Upload 310 files

.gitattributes

@@ -53,3 +53,23 @@ PIcture/pokemon/Rhyhorn/00000073.png filter=lfs diff=lfs merge=lfs -text
 PIcture/pokemon/Rhyhorn/00000094.png filter=lfs diff=lfs merge=lfs -text
 PIcture/pokemon/Rhyhorn/00000108.png filter=lfs diff=lfs merge=lfs -text
 PIcture/pokemon/Rhyhorn/00000111.png filter=lfs diff=lfs merge=lfs -text
+best_model.keras filter=lfs diff=lfs merge=lfs -text
+pokemon_classifier_model.keras filter=lfs diff=lfs merge=lfs -text
+pokemon/Bulbasaur/00000013.png filter=lfs diff=lfs merge=lfs -text
+pokemon/Bulbasaur/00000039.png filter=lfs diff=lfs merge=lfs -text
+pokemon/Bulbasaur/00000040.jpg filter=lfs diff=lfs merge=lfs -text
+pokemon/Bulbasaur/00000058.png filter=lfs diff=lfs merge=lfs -text
+pokemon/Bulbasaur/00000059.jpg filter=lfs diff=lfs merge=lfs -text
+pokemon/Bulbasaur/00000082.png filter=lfs diff=lfs merge=lfs -text
+pokemon/Bulbasaur/00000140.png filter=lfs diff=lfs merge=lfs -text
+pokemon/Bulbasaur/00000145.png filter=lfs diff=lfs merge=lfs -text
+pokemon/Jigglypuff/00000014.jpg filter=lfs diff=lfs merge=lfs -text
+pokemon/Jigglypuff/00000019.PNG filter=lfs diff=lfs merge=lfs -text
+pokemon/Jigglypuff/00000081.jpg filter=lfs diff=lfs merge=lfs -text
+pokemon/Jigglypuff/00000099.jpg filter=lfs diff=lfs merge=lfs -text
+pokemon/Rhyhorn/00000012.png filter=lfs diff=lfs merge=lfs -text
+pokemon/Rhyhorn/00000027.png filter=lfs diff=lfs merge=lfs -text
+pokemon/Rhyhorn/00000073.png filter=lfs diff=lfs merge=lfs -text
+pokemon/Rhyhorn/00000094.png filter=lfs diff=lfs merge=lfs -text
+pokemon/Rhyhorn/00000108.png filter=lfs diff=lfs merge=lfs -text
+pokemon/Rhyhorn/00000111.png filter=lfs diff=lfs merge=lfs -text

.history/app_20240520154754.py

@@ -0,0 +1,42 @@
+import gradio as gr
+import tensorflow as tf
+from PIL import Image
+import numpy as np
+
+model_path = "pokemon_classifier_model.keras"
+model = tf.keras.models.load_model(model_path)
+
+
+labels = ['Pikachu', 'Sandshrew', 'Squirtle']
+    
+def predict_image(image):
+    # Preprocess image
+    image = Image.fromarray(image.astype('uint8'))  # Convert numpy array to PIL image
+    image = image.resize((224, 224))  # Resize the image to 224x224 pixels
+    image = np.array(image) / 255.0   # Convert to float and normalize
+
+    # Ensure the image has 3 color channels
+    if image.ndim == 2:  # If grayscale, convert to RGB
+        image = np.stack((image,)*3, axis=-1)
+
+    prediction = model.predict(image[None, ...])  # Adding batch dimension
+    confidences = {labels[i]: float(prediction[0][i]) for i in range(len(labels))}
+    return confidences
+
+
+input_image = gr.Image()
+output_text = gr.Textbox(label="Predicted Value")
+
+
+iface = gr.Interface(
+    fn=predict_image,
+    inputs=input_image, 
+    outputs=gr.Label(),
+    title="Pokémon Classifier",
+    examples=["images/pikachu.png", "images/squirtle.png", "images/sandshrew.png"],
+    description="Upload an image of Pikachu, Sandshrew, or Squirtle and the classifier will predict which one it is."
+)
+
+
+
+iface.launch()

