diff --git a/backup.ipynb b/backup.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..a9a52049143171217d17418469293b143065a0d7
--- /dev/null
+++ b/backup.ipynb
@@ -0,0 +1,93 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "###########################################################################\n",
+ "# ImageGenerator with dataframes\n",
+ "###########################################################################\n",
+ "\n",
+ "#Size of our input images\n",
+ "SIZE = 128\n",
+ "# Size of ba\n",
+ "batch_size = 64\n",
+ "\n",
+ "# Pfad zum Ordner, der nur Bilder der Klasse A enthält\n",
+ "src_path = \"data/cell_images\"\n",
+ "\n",
+ "\n",
+ "# Klasse \"uninfected_train\"\n",
+ "# Pfad zum Ordner mit den Bildern\n",
+ "src_path_train = \"data/cell_images/uninfected_train\"\n",
+ "# Liste der Dateinamen im Ordner\n",
+ "file_list_train = os.listdir(src_path_train)\n",
+ "# Liste der Labels (Klassen) für die Bilder\n",
+ "labels_train = ['uninfected_train'] * len(file_list_train) # Bilder im Ordner werden Klasse \"uninfected_train\" zugeordnet\n",
+ "# Erstellen eines DataFrames mit Dateinamen und den entsprechenden Labels\n",
+ "df_data_train = pd.DataFrame({'filename': file_list_train, 'label': labels_train})\n",
+ "\n",
+ "# Klasse \"uninfected_test\"\n",
+ "src_path_test = \"data/cell_images/uninfected_test\"\n",
+ "file_list_test = os.listdir(src_path_test)\n",
+ "labels_test = ['uninfected_test'] * len(file_list_test)\n",
+ "df_data_test = pd.DataFrame({'filename': file_list_test, 'label': labels_test})\n",
+ "\n",
+ "# Klasse \"parasitized\"\n",
+ "src_path_parasitized = \"data/cell_images/parasitized\"\n",
+ "file_list_parasitized = os.listdir(src_path_parasitized)\n",
+ "labels_parasitized = ['parasitized'] * len(file_list_parasitized)\n",
+ "df_data_parasitized = pd.DataFrame({'filename': file_list_parasitized, 'label': labels_parasitized})\n",
+ "\n",
+ "\n",
+ "#Define generators for training, validation and also anomaly data\n",
+ "# Konfigurieren des ImageDataGenerator für das Rescaling der Pixelwerte\n",
+ "datagen = ImageDataGenerator(rescale=1./255)\n",
+ "\n",
+ "# Erstellen eines ImageDataGenerator-Objekts, um Bilder und Labels zu laden, Klasse \"df_data_train\"\n",
+ "train_generator = datagen.flow_from_dataframe(\n",
+ " df_data_train,\n",
+ " src_path_train, # Verzeichnis, das die Bilder enthält\n",
+ " x_col='filename', # Name der Spalte im DataFrame, die die Dateinamen enthält\n",
+ " y_col='label', # Name der Spalte im DataFrame, die die Labels enthält\n",
+ " target_size=(SIZE, SIZE), # Größe der Eingabebilder\n",
+ " batch_size=batch_size, # Anzahl der Bilder pro Batch\n",
+ " class_mode='categorical', # 'categorical' für Klassifikation, 'binary' für binäre Klassifikation\n",
+ " shuffle=True\n",
+ ")\n",
+ "\n",
+ "validation_generator = datagen.flow_from_dataframe(\n",
+ " df_data_test,\n",
+ " src_path_test,\n",
+ " x_col='filename',\n",
+ " y_col='label',\n",
+ " target_size=(SIZE, SIZE),\n",
+ " batch_size=batch_size,\n",
+ " class_mode='categorical',\n",
+ " shuffle=True\n",
+ ")\n",
+ "\n",
+ "anomaly_generator = datagen.flow_from_dataframe(\n",
+ " df_data_parasitized,\n",
+ " src_path_parasitized,\n",
+ " x_col='filename',\n",
+ " y_col='label',\n",
+ " target_size=(SIZE, SIZE),\n",
+ " batch_size=batch_size,\n",
+ " class_mode='categorical',\n",
+ " shuffle=True\n",
+ ")"
+ ]
+ }
+ ],
+ "metadata": {
+ "language_info": {
+ "name": "python"
+ },
+ "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/detecting_anomalie.ipynb b/detecting_anomalie.ipynb
index c8508818b4c7370d48d658cc3bde65692e829958..11f01ef413d7f6a4a076df3742e012b8a60826d8 100644
