Upload 8 files

Dockerfile

@@ -0,0 +1,26 @@
+FROM python:3.11-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+USER root
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+USER user
+
+COPY --chown=user requirements.txt .
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . .
+
+EXPOSE 7860
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,85 @@
+from fastapi import FastAPI, File, UploadFile
+from fastapi.responses import JSONResponse
+from fastapi.staticfiles import StaticFiles
+from fastapi.responses import FileResponse
+import numpy as np
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing.image import load_img, img_to_array
+from PIL import Image
+import io
+import tensorflow as tf
+from tensorflow.keras.layers import Dense
+
+app = FastAPI(title="Clasificador de Vehículos")
+
+class CompatDense(Dense):
+    def __init__(self, *Args, quantization_config=None, **kwargs):
+        # Eliminamos el problema de discusión y al padre
+        kwargs.pop('quantization_config', None)
+        super().__init__(*Args, **kwargs)
+
+# Cargar el modelo entrenado (arquitectura + pesos incluidos en modelo.h5)
+model = load_model(
+    'modelo/modelo.h5',
+    custom_objects={'Dense': CompatDense}
+)
+# Etiquetas de las clases, en el orden que usó ImageDataGenerator (alfabético)
+CLASS_NAMES = ['airplane', 'car', 'ship']   # 0: aéreo, 1: terrestre, 2: marítimo
+
+def preprocess_image(image: Image.Image):
+    """
+    Preprocesa la imagen para que coincida con el entrenamiento.
+    """
+    image = image.resize((150, 150))          # tamaño usado en el notebook
+    img_array = img_to_array(image)           # convierte a array (150,150,3)
+    img_array = img_array / 255.0             # normalización (rescale=1./255)
+    img_array = np.expand_dims(img_array, axis=0)  # añade dimensión batch
+    return img_array
+
+@app.post("/predict")
+async def predict(file: UploadFile = File(...)):
+    """
+    Recibe una imagen y devuelve la clase predicha con su confianza.
+    """
+    # Leer el contenido del archivo
+    contents = await file.read()
+    try:
+        # Convertir a imagen RGB
+        image = Image.open(io.BytesIO(contents)).convert('RGB')
+    except Exception:
+        return JSONResponse(
+            content={"error": "No se pudo leer la imagen. Asegúrate de enviar un archivo válido."},
+            status_code=400
+        )
+
+    # Preprocesar y predecir
+    processed = preprocess_image(image)
+    predictions = model.predict(processed)[0]   # array de 3 probabilidades
+
+    predicted_idx = np.argmax(predictions)
+    label = CLASS_NAMES[predicted_idx]
+    confidence = float(predictions[predicted_idx])
+
+    # Mapeo legible para el usuario
+    label_es = {"airplane": "Aéreo (Avión)", "car": "Terrestre (Coche)", "ship": "Marítimo (Barco)"}
+
+    return {
+        "prediccion": label_es[label],
+        "confianza": round(confidence, 4),
+        "probabilidades": {
+            "airplane": round(float(predictions[0]), 4),
+            "car": round(float(predictions[1]), 4),
+            "ship": round(float(predictions[2]), 4)
+        }
+    }
+
+app.mount("/static", StaticFiles(directory="static"), name="static")
+
+# Endpoint de bienvenida (opcional)
+@app.get("/")
+def read_index():
+    return FileResponse("static/index.html")
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)

modelo/modelo.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9bc227ef84ab70a013e28fab4142324a96180183565c6cd903c9227369f965
+size 269318872

modelo/modelo.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a286ad17c86fb09552ad270d0bb1cc1403da59d7cc36494676915634c885bc4b
+size 269313008

requirements.txt

@@ -0,0 +1,6 @@
+fastapi>=0.100.0
+uvicorn[standard]>=0.22.0
+python-multipart>=0.0.6
+tensorflow>=2.21.0
+Pillow>=10.0.0
+numpy>=1.24.0