.history/app_20240520174348.py

@@ -0,0 +1,42 @@
+import gradio as gr
+import tensorflow as tf
+from PIL import Image
+import numpy as np
+
+model_path = "pokemon_classifier_model.keras"
+model = tf.keras.models.load_model(model_path)
+
+
+labels = ['Bulbasaur', 'Jigglypuff', 'Rhyhorn']
+    
+def predict_image(image):
+    # Preprocess image
+    image = Image.fromarray(image.astype('uint8'))  # Convert numpy array to PIL image
+    image = image.resize((224, 224))  # Resize the image to 224x224 pixels
+    image = np.array(image) / 255.0   # Convert to float and normalize
+
+    # Ensure the image has 3 color channels
+    if image.ndim == 2:  # If grayscale, convert to RGB
+        image = np.stack((image,)*3, axis=-1)
+
+    prediction = model.predict(image[None, ...])  # Adding batch dimension
+    confidences = {labels[i]: float(prediction[0][i]) for i in range(len(labels))}
+    return confidences
+
+
+input_image = gr.Image()
+output_text = gr.Textbox(label="Predicted Value")
+
+
+iface = gr.Interface(
+    fn=predict_image,
+    inputs=input_image, 
+    outputs=gr.Label(),
+    title="Pokémon Classifier",
+    examples=["images/pikachu.png", "images/squirtle.png", "images/sandshrew.png"],
+    description="Upload an image of Pikachu, Sandshrew, or Squirtle and the classifier will predict which one it is."
+)
+
+
+
+iface.launch()

.history/app_20240520175521.py

@@ -0,0 +1,42 @@
+import gradio as gr
+import tensorflow as tf
+from PIL import Image
+import numpy as np
+
+model_path = "pokemon_classifier_model.keras"
+model = tf.keras.models.load_model(model_path)
+
+
+labels = ['Bulbasaur', 'Jigglypuff', 'Rhyhorn']
+    
+def predict_image(image):
+    # Preprocess image
+    image = Image.fromarray(image.astype('uint8'))  # Convert numpy array to PIL image
+    image = image.resize((224, 224))  # Resize the image to 224x224 pixels
+    image = np.array(image) / 255.0   # Convert to float and normalize
+
+    # Ensure the image has 3 color channels
+    if image.ndim == 2:  # If grayscale, convert to RGB
+        image = np.stack((image,)*3, axis=-1)
+
+    prediction = model.predict(image[None, ...])  # Adding batch dimension
+    confidences = {labels[i]: float(prediction[0][i]) for i in range(len(labels))}
+    return confidences
+
+
+input_image = gr.Image()
+output_text = gr.Textbox(label="Predicted Value")
+
+
+iface = gr.Interface(
+    fn=predict_image,
+    inputs=input_image, 
+    outputs=gr.Label(),
+    title="Pokémon Classifier",
+    examples=["images/pikachu.png", "images/squirtle.png", "images/sandshrew.png"],
+    description="Upload an image of Pikachu, Sandshrew, or Squirtle and the classifier will predict which one it is."
+)
+
+
+
+iface.launch()

