Upload 5 files

Dockerfile

@@ -0,0 +1,15 @@
+# Usa una imagen base de Python
+FROM python:3.9
+# Establece el directorio de trabajo
+WORKDIR /code
+
+# Copia los archivos necesarios al contenedor
+COPY ./requirements.txt /code/requirements.txt
+RUN pip install --no-cache-dir -r /code/requirements.txt
+
+COPY . .
+
+RUN chmod -R 777 /code
+
+# Comando para ejecutar la aplicación
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,52 @@
+from keras.api.models import Sequential
+from keras.api.layers import InputLayer, Dense
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+import numpy as np
+from typing import List
+
+
+class InputData(BaseModel):
+    data: List[float]  # Lista de características numéricas (flotantes)
+
+
+app = FastAPI()
+
+
+# Función para construir el modelo manualmente
+def build_model():
+    model = Sequential(
+        [
+            InputLayer(
+                input_shape=(2,), name="dense_2_input"
+            ),  # Ajusta el tamaño de entrada según tu modelo
+            Dense(16, activation="relu", name="dense_2"),
+            Dense(1, activation="sigmoid", name="dense_3"),
+        ]
+    )
+    model.load_weights(
+        "model.h5"
+    )  # Asegúrate de que los nombres de las capas coincidan para que los pesos se carguen correctamente
+    model.compile(
+        loss="mean_squared_error", optimizer="adam", metrics=["binary_accuracy"]
+    )
+    return model
+
+
+model = build_model()  # Construir el modelo al iniciar la aplicación
+
+
+# Ruta de predicción
+@app.post("/predict/")
+async def predict(data: InputData):
+    print(f"Data: {data}")
+    global model
+    try:
+        # Convertir la lista de entrada a un array de NumPy para la predicción
+        input_data = np.array(data.data).reshape(
+            1, -1
+        )  # Asumiendo que la entrada debe ser de forma (1, num_features)
+        prediction = model.predict(input_data).round()
+        return {"prediction": prediction.tolist()}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))

model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c77ee4f3b494b48b05355ea63692c68a94499890f2f8044406b6c45ea785599f
+size 13864

model.json

@@ -0,0 +1 @@
+{"class_name": "Sequential", "config": {"name": "sequential_1", "layers": [{"module": "keras.layers", "class_name": "InputLayer", "config": {"batch_input_shape": [null, 2], "dtype": "float32", "sparse": false, "ragged": false, "name": "dense_2_input"}, "registered_name": null}, {"module": "keras.layers", "class_name": "Dense", "config": {"name": "dense_2", "trainable": true, "dtype": "float32", "batch_input_shape": [null, 2], "units": 16, "activation": "relu", "use_bias": true, "kernel_initializer": {"module": "keras.initializers", "class_name": "GlorotUniform", "config": {"seed": null}, "registered_name": null}, "bias_initializer": {"module": "keras.initializers", "class_name": "Zeros", "config": {}, "registered_name": null}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "registered_name": null, "build_config": {"input_shape": [null, 2]}}, {"module": "keras.layers", "class_name": "Dense", "config": {"name": "dense_3", "trainable": true, "dtype": "float32", "units": 1, "activation": "sigmoid", "use_bias": true, "kernel_initializer": {"module": "keras.initializers", "class_name": "GlorotUniform", "config": {"seed": null}, "registered_name": null}, "bias_initializer": {"module": "keras.initializers", "class_name": "Zeros", "config": {}, "registered_name": null}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "registered_name": null, "build_config": {"input_shape": [null, 16]}}]}, "keras_version": "2.15.0", "backend": "tensorflow"}

requirements.txt

@@ -0,0 +1,5 @@
+tensorflow
+keras
+fastapi
+numpy
+pydantic