static/app.js

@@ -0,0 +1,167 @@
+const API_URL = window.location.origin + '/predict'; // Ajusta si es necesario
+
+const uploadArea = document.getElementById('uploadArea');
+const fileInput = document.getElementById('fileInput');
+const previewSection = document.getElementById('previewSection');
+const previewImage = document.getElementById('previewImage');
+const predictBtn = document.getElementById('predictBtn');
+const spinner = document.getElementById('spinner');
+const btnText = document.getElementById('btnText');
+const resultSection = document.getElementById('resultSection');
+const resultIcon = document.getElementById('resultIcon');
+const resultPrediction = document.getElementById('resultPrediction');
+const confidenceBar = document.getElementById('confidenceBar');
+const confidenceValue = document.getElementById('confidenceValue');
+const probabilitiesList = document.getElementById('probabilitiesList');
+const uploadAnotherBtn = document.getElementById('uploadAnotherBtn');
+
+let selectedFile = null;
+
+// Prevenir comportamientos por defecto para drag and drop
+['dragenter', 'dragover', 'dragleave', 'drop'].forEach(eventName => {
+    uploadArea.addEventListener(eventName, preventDefaults, false);
+});
+
+function preventDefaults(e) {
+    e.preventDefault();
+    e.stopPropagation();
+}
+
+['dragenter', 'dragover'].forEach(eventName => {
+    uploadArea.addEventListener(eventName, () => uploadArea.classList.add('dragover'));
+});
+
+['dragleave', 'drop'].forEach(eventName => {
+    uploadArea.addEventListener(eventName, () => uploadArea.classList.remove('dragover'));
+});
+
+uploadArea.addEventListener('drop', handleDrop);
+uploadArea.addEventListener('click', () => fileInput.click());
+fileInput.addEventListener('change', handleFileSelect);
+
+function handleDrop(e) {
+    const dt = e.dataTransfer;
+    const files = dt.files;
+    if (files.length) {
+        handleFiles(files);
+    }
+}
+
+function handleFileSelect(e) {
+    handleFiles(e.target.files);
+}
+
+function handleFiles(files) {
+    if (!files || files.length === 0) return;
+    const file = files[0];
+    if (!file.type.startsWith('image/')) {
+        alert('Por favor selecciona una imagen válida (JPG, PNG, etc.)');
+        return;
+    }
+    selectedFile = file;
+
+    // Mostrar vista previa
+    const reader = new FileReader();
+    reader.onload = (e) => {
+        previewImage.src = e.target.result;
+        previewSection.classList.add('active');
+        predictBtn.disabled = false;
+        // Ocultar resultado anterior
+        resultSection.classList.remove('active');
+        uploadAnotherBtn.style.display = 'none';
+    };
+    reader.readAsDataURL(file);
+}
+
+predictBtn.addEventListener('click', classifyImage);
+
+async function classifyImage() {
+    if (!selectedFile) return;
+
+    // Estado de carga
+    predictBtn.disabled = true;
+    spinner.style.display = 'inline-block';
+    btnText.textContent = 'Analizando...';
+    resultSection.classList.remove('active');
+
+    const formData = new FormData();
+    formData.append('file', selectedFile);
+
+    try {
+        const response = await fetch(API_URL, {
+            method: 'POST',
+            body: formData
+        });
+
+        if (!response.ok) {
+            const errorData = await response.json();
+            throw new Error(errorData.error || 'Error en la API');
+        }
+
+        const data = await response.json();
+        displayResult(data);
+    } catch (error) {
+        alert('Error: ' + error.message);
+    } finally {
+        spinner.style.display = 'none';
+        btnText.textContent = '🔍 Analizar imagen';
+        predictBtn.disabled = false;
+    }
+}
+
+function displayResult(data) {
+    const classMapping = {
+        airplane: { icon: '✈️', label: 'Avión (Aéreo)', color: 'linear-gradient(90deg, #4299e1, #3182ce)' },
+        car: { icon: '🚗', label: 'Coche (Terrestre)', color: 'linear-gradient(90deg, #48bb78, #38a169)' },
+        ship: { icon: '🚢', label: 'Barco (Marítimo)', color: 'linear-gradient(90deg, #ed8936, #dd6b20)' }
+    };
+
+    // Clase con mayor probabilidad
+    const predictedClass = Object.keys(data.probabilidades).reduce((a, b) =>
+        data.probabilidades[a] > data.probabilidades[b] ? a : b
+    );
+
+    const confianza = data.probabilidades[predictedClass];
+    const classInfo = classMapping[predictedClass];
+
+    resultIcon.textContent = classInfo.icon;
+    resultPrediction.textContent = classInfo.label;
+    confidenceBar.style.background = classInfo.color;
+
+    const percent = Math.round(confianza * 100);
+    confidenceBar.style.width = percent + '%';
+    confidenceValue.textContent = percent + '%';
+
+    // Construir lista de probabilidades
+    probabilitiesList.innerHTML = '';
+    const labels = {
+        airplane: '✈️ Avión',
+        car: '🚗 Coche',
+        ship: '🚢 Barco'
+    };
+
+    for (const [key, prob] of Object.entries(data.probabilidades)) {
+        const probPercent = Math.round(prob * 100);
+        const item = document.createElement('div');
+        item.className = 'prob-item';
+        item.innerHTML = `
+            <div class="prob-label">
+                <span>${labels[key]}</span>
+            </div>
+            <span class="prob-value">${probPercent}%</span>
+        `;
+        probabilitiesList.appendChild(item);
+    }
+
+    resultSection.classList.add('active');
+    uploadAnotherBtn.style.display = 'inline-block';
+}
+
+uploadAnotherBtn.addEventListener('click', () => {
+    fileInput.value = '';
+    selectedFile = null;
+    previewSection.classList.remove('active');
+    resultSection.classList.remove('active');
+    predictBtn.disabled = true;
+    uploadAnotherBtn.style.display = 'none';
+});