.history/app_20240520175656.py

@@ -0,0 +1,42 @@
+import gradio as gr
+import tensorflow as tf
+from PIL import Image
+import numpy as np
+
+model_path = "pokemon_classifier_model.keras"
+model = tf.keras.models.load_model(model_path)
+
+
+labels = ['Bulbasaur', 'Jigglypuff', 'Rhyhorn']
+    
+def predict_image(image):
+    # Preprocess image
+    image = Image.fromarray(image.astype('uint8'))  # Convert numpy array to PIL image
+    image = image.resize((224, 224))  # Resize the image to 224x224 pixels
+    image = np.array(image) / 255.0   # Convert to float and normalize
+
+    # Ensure the image has 3 color channels
+    if image.ndim == 2:  # If grayscale, convert to RGB
+        image = np.stack((image,)*3, axis=-1)
+
+    prediction = model.predict(image[None, ...])  # Adding batch dimension
+    confidences = {labels[i]: float(prediction[0][i]) for i in range(len(labels))}
+    return confidences
+
+
+input_image = gr.Image()
+output_text = gr.Textbox(label="Predicted Value")
+
+
+iface = gr.Interface(
+    fn=predict_image,
+    inputs=input_image, 
+    outputs=gr.Label(),
+    title="Pokémon Classifier",
+    examples=["images/pikachu.png", "images/squirtle.png", "images/sandshrew.png"],
+    description="Upload an image of Pikachu, Sandshrew, or Squirtle and the classifier will predict which one it is."
+)
+
+
+
+iface.launch()

.history/app_20240521123743.py

@@ -0,0 +1,42 @@
+import gradio as gr
+import tensorflow as tf
+from PIL import Image
+import numpy as np
+
+model_path = "pokemon_classifier_model.keras"
+model = tf.keras.models.load_model(model_path)
+
+
+labels = ['Bulbasaur', 'Jigglypuff', 'Rhyhorn']
+    
+def predict_image(image):
+    # Preprocess image
+    image = Image.fromarray(image.astype('uint8'))  # Convert numpy array to PIL image
+    image = image.resize((224, 224))  # Resize the image to 224x224 pixels
+    image = np.array(image) / 255.0   # Convert to float and normalize
+
+    # Ensure the image has 3 color channels
+    if image.ndim == 2:  # If grayscale, convert to RGB
+        image = np.stack((image,)*3, axis=-1)
+
+    prediction = model.predict(image[None, ...])  # Adding batch dimension
+    confidences = {labels[i]: float(prediction[0][i]) for i in range(len(labels))}
+    return confidences
+
+
+input_image = gr.Image()
+output_text = gr.Textbox(label="Predicted Value")
+
+
+iface = gr.Interface(
+    fn=predict_image,
+    inputs=input_image, 
+    outputs=gr.Label(),
+    title="Pokémon Classifier",
+    examples=["pokemon/Bulbasur.png", "pokemon/Jigglypuff.png", "pokemon/Rhyhorn.png"],
+    description="Upload an image of Bulbasur, Jigglypuff, or Rhyhorn and the classifier will predict which one it is."
+)
+
+
+
+iface.launch()

