397 lines
13 KiB
Plaintext
397 lines
13 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Einfacher Bildklassifikator\n",
|
||
"\n",
|
||
"Dieses Notebook zeigt, wie man Bilder mit einem vortrainierten neuronalen Netzwerk klassifiziert.\n",
|
||
"\n",
|
||
"**Was Sie lernen werden:**\n",
|
||
"- Wie man ein vortrainiertes Modell lädt und verwendet\n",
|
||
"- Bildvorverarbeitung\n",
|
||
"- Vorhersagen für Bilder treffen\n",
|
||
"- Verständnis von Vertrauenswerten\n",
|
||
"\n",
|
||
"**Anwendungsfall:** Objekte in Bildern identifizieren (wie \"Katze\", \"Hund\", \"Auto\" usw.)\n",
|
||
"\n",
|
||
"---\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Schritt 1: Erforderliche Bibliotheken importieren\n",
|
||
"\n",
|
||
"Lassen Sie uns die benötigten Tools importieren. Keine Sorge, wenn Sie noch nicht alles davon verstehen!\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Core libraries\n",
|
||
"import numpy as np\n",
|
||
"from PIL import Image\n",
|
||
"import requests\n",
|
||
"from io import BytesIO\n",
|
||
"\n",
|
||
"# TensorFlow for deep learning\n",
|
||
"try:\n",
|
||
" import tensorflow as tf\n",
|
||
" from tensorflow.keras.applications import MobileNetV2\n",
|
||
" from tensorflow.keras.applications.mobilenet_v2 import preprocess_input, decode_predictions\n",
|
||
" print(\"✅ TensorFlow loaded successfully!\")\n",
|
||
" print(f\" Version: {tf.__version__}\")\n",
|
||
"except ImportError:\n",
|
||
" print(\"❌ Please install TensorFlow: pip install tensorflow\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Schritt 2: Vortrainiertes Modell laden\n",
|
||
"\n",
|
||
"Wir verwenden **MobileNetV2**, ein neuronales Netzwerk, das bereits mit Millionen von Bildern trainiert wurde.\n",
|
||
"\n",
|
||
"Das nennt man **Transfer Learning** – die Nutzung eines Modells, das von jemand anderem trainiert wurde!\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"print(\"📦 Loading pre-trained MobileNetV2 model...\")\n",
|
||
"print(\" This may take a minute on first run (downloading weights)...\")\n",
|
||
"\n",
|
||
"# Load the model\n",
|
||
"# include_top=True means we use the classification layer\n",
|
||
"# weights='imagenet' means it was trained on ImageNet dataset\n",
|
||
"model = MobileNetV2(weights='imagenet', include_top=True)\n",
|
||
"\n",
|
||
"print(\"✅ Model loaded!\")\n",
|
||
"print(f\" The model can recognize 1000 different object categories\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Schritt 3: Hilfsfunktionen\n",
|
||
"\n",
|
||
"Lassen Sie uns Funktionen erstellen, um Bilder für unser Modell zu laden und vorzubereiten.\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"def load_image_from_url(url):\n",
|
||
" \"\"\"\n",
|
||
" Load an image from a URL.\n",
|
||
" \n",
|
||
" Args:\n",
|
||
" url: Web address of the image\n",
|
||
" \n",
|
||
" Returns:\n",
|
||
" PIL Image object\n",
|
||
" \"\"\"\n",
|
||
" response = requests.get(url)\n",
|
||
" img = Image.open(BytesIO(response.content))\n",
|
||
" return img\n",
|
||
"\n",
|
||
"\n",
|
||
"def prepare_image(img):\n",
|
||
" \"\"\"\n",
|
||
" Prepare an image for the model.\n",
|
||
" \n",
|
||
" Steps:\n",
|
||
" 1. Resize to 224x224 (model's expected size)\n",
|
||
" 2. Convert to array\n",
|
||
" 3. Add batch dimension\n",
|
||
" 4. Preprocess for MobileNetV2\n",
|
||
" \n",
|
||
" Args:\n",
|
||
" img: PIL Image\n",
|
||
" \n",
|
||
" Returns:\n",
|
||
" Preprocessed image array\n",
|
||
" \"\"\"\n",
|
||
" # Resize to 224x224 pixels\n",
|
||
" img = img.resize((224, 224))\n",
|
||
" \n",
|
||
" # Convert to numpy array\n",
|
||
" img_array = np.array(img)\n",
|
||
" \n",
|
||
" # Add batch dimension (model expects multiple images)\n",
|
||
" img_array = np.expand_dims(img_array, axis=0)\n",
|
||
" \n",
|
||
" # Preprocess for MobileNetV2\n",
|
||
" img_array = preprocess_input(img_array)\n",
|
||
" \n",
|
||
" return img_array\n",
|
||
"\n",
|
||
"\n",
|
||
"def classify_image(img):\n",
|
||
" \"\"\"\n",
|
||