--- a/detecting_anomalie.ipynb
+++ b/detecting_anomalie.ipynb
@@ -19,7 +19,7 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
@@ -37,7 +37,7 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 2,
"metadata": {},
"outputs": [
{
@@ -84,7 +84,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 3,
"metadata": {},
"outputs": [
{
@@ -165,426 +165,9 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Epoch 1/200\n",
- "5/5 [==============================] - 28s 5s/step - loss: 0.0921 - mse: 0.0921 - val_loss: 0.0807 - val_mse: 0.0807\n",
- "Epoch 2/200\n",
- "5/5 [==============================] - 30s 6s/step - loss: 0.0741 - mse: 0.0741 - val_loss: 0.0575 - val_mse: 0.0575\n",
- "Epoch 3/200\n",
- "5/5 [==============================] - 27s 5s/step - loss: 0.0520 - mse: 0.0520 - val_loss: 0.0420 - val_mse: 0.0420\n",
- "Epoch 4/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0348 - mse: 0.0348 - val_loss: 0.0249 - val_mse: 0.0249\n",
- "Epoch 5/200\n",
- "5/5 [==============================] - 28s 6s/step - loss: 0.0229 - mse: 0.0229 - val_loss: 0.0183 - val_mse: 0.0183\n",
- "Epoch 6/200\n",
- "5/5 [==============================] - 30s 6s/step - loss: 0.0171 - mse: 0.0171 - val_loss: 0.0165 - val_mse: 0.0165\n",
- "Epoch 7/200\n",
- "5/5 [==============================] - 31s 6s/step - loss: 0.0158 - mse: 0.0158 - val_loss: 0.0144 - val_mse: 0.0144\n",
- "Epoch 8/200\n",
- "5/5 [==============================] - 33s 7s/step - loss: 0.0143 - mse: 0.0143 - val_loss: 0.0136 - val_mse: 0.0136\n",
- "Epoch 9/200\n",
- "5/5 [==============================] - 39s 8s/step - loss: 0.0134 - mse: 0.0134 - val_loss: 0.0135 - val_mse: 0.0135\n",
- "Epoch 10/200\n",
- "5/5 [==============================] - 37s 7s/step - loss: 0.0127 - mse: 0.0127 - val_loss: 0.0125 - val_mse: 0.0125\n",
- "Epoch 11/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0123 - mse: 0.0123 - val_loss: 0.0119 - val_mse: 0.0119\n",
- "Epoch 12/200\n",
- "5/5 [==============================] - 28s 6s/step - loss: 0.0117 - mse: 0.0117 - val_loss: 0.0114 - val_mse: 0.0114\n",
- "Epoch 13/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0110 - mse: 0.0110 - val_loss: 0.0110 - val_mse: 0.0110\n",
- "Epoch 14/200\n",
- "5/5 [==============================] - 22s 4s/step - loss: 0.0109 - mse: 0.0109 - val_loss: 0.0121 - val_mse: 0.0121\n",
- "Epoch 15/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0107 - mse: 0.0107 - val_loss: 0.0103 - val_mse: 0.0103\n",
- "Epoch 16/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0105 - mse: 0.0105 - val_loss: 0.0104 - val_mse: 0.0104\n",
- "Epoch 17/200\n",
- "5/5 [==============================] - 21s 4s/step - loss: 0.0101 - mse: 0.0101 - val_loss: 0.0106 - val_mse: 0.0106\n",
- "Epoch 18/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0103 - mse: 0.0103 - val_loss: 0.0101 - val_mse: 0.0101\n",
- "Epoch 19/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0100 - mse: 0.0100 - val_loss: 0.0100 - val_mse: 0.0100\n",
- "Epoch 20/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0097 - mse: 0.0097 - val_loss: 0.0100 - val_mse: 0.0100\n",
- "Epoch 21/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0097 - mse: 0.0097 - val_loss: 0.0091 - val_mse: 0.0091\n",
- "Epoch 22/200\n",
- "5/5 [==============================] - 21s 4s/step - loss: 0.0094 - mse: 0.0094 - val_loss: 0.0095 - val_mse: 0.0095\n",
- "Epoch 23/200\n",
- "5/5 [==============================] - 21s 5s/step - loss: 0.0093 - mse: 0.0093 - val_loss: 0.0099 - val_mse: 0.0099\n",
- "Epoch 24/200\n",
- "5/5 [==============================] - 21s 4s/step - loss: 0.0094 - mse: 0.0094 - val_loss: 0.0091 - val_mse: 0.0091\n",
