up

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.12-slim
+
+WORKDIR /app
+
+COPY ./requirements.txt .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 7860
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,48 @@
+from fastapi import FastAPI, File, UploadFile
+from transformers import ViTImageProcessor, ViTForImageClassification
+from PIL import Image
+import torch
+import io
+
+MODEL_NAME = "ahmed-masoud/sign_language_translator"
+
+
+try:
+    processor = ViTImageProcessor.from_pretrained(MODEL_NAME)
+    
+    model = ViTForImageClassification.from_pretrained(MODEL_NAME)
+    
+    print(f"Modelo '{MODEL_NAME}' cargado")
+    
+except Exception as e:
+    print(f"Error al cargar el modelo {e}")
+    model = None
+    processor = None
+
+app = FastAPI(title="API de ASL con modelo de HF")
+
+
+@app.post("/predict/")
+async def translate_sign(file: UploadFile = File(...)):
+    if not model or not processor:
+        return {"error": "Modelo no disponible."}
+
+    image_bytes = await file.read()
+    image = Image.open(io.BytesIO(image_bytes))
+
+    inputs = processor(images=image, return_tensors="pt")
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+
+    predicted_class_idx = logits.argmax(-1).item()
+    
+    predicted_label = model.config.id2label[predicted_class_idx]
+
+    return {"prediction": predicted_label}
+
+
+@app.get("/")
+def read_root():
+    return {"message": "API ok. Usa el endpoint /predict/ para predecir."}

requirements.txt

@@ -0,0 +1,7 @@
+fastapi
+uvicorn[standard]
+python-multipart
+Pillow
+transformers[torch]
+torch
+torchvision