["example1.jpg"],
["example2.png"]
],
inputs=[image_input],
outputs=[output_text],
fn=predict_text,
cache_examples=False
)
gr.Markdown("### Model Bilgileri")
gr.Markdown("""
- **Model Tipi**: Pix2Text (Görüntüden Metin Çıkarma)
- **Framework**: PyTorch + Transformers
- **Desteklenen Formatlar**: JPG, PNG, JPEG
- **Maksimum Görüntü Boyutu**: 2048x2048 piksel
""")
return demo
if __name__ == "__main__":
demo = create_demo()
demo.launch(
server_name="0.0.0.0",
server_port=7860,
share=True
) |