- "Epoch 25/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0091 - mse: 0.0091 - val_loss: 0.0090 - val_mse: 0.0090\n",
- "Epoch 26/200\n",
- "5/5 [==============================] - 27s 5s/step - loss: 0.0088 - mse: 0.0088 - val_loss: 0.0087 - val_mse: 0.0087\n",
- "Epoch 27/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0087 - mse: 0.0087 - val_loss: 0.0087 - val_mse: 0.0087\n",
- "Epoch 28/200\n",
- "5/5 [==============================] - 29s 6s/step - loss: 0.0088 - mse: 0.0088 - val_loss: 0.0081 - val_mse: 0.0081\n",
- "Epoch 29/200\n",
- "5/5 [==============================] - 31s 6s/step - loss: 0.0084 - mse: 0.0084 - val_loss: 0.0083 - val_mse: 0.0083\n",
- "Epoch 30/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0082 - mse: 0.0082 - val_loss: 0.0081 - val_mse: 0.0081\n",
- "Epoch 31/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0080 - mse: 0.0080 - val_loss: 0.0078 - val_mse: 0.0078\n",
- "Epoch 32/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0077 - mse: 0.0077 - val_loss: 0.0077 - val_mse: 0.0077\n",
- "Epoch 33/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0075 - mse: 0.0075 - val_loss: 0.0070 - val_mse: 0.0070\n",
- "Epoch 34/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0074 - mse: 0.0074 - val_loss: 0.0074 - val_mse: 0.0074\n",
- "Epoch 35/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0071 - mse: 0.0071 - val_loss: 0.0073 - val_mse: 0.0073\n",
- "Epoch 36/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0072 - mse: 0.0072 - val_loss: 0.0069 - val_mse: 0.0069\n",
- "Epoch 37/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0072 - mse: 0.0072 - val_loss: 0.0071 - val_mse: 0.0071\n",
- "Epoch 38/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0072 - mse: 0.0072 - val_loss: 0.0069 - val_mse: 0.0069\n",
- "Epoch 39/200\n",
- "5/5 [==============================] - 21s 4s/step - loss: 0.0069 - mse: 0.0069 - val_loss: 0.0069 - val_mse: 0.0069\n",
- "Epoch 40/200\n",
- "5/5 [==============================] - 21s 4s/step - loss: 0.0068 - mse: 0.0068 - val_loss: 0.0068 - val_mse: 0.0068\n",
- "Epoch 41/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0067 - mse: 0.0067 - val_loss: 0.0067 - val_mse: 0.0067\n",
- "Epoch 42/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0066 - mse: 0.0066 - val_loss: 0.0065 - val_mse: 0.0065\n",
- "Epoch 43/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0064 - mse: 0.0064 - val_loss: 0.0062 - val_mse: 0.0062\n",
- "Epoch 44/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0064 - mse: 0.0064 - val_loss: 0.0063 - val_mse: 0.0063\n",
- "Epoch 45/200\n",
- "5/5 [==============================] - 28s 6s/step - loss: 0.0063 - mse: 0.0063 - val_loss: 0.0063 - val_mse: 0.0063\n",
- "Epoch 46/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0063 - mse: 0.0063 - val_loss: 0.0063 - val_mse: 0.0063\n",
- "Epoch 47/200\n",
- "5/5 [==============================] - 30s 6s/step - loss: 0.0065 - mse: 0.0065 - val_loss: 0.0063 - val_mse: 0.0063\n",
- "Epoch 48/200\n",
- "5/5 [==============================] - 22s 4s/step - loss: 0.0063 - mse: 0.0063 - val_loss: 0.0062 - val_mse: 0.0062\n",
- "Epoch 49/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0063 - mse: 0.0063 - val_loss: 0.0063 - val_mse: 0.0063\n",
- "Epoch 50/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0061 - mse: 0.0061 - val_loss: 0.0059 - val_mse: 0.0059\n",
- "Epoch 51/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0061 - mse: 0.0061 - val_loss: 0.0060 - val_mse: 0.0060\n",
- "Epoch 52/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0059 - mse: 0.0059 - val_loss: 0.0058 - val_mse: 0.0058\n",