.ipynb_checkpoints/main-checkpoint.ipynb

@@ -0,0 +1,203 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Found 391 images belonging to 3 classes.\n",
+      "Found 96 images belonging to 3 classes.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "import os\n",
+    "\n",
+    "base_dir = 'dataset'\n",
+    "\n",
+    "image_size = (224, 224)\n",
+    "batch_size = 32\n",
+    "\n",
+    "train_datagen = ImageDataGenerator(\n",
+    "    rescale=1./255,\n",
+    "    rotation_range=40,\n",
+    "    width_shift_range=0.2,\n",
+    "    height_shift_range=0.2,\n",
+    "    shear_range=0.2,\n",
+    "    zoom_range=0.2,\n",
+    "    horizontal_flip=True,\n",
+    "    fill_mode='nearest',\n",
+    "    validation_split=0.2  \n",
+    ")\n",
+    "\n",
+    "train_generator = train_datagen.flow_from_directory(\n",
+    "    base_dir,\n",
+    "    target_size=image_size,\n",
+    "    batch_size=batch_size,\n",
+    "    class_mode='categorical',\n",
+    "    subset='training' \n",
+    ")\n",
+    "\n",
+    "validation_generator = train_datagen.flow_from_directory(\n",
+    "    base_dir,\n",
+    "    target_size=image_size,\n",
+    "    batch_size=batch_size,\n",
+    "    class_mode='categorical',\n",
+    "    subset='validation' \n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tensorflow.keras.models import Sequential\n",
+    "from tensorflow.keras.layers import Dense, GlobalAveragePooling2D\n",
+    "from tensorflow.keras.applications import ResNet50\n",
+    "from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau\n",
+    "import tensorflow as tf\n",
+    "\n",
+    "base_model = ResNet50(weights='imagenet', include_top=False, input_shape=(224, 224, 3))\n",
+    "\n",
+    "base_model.trainable = False\n",
+    "\n",
+    "model = Sequential([\n",
+    "    base_model,\n",
+    "    GlobalAveragePooling2D(),\n",
+    "    Dense(512, activation='relu'),\n",
+    "    Dense(3, activation='softmax')  \n",
+    "])\n",
+    "\n",
+    "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
+    "\n",
+    "early_stopping = EarlyStopping(monitor='val_loss', patience=5, restore_best_weights=True)\n",
+    "model_checkpoint = ModelCheckpoint('best_model.keras', save_best_only=True)\n",
+    "reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=2, min_lr=1e-7)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 2s/step - accuracy: 0.3927 - loss: 1.3381 - val_accuracy: 0.4688 - val_loss: 1.0825 - learning_rate: 0.0010\n",
+      "Epoch 2/10\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m22s\u001b[0m 1s/step - accuracy: 0.4262 - loss: 1.1153 - val_accuracy: 0.4792 - val_loss: 1.0168 - learning_rate: 0.0010\n",
+      "Epoch 3/10\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 1s/step - accuracy: 0.5207 - loss: 1.0038 - val_accuracy: 0.6146 - val_loss: 0.9397 - learning_rate: 0.0010\n",
+      "Epoch 4/10\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 1s/step - accuracy: 0.5667 - loss: 0.9722 - val_accuracy: 0.5521 - val_loss: 0.8991 - learning_rate: 0.0010\n",
+      "Epoch 5/10\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 2s/step - accuracy: 0.4955 - loss: 1.0044 - val_accuracy: 0.6562 - val_loss: 0.9241 - learning_rate: 0.0010\n",
+      "Epoch 6/10\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m30s\u001b[0m 2s/step - accuracy: 0.5938 - loss: 0.9319 - val_accuracy: 0.5938 - val_loss: 0.8967 - learning_rate: 0.0010\n",
+      "Epoch 7/10\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 2s/step - accuracy: 0.6017 - loss: 0.9330 - val_accuracy: 0.6354 - val_loss: 0.8814 - learning_rate: 0.0010\n",
+      "Epoch 8/10\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 2s/step - accuracy: 0.5250 - loss: 0.9443 - val_accuracy: 0.6458 - val_loss: 0.8834 - learning_rate: 0.0010\n",
+      "Epoch 9/10\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 2s/step - accuracy: 0.5166 - loss: 0.9913 - val_accuracy: 0.6562 - val_loss: 0.8957 - learning_rate: 0.0010\n",
+      "Epoch 10/10\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 2s/step - accuracy: 0.6796 - loss: 0.8320 - val_accuracy: 0.6875 - val_loss: 0.7982 - learning_rate: 2.0000e-04\n"
+     ]
+    }
+   ],
+   "source": [
+    "history = model.fit(\n",
+    "    train_generator,\n",
+    "    epochs=10,\n",
+    "    validation_data=validation_generator,\n",
+    "    callbacks=[early_stopping, model_checkpoint, reduce_lr]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 10/20\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m51s\u001b[0m 3s/step - accuracy: 0.4460 - loss: 1.3447 - val_accuracy: 0.5625 - val_loss: 0.8845 - learning_rate: 1.0000e-05\n",
+      "Epoch 11/20\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m46s\u001b[0m 3s/step - accuracy: 0.5523 - loss: 1.0105 - val_accuracy: 0.5000 - val_loss: 1.0040 - learning_rate: 1.0000e-05\n",
+      "Epoch 12/20\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m49s\u001b[0m 3s/step - accuracy: 0.6260 - loss: 0.8541 - val_accuracy: 0.4688 - val_loss: 1.1044 - learning_rate: 1.0000e-05\n",
+      "Epoch 13/20\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m48s\u001b[0m 3s/step - accuracy: 0.6385 - loss: 0.7894 - val_accuracy: 0.4583 - val_loss: 1.3327 - learning_rate: 2.0000e-06\n",
+      "Epoch 14/20\n",
+      "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m50s\u001b[0m 3s/step - accuracy: 0.6777 - loss: 0.7459 - val_accuracy: 0.4792 - val_loss: 1.6466 - learning_rate: 2.0000e-06\n"
+     ]
+    }
+   ],
+   "source": [
+    "base_model.trainable = True\n",
+    "fine_tune_at = 100\n",
+    "\n",
+    "for layer in base_model.layers[:fine_tune_at]:\n",
+    "    layer.trainable = False\n",
+    "\n",
+    "model.compile(optimizer=tf.keras.optimizers.Adam(1e-5), \n",
+    "              metrics=['accuracy'])\n",
+    "\n",
+    "fine_tune_epochs = 10\n",
+    "total_epochs = history.epoch[-1] + fine_tune_epochs + 1\n",
+    "\n",
+    "history_fine = model.fit(\n",
+    "    train_generator,\n",
+    "    epochs=total_epochs,\n",
+    "    initial_epoch=history.epoch[-1],\n",
+    "    validation_data=validation_generator,\n",
+    "    callbacks=[early_stopping, model_checkpoint, reduce_lr]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.save('pokemon_classifier_model.keras')\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.9.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