" Classify an image and return top predictions.\n",
|
||
" \n",
|
||
" Args:\n",
|
||
" img: PIL Image\n",
|
||
" \n",
|
||
" Returns:\n",
|
||
" List of (class_name, confidence) tuples\n",
|
||
" \"\"\"\n",
|
||
" # Prepare the image\n",
|
||
" img_array = prepare_image(img)\n",
|
||
" \n",
|
||
" # Make prediction\n",
|
||
" predictions = model.predict(img_array, verbose=0)\n",
|
||
" \n",
|
||
" # Decode predictions to human-readable labels\n",
|
||
" # top=5 means we get the top 5 most likely classes\n",
|
||
" decoded = decode_predictions(predictions, top=5)[0]\n",
|
||
" \n",
|
||
" # Convert to simpler format\n",
|
||
" results = [(label, float(confidence)) for (_, label, confidence) in decoded]\n",
|
||
" \n",
|
||
" return results\n",
|
||
"\n",
|
||
"\n",
|
||
"print(\"✅ Helper functions ready!\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Schritt 4: Testen mit Beispielbildern\n",
|
||
"\n",
|
||
"Lass uns einige Bilder aus dem Internet klassifizieren!\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Sample images to classify\n",
|
||
"# These are from Unsplash (free stock photos)\n",
|
||
"test_images = [\n",
|
||
" {\n",
|
||
" \"url\": \"https://images.unsplash.com/photo-1514888286974-6c03e2ca1dba?w=400\",\n",
|
||
" \"description\": \"A cat\"\n",
|
||
" },\n",
|
||
" {\n",
|
||
" \"url\": \"https://images.unsplash.com/photo-1552053831-71594a27632d?w=400\",\n",
|
||
" \"description\": \"A dog\"\n",
|
||
" },\n",
|
||
" {\n",
|
||
" \"url\": \"https://images.unsplash.com/photo-1511919884226-fd3cad34687c?w=400\",\n",
|
||
" \"description\": \"A car\"\n",
|
||
" },\n",
|
||
"]\n",
|
||
"\n",
|
||
"print(f\"🧪 Testing on {len(test_images)} images...\")\n",
|
||
"print(\"=\" * 70)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Klassifizieren Sie jedes Bild\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"for i, img_data in enumerate(test_images, 1):\n",
|
||
" print(f\"\\n📸 Image {i}: {img_data['description']}\")\n",
|
||
" print(\"-\" * 70)\n",
|
||
" \n",
|
||
" try:\n",
|
||
" # Load image\n",
|
||
" img = load_image_from_url(img_data['url'])\n",
|
||
" \n",
|
||
" # Display image\n",
|
||
" display(img.resize((200, 200))) # Show smaller version\n",
|
||
" \n",
|
||
" # Classify\n",
|
||
" results = classify_image(img)\n",
|
||
" \n",
|
||
" # Show predictions\n",
|
||
" print(\"\\n🎯 Top 5 Predictions:\")\n",
|
||
" for rank, (label, confidence) in enumerate(results, 1):\n",
|
||
" # Create a visual bar\n",
|
||
" bar_length = int(confidence * 50)\n",
|
||
" bar = \"█\" * bar_length\n",
|
||
" \n",
|
||
" print(f\" {rank}. {label:20s} {confidence*100:5.2f}% {bar}\")\n",
|
||
" \n",
|
||
" except Exception as e:\n",
|
||
" print(f\"❌ Error: {e}\")\n",
|
||
"\n",
|
||
"print(\"\\n\" + \"=\" * 70)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Schritt 5: Probieren Sie Ihre eigenen Bilder aus!\n",
|
||
"\n",
|
||
"Ersetzen Sie die untenstehende URL durch eine beliebige Bild-URL, die Sie klassifizieren möchten.\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Try your own image!\n",
|
||
"# Replace this URL with any image URL\n",
|
||
"custom_image_url = \"https://images.unsplash.com/photo-1472491235688-bdc81a63246e?w=400\" # A flower\n",
|
||
"\n",
|
||
"print(\"🖼️ Classifying your custom image...\")\n",
|
||
"print(\"=\" * 70)\n",
|
||
"\n",
|
||
"try:\n",
|
||
" # Load and show image\n",
|
||
" img = load_image_from_url(custom_image_url)\n",
|
||
" display(img.resize((300, 300)))\n",
|
||
" \n",
|
||
" # Classify\n",
|
||
" results = classify_image(img)\n",
|
||
" \n",
|
||
" # Show results\n",
|
||
" print(\"\\n🎯 Top 5 Predictions:\")\n",
|
||
" print(\"-\" * 70)\n",
|
||
" for rank, (label, confidence) in enumerate(results, 1):\n",
|
||
" bar_length = int(confidence * 50)\n",
|
||
" bar = \"█\" * bar_length\n",
|
||
" print(f\" {rank}. {label:20s} {confidence*100:5.2f}% {bar}\")\n",
|
||
" \n",
|
||
" # Highlight top prediction\n",
|
||
" top_label, top_confidence = results[0]\n",
|
||