- "Epoch 53/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0060 - mse: 0.0060 - val_loss: 0.0064 - val_mse: 0.0064\n",
- "Epoch 54/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0059 - mse: 0.0059 - val_loss: 0.0058 - val_mse: 0.0058\n",
- "Epoch 55/200\n",
- "5/5 [==============================] - 30s 6s/step - loss: 0.0062 - mse: 0.0062 - val_loss: 0.0057 - val_mse: 0.0057\n",
- "Epoch 56/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0061 - mse: 0.0061 - val_loss: 0.0062 - val_mse: 0.0062\n",
- "Epoch 57/200\n",
- "5/5 [==============================] - 35s 7s/step - loss: 0.0061 - mse: 0.0061 - val_loss: 0.0061 - val_mse: 0.0061\n",
- "Epoch 58/200\n",
- "5/5 [==============================] - 35s 7s/step - loss: 0.0059 - mse: 0.0059 - val_loss: 0.0062 - val_mse: 0.0062\n",
- "Epoch 59/200\n",
- "5/5 [==============================] - 37s 8s/step - loss: 0.0058 - mse: 0.0058 - val_loss: 0.0059 - val_mse: 0.0059\n",
- "Epoch 60/200\n",
- "5/5 [==============================] - 44s 9s/step - loss: 0.0058 - mse: 0.0058 - val_loss: 0.0061 - val_mse: 0.0061\n",
- "Epoch 61/200\n",
- "5/5 [==============================] - 31s 6s/step - loss: 0.0057 - mse: 0.0057 - val_loss: 0.0057 - val_mse: 0.0057\n",
- "Epoch 62/200\n",
- "5/5 [==============================] - 39s 7s/step - loss: 0.0057 - mse: 0.0057 - val_loss: 0.0059 - val_mse: 0.0059\n",
- "Epoch 63/200\n",
- "5/5 [==============================] - 49s 10s/step - loss: 0.0057 - mse: 0.0057 - val_loss: 0.0058 - val_mse: 0.0058\n",
- "Epoch 64/200\n",
- "5/5 [==============================] - 45s 9s/step - loss: 0.0056 - mse: 0.0056 - val_loss: 0.0059 - val_mse: 0.0059\n",
- "Epoch 65/200\n",
- "5/5 [==============================] - 53s 11s/step - loss: 0.0057 - mse: 0.0057 - val_loss: 0.0054 - val_mse: 0.0054\n",
- "Epoch 66/200\n",
- "5/5 [==============================] - 46s 10s/step - loss: 0.0054 - mse: 0.0054 - val_loss: 0.0058 - val_mse: 0.0058\n",
- "Epoch 67/200\n",
- "5/5 [==============================] - 53s 11s/step - loss: 0.0056 - mse: 0.0056 - val_loss: 0.0056 - val_mse: 0.0056\n",
- "Epoch 68/200\n",
- "5/5 [==============================] - 37s 7s/step - loss: 0.0057 - mse: 0.0057 - val_loss: 0.0055 - val_mse: 0.0055\n",
- "Epoch 69/200\n",
- "5/5 [==============================] - 38s 8s/step - loss: 0.0055 - mse: 0.0055 - val_loss: 0.0058 - val_mse: 0.0058\n",
- "Epoch 70/200\n",
- "5/5 [==============================] - 36s 7s/step - loss: 0.0056 - mse: 0.0056 - val_loss: 0.0054 - val_mse: 0.0054\n",
- "Epoch 71/200\n",
- "5/5 [==============================] - 31s 6s/step - loss: 0.0055 - mse: 0.0055 - val_loss: 0.0053 - val_mse: 0.0053\n",
- "Epoch 72/200\n",
- "5/5 [==============================] - 29s 6s/step - loss: 0.0055 - mse: 0.0055 - val_loss: 0.0057 - val_mse: 0.0057\n",
- "Epoch 73/200\n",
- "5/5 [==============================] - 27s 5s/step - loss: 0.0055 - mse: 0.0055 - val_loss: 0.0055 - val_mse: 0.0055\n",
- "Epoch 74/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0054 - mse: 0.0054 - val_loss: 0.0056 - val_mse: 0.0056\n",
- "Epoch 75/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0054 - mse: 0.0054 - val_loss: 0.0052 - val_mse: 0.0052\n",
- "Epoch 76/200\n",
- "5/5 [==============================] - 27s 5s/step - loss: 0.0054 - mse: 0.0054 - val_loss: 0.0057 - val_mse: 0.0057\n",
- "Epoch 77/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0054 - mse: 0.0054 - val_loss: 0.0054 - val_mse: 0.0054\n",
- "Epoch 78/200\n",
- "5/5 [==============================] - 28s 6s/step - loss: 0.0054 - mse: 0.0054 - val_loss: 0.0051 - val_mse: 0.0051\n",
