Update app.py

app.py

@@ -4,67 +4,72 @@ import onnxruntime as rt
 from torchvision import transforms as T
 from PIL import Image
 from tokenizer_base import Tokenizer
-import pathlib
-import os
-import gradio as gr
-from huggingface_hub import Repository
-
-
+import io
+import base64
+from fastapi import FastAPI, UploadFile, File
+from pydantic import BaseModel
+import numpy as np
 
+# Параметры модели
 model_file = "captcha.onnx"
 img_size = (32,128)
 charset = r"0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"
 tokenizer_base = Tokenizer(charset)
 
+# Инициализация преобразования изображений
 def get_transform(img_size):
-        transforms = []
-        transforms.extend([
-            T.Resize(img_size, T.InterpolationMode.BICUBIC),
-            T.ToTensor(),
-            T.Normalize(0.5, 0.5)
-        ])
-        return T.Compose(transforms)
+    transforms = []
+    transforms.extend([
+        T.Resize(img_size, T.InterpolationMode.BICUBIC),
+        T.ToTensor(),
+        T.Normalize(0.5, 0.5)
+    ])
+    return T.Compose(transforms)
 
 def to_numpy(tensor):
     return tensor.detach().cpu().numpy() if tensor.requires_grad else tensor.cpu().numpy()
 
+# Загрузка модели
 def initialize_model(model_file):
     transform = get_transform(img_size)
-    # Onnx model loading
     onnx_model = onnx.load(model_file)
     onnx.checker.check_model(onnx_model)
     ort_session = rt.InferenceSession(model_file)
-    return transform,ort_session 
+    return transform, ort_session 
+
+# Инициализация модели
+transform, ort_session = initialize_model(model_file=model_file)
 
+# Функция для получения текста с изображения
 def get_text(img_org):
-    # img_org = Image.open(image_path)
-    # Preprocess. Model expects a batch of images with shape: (B, C, H, W)
     x = transform(img_org.convert('RGB')).unsqueeze(0)
-
-    # compute ONNX Runtime output prediction
     ort_inputs = {ort_session.get_inputs()[0].name: to_numpy(x)}
     logits = ort_session.run(None, ort_inputs)[0]
     probs = torch.tensor(logits).softmax(-1)
     preds, probs = tokenizer_base.decode(probs)
     preds = preds[0]
-    print(preds)
     return preds
 
-transform,ort_session = initialize_model(model_file=model_file)
+# FastAPI приложение
+app = FastAPI()
+
+# Модель данных для работы с запросом
+class ImageData(BaseModel):
+    image: str
 
-gr.Interface(
-    get_text,
-    inputs=gr.Image(type="pil"),
-    outputs=gr.Textbox(),
-    title="Text Captcha Reader",
-    examples=["8000.png","11JW29.png","2a8486.jpg","2nbcx.png",
-             "000679.png","000HU.png","00Uga.png.jpg","00bAQwhAZU.jpg",
-             "00h57kYf.jpg","0EoHdtVb.png","0JS21.png","0p98z.png","10010.png"]
-).launch()
+# Endpoint для обработки изображения в формате Base64
+@app.post("/predict/")
+async def predict(data: ImageData):
+    try:
+        # Декодируем Base64
+        img_data = base64.b64decode(data.image.split(",")[1])
+        img = Image.open(io.BytesIO(img_data))
+        result = get_text(img)
+        return {"result": result}
+    except Exception as e:
+        return {"error": str(e)}
 
-# if __name__ == "__main__":
-#     image_path = "8000.png"
-#     preds,probs = get_text(image_path)
-#     print(preds[0])
-     
+# Запуск сервера (для локального тестирования)
+# Если вы хотите запустить сервер на хосте, используйте команду:
+# uvicorn filename:app --reload