" print(\"\\n\" + \"=\" * 70)\n",
|
||
" print(f\"\\n🏆 Best guess: {top_label} ({top_confidence*100:.2f}% confident)\")\n",
|
||
" \n",
|
||
"except Exception as e:\n",
|
||
" print(f\"❌ Error: {e}\")\n",
|
||
" print(\" Make sure the URL points to a valid image!\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 💡 Was ist gerade passiert?\n",
|
||
"\n",
|
||
"1. **Wir haben ein vortrainiertes Modell geladen** - MobileNetV2 wurde mit Millionen von Bildern trainiert. \n",
|
||
"2. **Wir haben Bilder vorverarbeitet** - Sie wurden für das Modell passend skaliert und formatiert. \n",
|
||
"3. **Das Modell hat Vorhersagen getroffen** - Es hat Wahrscheinlichkeiten für 1000 Objektklassen ausgegeben. \n",
|
||
"4. **Wir haben die Ergebnisse dekodiert** - Zahlen wurden in menschenlesbare Labels umgewandelt. \n",
|
||
"\n",
|
||
"### Verständnis der Vertrauenswerte\n",
|
||
"\n",
|
||
"- **90-100%**: Sehr sicher (fast garantiert korrekt) \n",
|
||
"- **70-90%**: Sicher (wahrscheinlich korrekt) \n",
|
||
"- **50-70%**: Etwas sicher (könnte korrekt sein) \n",
|
||
"- **Unter 50%**: Nicht sehr sicher (unsicher) \n",
|
||
"\n",
|
||
"### Warum könnten Vorhersagen falsch sein?\n",
|
||
"\n",
|
||
"- **Ungewöhnlicher Winkel oder Beleuchtung** - Das Modell wurde mit typischen Fotos trainiert. \n",
|
||
"- **Mehrere Objekte** - Das Modell erwartet ein Hauptobjekt. \n",
|
||
"- **Seltene Objekte** - Das Modell kennt nur 1000 Kategorien. \n",
|
||
"- **Schlechte Bildqualität** - Verschwommene oder verpixelte Bilder sind schwieriger zu erkennen. \n",
|
||
"\n",
|
||
"---\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 🚀 Nächste Schritte\n",
|
||
"\n",
|
||
"1. **Probieren Sie verschiedene Bilder aus:**\n",
|
||
" - Finden Sie Bilder auf [Unsplash](https://unsplash.com)\n",
|
||
" - Rechtsklick → „Bildadresse kopieren“, um die URL zu erhalten\n",
|
||
"\n",
|
||
"2. **Experimentieren:**\n",
|
||
" - Was passiert mit abstrakter Kunst?\n",
|
||
" - Kann es Objekte aus verschiedenen Blickwinkeln erkennen?\n",
|
||
" - Wie geht es mit mehreren Objekten um?\n",
|
||
"\n",
|
||
"3. **Mehr erfahren:**\n",
|
||
" - Erkunden Sie [Computer Vision Lektionen](../lessons/4-ComputerVision/README.md)\n",
|
||
" - Lernen Sie, Ihren eigenen Bildklassifikator zu trainieren\n",
|
||
" - Verstehen Sie, wie CNNs (Convolutional Neural Networks) funktionieren\n",
|
||
"\n",
|
||
"---\n",
|
||
"\n",
|
||
"## 🎉 Herzlichen Glückwunsch!\n",
|
||
"\n",
|
||
"Sie haben gerade einen Bildklassifikator mit einem hochmodernen neuronalen Netzwerk erstellt!\n",
|
||
"\n",
|
||
"Diese Technik wird verwendet für:\n",
|
||
"- Google Fotos (Organisieren Ihrer Bilder)\n",
|
||
"- Selbstfahrende Autos (Objekterkennung)\n",
|
||
"- Medizinische Diagnosen (Analyse von Röntgenbildern)\n",
|
||
"- Qualitätskontrolle (Erkennung von Defekten)\n",
|
||
"\n",
|
||
"Bleiben Sie neugierig und lernen Sie weiter! 🚀\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"\n---\n\n**Haftungsausschluss**: \nDieses Dokument wurde mit dem KI-Übersetzungsdienst [Co-op Translator](https://github.com/Azure/co-op-translator) übersetzt. Obwohl wir uns um Genauigkeit bemühen, weisen wir darauf hin, dass automatisierte Übersetzungen Fehler oder Ungenauigkeiten enthalten können. Das Originaldokument in seiner ursprünglichen Sprache sollte als maßgebliche Quelle betrachtet werden. Für kritische Informationen wird eine professionelle menschliche Übersetzung empfohlen. Wir übernehmen keine Haftung für Missverständnisse oder Fehlinterpretationen, die aus der Nutzung dieser Übersetzung entstehen.\n"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "Python 3",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.8.0"
|
||
},
|
||
"coopTranslator": {
|
||
"original_hash": "1d472141d9df46b751542b3c29f88677",
|
||
"translation_date": "2025-10-03T11:37:36+00:00",
|
||
"source_file": "examples/03-image-classifier.ipynb",
|
||
"language_code": "de"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 4
|
||
} |