- "Epoch 79/200\n",
- "5/5 [==============================] - 31s 6s/step - loss: 0.0054 - mse: 0.0054 - val_loss: 0.0052 - val_mse: 0.0052\n",
- "Epoch 80/200\n",
- "5/5 [==============================] - 33s 7s/step - loss: 0.0054 - mse: 0.0054 - val_loss: 0.0052 - val_mse: 0.0052\n",
- "Epoch 81/200\n",
- "5/5 [==============================] - 34s 7s/step - loss: 0.0053 - mse: 0.0053 - val_loss: 0.0058 - val_mse: 0.0058\n",
- "Epoch 82/200\n",
- "5/5 [==============================] - 28s 5s/step - loss: 0.0055 - mse: 0.0055 - val_loss: 0.0051 - val_mse: 0.0051\n",
- "Epoch 83/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0053 - mse: 0.0053 - val_loss: 0.0053 - val_mse: 0.0053\n",
- "Epoch 84/200\n",
- "5/5 [==============================] - 27s 5s/step - loss: 0.0053 - mse: 0.0053 - val_loss: 0.0051 - val_mse: 0.0051\n",
- "Epoch 85/200\n",
- "5/5 [==============================] - 29s 5s/step - loss: 0.0051 - mse: 0.0051 - val_loss: 0.0051 - val_mse: 0.0051\n",
- "Epoch 86/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0052 - mse: 0.0052 - val_loss: 0.0051 - val_mse: 0.0051\n",
- "Epoch 87/200\n",
- "5/5 [==============================] - 27s 5s/step - loss: 0.0052 - mse: 0.0052 - val_loss: 0.0052 - val_mse: 0.0052\n",
- "Epoch 88/200\n",
- "5/5 [==============================] - 27s 5s/step - loss: 0.0051 - mse: 0.0051 - val_loss: 0.0052 - val_mse: 0.0052\n",
- "Epoch 89/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0050 - mse: 0.0050 - val_loss: 0.0049 - val_mse: 0.0049\n",
- "Epoch 90/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0051 - mse: 0.0051 - val_loss: 0.0052 - val_mse: 0.0052\n",
- "Epoch 91/200\n",
- "5/5 [==============================] - 23s 4s/step - loss: 0.0051 - mse: 0.0051 - val_loss: 0.0053 - val_mse: 0.0053\n",
- "Epoch 92/200\n",
- "5/5 [==============================] - 23s 4s/step - loss: 0.0052 - mse: 0.0052 - val_loss: 0.0055 - val_mse: 0.0055\n",
- "Epoch 93/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0052 - mse: 0.0052 - val_loss: 0.0050 - val_mse: 0.0050\n",
- "Epoch 94/200\n",
- "5/5 [==============================] - 23s 5s/step - loss: 0.0051 - mse: 0.0051 - val_loss: 0.0050 - val_mse: 0.0050\n",
- "Epoch 95/200\n",
- "5/5 [==============================] - 23s 4s/step - loss: 0.0050 - mse: 0.0050 - val_loss: 0.0050 - val_mse: 0.0050\n",
- "Epoch 96/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0049 - mse: 0.0049 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 97/200\n",
- "5/5 [==============================] - 29s 6s/step - loss: 0.0050 - mse: 0.0050 - val_loss: 0.0052 - val_mse: 0.0052\n",
- "Epoch 98/200\n",
- "5/5 [==============================] - 31s 6s/step - loss: 0.0049 - mse: 0.0049 - val_loss: 0.0051 - val_mse: 0.0051\n",
- "Epoch 99/200\n",
- "5/5 [==============================] - 29s 6s/step - loss: 0.0049 - mse: 0.0049 - val_loss: 0.0050 - val_mse: 0.0050\n",
- "Epoch 100/200\n",
- "5/5 [==============================] - 29s 6s/step - loss: 0.0050 - mse: 0.0050 - val_loss: 0.0050 - val_mse: 0.0050\n",
- "Epoch 101/200\n",
- "5/5 [==============================] - 23s 4s/step - loss: 0.0050 - mse: 0.0050 - val_loss: 0.0050 - val_mse: 0.0050\n",
- "Epoch 102/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0050 - mse: 0.0050 - val_loss: 0.0052 - val_mse: 0.0052\n",
- "Epoch 103/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0050 - mse: 0.0050 - val_loss: 0.0050 - val_mse: 0.0050\n",
- "Epoch 104/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 105/200\n",
- "5/5 [==============================] - 27s 6s/step - loss: 0.0049 - mse: 0.0049 - val_loss: 0.0050 - val_mse: 0.0050\n",