static/index.html

@@ -0,0 +1,52 @@
+<!DOCTYPE html>
+<html lang="es">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Clasificador de Vehículos 🚗✈️🚢</title>
+    <link rel="stylesheet" href="/static/style.css">
+</head>
+<body>
+    <div class="container">
+        <h1>🚗 ✈️ 🚢</h1>
+        <h1>Clasificador de Vehículos</h1>
+        <p class="subtitle">Sube una imagen y descubre si es un coche, un avión o un barco</p>
+
+        <!-- Zona de subida -->
+        <div class="upload-area" id="uploadArea">
+            <div class="upload-icon">📷</div>
+            <p>Arrastra y suelta una imagen aquí o <span>haz clic para seleccionar</span></p>
+            <input type="file" id="fileInput" accept="image/*">
+        </div>
+
+        <!-- Vista previa -->
+        <div class="preview-section" id="previewSection">
+            <img id="previewImage" class="preview-image" src="" alt="Vista previa">
+        </div>
+
+        <!-- Botón predecir -->
+        <button class="btn-predict" id="predictBtn" disabled>
+            <span class="spinner" id="spinner"></span>
+            <span id="btnText">🔍 Analizar imagen</span>
+        </button>
+
+        <!-- Resultado -->
+        <div class="result-section" id="resultSection">
+            <div class="result-header">
+                <span class="result-icon" id="resultIcon"></span>
+                <span class="result-prediction" id="resultPrediction"></span>
+            </div>
+            <div class="confidence-bar-container">
+                <div class="confidence-bar" id="confidenceBar"></div>
+            </div>
+            <p class="confidence-text">
+                Confianza: <strong id="confidenceValue">0%</strong>
+            </p>
+            <div class="probabilities" id="probabilitiesList"></div>
+            <button class="upload-another" id="uploadAnotherBtn">🔄 Subir otra imagen</button>
+        </div>
+    </div>
+
+    <script src="/static/app.js"></script>
+</body>
+</html>