app.py

@@ -0,0 +1,42 @@
+import gradio as gr
+import tensorflow as tf
+from PIL import Image
+import numpy as np
+
+model_path = "pokemon_classifier_model.keras"
+model = tf.keras.models.load_model(model_path)
+
+
+labels = ['Bulbasaur', 'Jigglypuff', 'Rhyhorn']
+    
+def predict_image(image):
+    # Preprocess image
+    image = Image.fromarray(image.astype('uint8'))  # Convert numpy array to PIL image
+    image = image.resize((224, 224))  # Resize the image to 224x224 pixels
+    image = np.array(image) / 255.0   # Convert to float and normalize
+
+    # Ensure the image has 3 color channels
+    if image.ndim == 2:  # If grayscale, convert to RGB
+        image = np.stack((image,)*3, axis=-1)
+
+    prediction = model.predict(image[None, ...])  # Adding batch dimension
+    confidences = {labels[i]: float(prediction[0][i]) for i in range(len(labels))}
+    return confidences
+
+
+input_image = gr.Image()
+output_text = gr.Textbox(label="Predicted Value")
+
+
+iface = gr.Interface(
+    fn=predict_image,
+    inputs=input_image, 
+    outputs=gr.Label(),
+    title="Pokémon Classifier",
+    examples=["pokemon/Bulbasur.png", "pokemon/Jigglypuff.png", "pokemon/Rhyhorn.png"],
+    description="Upload an image of Bulbasur, Jigglypuff, or Rhyhorn and the classifier will predict which one it is."
+)
+
+
+
+iface.launch()

best_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d49cc8758bae0cadc0069d0bc1f76e31d37fbb7366db48916ee4276ac0e1ed
+size 107570656