- "Epoch 106/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0049 - mse: 0.0049 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 107/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0049 - mse: 0.0049 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 108/200\n",
- "5/5 [==============================] - 21s 4s/step - loss: 0.0049 - mse: 0.0049 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 109/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0051 - mse: 0.0051 - val_loss: 0.0053 - val_mse: 0.0053\n",
- "Epoch 110/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0050 - mse: 0.0050 - val_loss: 0.0050 - val_mse: 0.0050\n",
- "Epoch 111/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0049 - mse: 0.0049 - val_loss: 0.0050 - val_mse: 0.0050\n",
- "Epoch 112/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0047 - val_mse: 0.0047\n",
- "Epoch 113/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0049 - mse: 0.0049 - val_loss: 0.0046 - val_mse: 0.0046\n",
- "Epoch 114/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0050 - val_mse: 0.0050\n",
- "Epoch 115/200\n",
- "5/5 [==============================] - 28s 6s/step - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0050 - val_mse: 0.0050\n",
- "Epoch 116/200\n",
- "5/5 [==============================] - 29s 6s/step - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0049 - val_mse: 0.0049\n",
- "Epoch 117/200\n",
- "5/5 [==============================] - 30s 6s/step - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0047 - val_mse: 0.0047\n",
- "Epoch 118/200\n",
- "5/5 [==============================] - 30s 6s/step - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 119/200\n",
- "5/5 [==============================] - 22s 4s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 120/200\n",
- "5/5 [==============================] - 24s 6s/step - loss: 0.0047 - mse: 0.0047 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 121/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0047 - mse: 0.0047 - val_loss: 0.0047 - val_mse: 0.0047\n",
- "Epoch 122/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 123/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0049 - mse: 0.0049 - val_loss: 0.0049 - val_mse: 0.0049\n",
- "Epoch 124/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0047 - val_mse: 0.0047\n",
- "Epoch 125/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0047 - val_mse: 0.0047\n",
- "Epoch 126/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 127/200\n",
- "5/5 [==============================] - 21s 4s/step - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0047 - val_mse: 0.0047\n",
- "Epoch 128/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0047 - mse: 0.0047 - val_loss: 0.0044 - val_mse: 0.0044\n",
- "Epoch 129/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 130/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 131/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0047 - mse: 0.0047 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 132/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0046 - val_mse: 0.0046\n",
- "Epoch 133/200\n",
- "5/5 [==============================] - 27s 5s/step - loss: 0.0047 - mse: 0.0047 - val_loss: 0.0046 - val_mse: 0.0046\n",
- "Epoch 134/200\n",
- "5/5 [==============================] - 28s 6s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0046 - val_mse: 0.0046\n",
- "Epoch 135/200\n",
- "5/5 [==============================] - 30s 6s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 136/200\n",