static/style.css

@@ -0,0 +1,251 @@
+/* Reset y base */
+* {
+    box-sizing: border-box;
+    margin: 0;
+    padding: 0;
+}
+
+body {
+    font-family: 'Segoe UI', system-ui, sans-serif;
+    min-height: 100vh;
+    background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    padding: 20px;
+}
+
+.container {
+    background: white;
+    border-radius: 24px;
+    box-shadow: 0 20px 60px rgba(0,0,0,0.2);
+    padding: 40px;
+    max-width: 600px;
+    width: 100%;
+    text-align: center;
+    transition: all 0.3s ease;
+}
+
+h1 {
+    font-size: 2rem;
+    margin-bottom: 10px;
+    color: #2d3748;
+}
+
+.subtitle {
+    color: #718096;
+    margin-bottom: 30px;
+}
+
+/* Zona de carga */
+.upload-area {
+    border: 3px dashed #cbd5e0;
+    border-radius: 16px;
+    padding: 40px 20px;
+    margin-bottom: 20px;
+    cursor: pointer;
+    transition: all 0.3s;
+    background: #f7fafc;
+}
+
+.upload-area:hover,
+.upload-area.dragover {
+    border-color: #667eea;
+    background: #edf2ff;
+}
+
+.upload-icon {
+    font-size: 48px;
+    margin-bottom: 15px;
+}
+
+.upload-area p {
+    color: #4a5568;
+    font-weight: 500;
+}
+
+.upload-area span {
+    color: #667eea;
+    text-decoration: underline;
+}
+
+input[type="file"] {
+    display: none;
+}
+
+/* Vista previa */
+.preview-section {
+    display: none;
+    margin-bottom: 20px;
+}
+
+.preview-section.active {
+    display: block;
+}
+
+.preview-image {
+    width: 100%;
+    height: 300px;
+    object-fit: contain;
+    border-radius: 16px;
+    background: #edf2f7;
+    border: 2px solid #e2e8f0;
+}
+
+/* Botón predecir */
+.btn-predict {
+    background: #667eea;
+    color: white;
+    border: none;
+    padding: 14px 32px;
+    border-radius: 12px;
+    font-size: 1.1rem;
+    font-weight: 600;
+    cursor: pointer;
+    transition: all 0.2s;
+    width: 100%;
+    margin-top: 10px;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    gap: 10px;
+}
+
+.btn-predict:hover {
+    background: #5a67d8;
+    transform: translateY(-1px);
+    box-shadow: 0 8px 20px rgba(102,126,234,0.3);
+}
+
+.btn-predict:disabled {
+    background: #a0aec0;
+    cursor: not-allowed;
+    transform: none;
+    box-shadow: none;
+}
+
+/* Spinner */
+.spinner {
+    display: none;
+    border: 3px solid rgba(255,255,255,0.3);
+    border-top: 3px solid white;
+    border-radius: 50%;
+    width: 20px;
+    height: 20px;
+    animation: spin 1s linear infinite;
+}
+
+@keyframes spin {
+    to { transform: rotate(360deg); }
+}
+
+/* Resultados */
+.result-section {
+    display: none;
+    background: #f7fafc;
+    border-radius: 16px;
+    padding: 24px;
+    margin-top: 20px;
+    text-align: left;
+}
+
+.result-section.active {
+    display: block;
+}
+
+.result-header {
+    display: flex;
+    align-items: center;
+    gap: 12px;
+    margin-bottom: 16px;
+}
+
+.result-icon {
+    font-size: 36px;
+}
+
+.result-prediction {
+    font-size: 1.5rem;
+    font-weight: 700;
+    color: #2d3748;
+}
+
+.confidence-bar-container {
+    background: #e2e8f0;
+    border-radius: 12px;
+    height: 12px;
+    margin-bottom: 12px;
+    overflow: hidden;
+}
+
+.confidence-bar {
+    height: 100%;
+    border-radius: 12px;
+    width: 0%;
+    background: linear-gradient(90deg, #48bb78, #38a169);
+    transition: width 0.8s ease;
+}
+
+.confidence-text {
+    color: #4a5568;
+    margin-bottom: 12px;
+}
+
+/* Lista de probabilidades */
+.probabilities {
+    display: flex;
+    flex-direction: column;
+    gap: 8px;
+}
+
+.prob-item {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    padding: 8px 12px;
+    background: white;
+    border-radius: 8px;
+    box-shadow: 0 1px 3px rgba(0,0,0,0.05);
+}
+
+.prob-label {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+}
+
+.prob-value {
+    font-weight: 600;
+}
+
+/* Botón "Subir otra imagen" */
+.upload-another {
+    display: none;
+    background: transparent;
+    border: 2px solid #667eea;
+    color: #667eea;
+    padding: 8px 20px;
+    border-radius: 8px;
+    font-weight: 600;
+    cursor: pointer;
+    margin-top: 16px;
+    transition: 0.2s;
+}
+
+.upload-another:hover {
+    background: #667eea;
+    color: white;
+}
+
+/* Responsive */
+@media (max-width: 500px) {
+    .container {
+        padding: 24px;
+    }
+    h1 {
+        font-size: 1.5rem;
+    }
+    .upload-area {
+        padding: 24px 16px;
+    }
+}