main.ipynb

@@ -0,0 +1,246 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Import erfolgreich\n"
+     ]
+    }
+   ],
+   "source": [
+    "from tensorflow.keras.models import Sequential\n",
+    "from tensorflow.keras.layers import Dense, GlobalAveragePooling2D\n",
+    "from tensorflow.keras.applications import ResNet50\n",
+    "from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau\n",
+    "import tensorflow as tf\n",
+    "print(\"Import erfolgreich\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Found 361 images belonging to 3 classes.\n",
+      "Found 89 images belonging to 3 classes.\n",
+      "Aktueller Arbeitspfad: c:\\Users\\lukas\\Studium\\6. Semester\\KI Anwendungen\\PIcture\n",
+      "Verzeichnisinhalt: ['.history', '.ipynb_checkpoints', 'app.py', 'main.ipynb', 'pokemon']\n"
+     ]
+    }
+   ],
+   "source": [
+    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "import os\n",
+    "\n",
+    "base_dir = 'pokemon'\n",
+    "\n",
+    "image_size = (224, 224)\n",
+    "batch_size = 32\n",
+    "\n",
+    "train_datagen = ImageDataGenerator(\n",
+    "    rescale=1./255,\n",
+    "    rotation_range=40,\n",
+    "    width_shift_range=0.2,\n",
+    "    height_shift_range=0.2,\n",
+    "    shear_range=0.2,\n",
+    "    zoom_range=0.2,\n",
+    "    horizontal_flip=True,\n",
+    "    fill_mode='nearest',\n",
+    "    validation_split=0.2  \n",
+    ")\n",
+    "\n",
+    "train_generator = train_datagen.flow_from_directory(\n",
+    "    base_dir,\n",
+    "    target_size=image_size,\n",
+    "    batch_size=batch_size,\n",
+    "    class_mode='categorical',\n",
+    "    subset='training' \n",
+    ")\n",
+    "\n",
+    "validation_generator = train_datagen.flow_from_directory(\n",
+    "    base_dir,\n",
+    "    target_size=image_size,\n",
+    "    batch_size=batch_size,\n",
+    "    class_mode='categorical',\n",
+    "    subset='validation' \n",
+    ")\n",
+    "\n",
+    "# Aktuellen Arbeitspfad drucken\n",
+    "print(\"Aktueller Arbeitspfad:\", os.getcwd())\n",
+    "\n",
+    "# Inhalte im aktuellen Verzeichnis auflisten\n",
+    "print(\"Verzeichnisinhalt:\", os.listdir())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_model = ResNet50(weights='imagenet', include_top=False, input_shape=(224, 224, 3))\n",
+    "\n",
+    "base_model.trainable = False\n",
+    "\n",
+    "model = Sequential([\n",
+    "    base_model,\n",
+    "    GlobalAveragePooling2D(),\n",
+    "    Dense(512, activation='relu'),\n",
+    "    Dense(3, activation='softmax')  \n",
+    "])\n",
+    "\n",
+    "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
+    "\n",
+    "early_stopping = EarlyStopping(monitor='val_loss', patience=5, restore_best_weights=True)\n",
+    "model_checkpoint = ModelCheckpoint('best_model.keras', save_best_only=True)\n",
+    "reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=2, min_lr=1e-7)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\lukas\\anaconda3\\envs\\kia\\lib\\site-packages\\keras\\src\\trainers\\data_adapters\\py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.\n",
+      "  self._warn_if_super_not_called()\n",
+      "c:\\Users\\lukas\\anaconda3\\envs\\kia\\lib\\site-packages\\PIL\\Image.py:1000: UserWarning: Palette images with Transparency expressed in bytes should be converted to RGBA images\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m82s\u001b[0m 5s/step - accuracy: 0.3422 - loss: 1.4997 - val_accuracy: 0.3258 - val_loss: 1.1893 - learning_rate: 0.0010\n",
+      "Epoch 2/10\n",
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m60s\u001b[0m 4s/step - accuracy: 0.3986 - loss: 1.1751 - val_accuracy: 0.4045 - val_loss: 1.1911 - learning_rate: 0.0010\n",
+      "Epoch 3/10\n",
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━��━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m59s\u001b[0m 4s/step - accuracy: 0.4265 - loss: 1.1501 - val_accuracy: 0.5393 - val_loss: 1.0268 - learning_rate: 0.0010\n",
+      "Epoch 4/10\n",
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m51s\u001b[0m 4s/step - accuracy: 0.5038 - loss: 1.0047 - val_accuracy: 0.6180 - val_loss: 0.9316 - learning_rate: 0.0010\n",
+      "Epoch 5/10\n",
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m47s\u001b[0m 3s/step - accuracy: 0.4520 - loss: 1.0198 - val_accuracy: 0.4831 - val_loss: 0.9292 - learning_rate: 0.0010\n",
+      "Epoch 6/10\n",
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m45s\u001b[0m 3s/step - accuracy: 0.5053 - loss: 0.9459 - val_accuracy: 0.6292 - val_loss: 0.9976 - learning_rate: 0.0010\n",
+      "Epoch 7/10\n",
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m46s\u001b[0m 3s/step - accuracy: 0.5592 - loss: 0.9549 - val_accuracy: 0.5618 - val_loss: 0.8820 - learning_rate: 0.0010\n",
+      "Epoch 8/10\n",
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m53s\u001b[0m 4s/step - accuracy: 0.4919 - loss: 0.9838 - val_accuracy: 0.5281 - val_loss: 0.8794 - learning_rate: 0.0010\n",
+      "Epoch 9/10\n",
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m60s\u001b[0m 4s/step - accuracy: 0.5190 - loss: 0.9214 - val_accuracy: 0.6180 - val_loss: 0.8400 - learning_rate: 0.0010\n",
+      "Epoch 10/10\n",
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m51s\u001b[0m 4s/step - accuracy: 0.5295 - loss: 0.9299 - val_accuracy: 0.5730 - val_loss: 0.8847 - learning_rate: 0.0010\n"
+     ]
+    }
+   ],
+   "source": [
+    "history = model.fit(\n",
+    "    train_generator,\n",
+    "    epochs=10,\n",
+    "    validation_data=validation_generator,\n",
+    "    callbacks=[early_stopping, model_checkpoint, reduce_lr]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 10/20\n",
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m101s\u001b[0m 7s/step - accuracy: 0.4401 - loss: 3.5201 - val_accuracy: 0.4607 - val_loss: 0.9513 - learning_rate: 1.0000e-05\n",
+      "Epoch 11/20\n",
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m78s\u001b[0m 6s/step - accuracy: 0.5555 - loss: 2.0987 - val_accuracy: 0.4157 - val_loss: 1.0550 - learning_rate: 1.0000e-05\n",
+      "Epoch 12/20\n",
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 6s/step - accuracy: 0.4555 - loss: 1.7529 - val_accuracy: 0.4157 - val_loss: 1.2538 - learning_rate: 1.0000e-05\n",
+      "Epoch 13/20\n",
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m72s\u001b[0m 6s/step - accuracy: 0.5554 - loss: 1.0633 - val_accuracy: 0.4157 - val_loss: 1.4237 - learning_rate: 2.0000e-06\n",
+      "Epoch 14/20\n",
+      "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m75s\u001b[0m 6s/step - accuracy: 0.5212 - loss: 1.2389 - val_accuracy: 0.4157 - val_loss: 1.7295 - learning_rate: 2.0000e-06\n"
+     ]
+    }
+   ],
+   "source": [
+    "base_model.trainable = True\n",
+    "fine_tune_at = 100\n",
+    "\n",
+    "# Set the earlier layers to not be trainable\n",
+    "for layer in base_model.layers[:fine_tune_at]:\n",
+    "    layer.trainable = False\n",
+    "\n",
+    "# Ensure you include a loss function here\n",
+    "model.compile(optimizer=tf.keras.optimizers.Adam(1e-5), \n",
+    "              loss='categorical_crossentropy',  # This should be the loss function you used initially\n",
+    "              metrics=['accuracy'])\n",
+    "\n",
+    "fine_tune_epochs = 10\n",
+    "total_epochs = history.epoch[-1] + fine_tune_epochs + 1\n",
+    "\n",
+    "history_fine = model.fit(\n",
+    "    train_generator,\n",
+    "    epochs=total_epochs,\n",
+    "    initial_epoch=history.epoch[-1],\n",
+    "    validation_data=validation_generator,\n",
+    "    callbacks=[early_stopping, model_checkpoint, reduce_lr]\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.save('pokemon_classifier_model.keras')\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.9.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}