- "5/5 [==============================] - 31s 6s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0047 - val_mse: 0.0047\n",
- "Epoch 137/200\n",
- "5/5 [==============================] - 28s 5s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0046 - val_mse: 0.0046\n",
- "Epoch 138/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0047 - mse: 0.0047 - val_loss: 0.0044 - val_mse: 0.0044\n",
- "Epoch 139/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 140/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 141/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 142/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0047 - val_mse: 0.0047\n",
- "Epoch 143/200\n",
- "5/5 [==============================] - 22s 5s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0046 - val_mse: 0.0046\n",
- "Epoch 144/200\n",
- "5/5 [==============================] - 22s 5s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0046 - val_mse: 0.0046\n",
- "Epoch 145/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 146/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0047 - mse: 0.0047 - val_loss: 0.0049 - val_mse: 0.0049\n",
- "Epoch 147/200\n",
- "5/5 [==============================] - 22s 4s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0046 - val_mse: 0.0046\n",
- "Epoch 148/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0047 - val_mse: 0.0047\n",
- "Epoch 149/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 150/200\n",
- "5/5 [==============================] - 22s 4s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0046 - val_mse: 0.0046\n",
- "Epoch 151/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 152/200\n",
- "5/5 [==============================] - 30s 6s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0044 - val_mse: 0.0044\n",
- "Epoch 153/200\n",
- "5/5 [==============================] - 31s 6s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 154/200\n",
- "5/5 [==============================] - 31s 6s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0044 - val_mse: 0.0044\n",
- "Epoch 155/200\n",
- "5/5 [==============================] - 32s 6s/step - loss: 0.0049 - mse: 0.0049 - val_loss: 0.0047 - val_mse: 0.0047\n",
- "Epoch 156/200\n",
- "5/5 [==============================] - 28s 6s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0044 - val_mse: 0.0044\n",
- "Epoch 157/200\n",
- "5/5 [==============================] - 22s 4s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 158/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0047 - mse: 0.0047 - val_loss: 0.0043 - val_mse: 0.0043\n",
- "Epoch 159/200\n",
- "5/5 [==============================] - 22s 5s/step - loss: 0.0047 - mse: 0.0047 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 160/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 161/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0049 - val_mse: 0.0049\n",
- "Epoch 162/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 163/200\n",
- "5/5 [==============================] - 22s 4s/step - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 164/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0047 - mse: 0.0047 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 165/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0046 - val_mse: 0.0046\n",
- "Epoch 166/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0044 - val_mse: 0.0044\n",
- "Epoch 167/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0043 - val_mse: 0.0043\n",
- "Epoch 168/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0048 - val_mse: 0.0048\n",
- "Epoch 169/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0044 - val_mse: 0.0044\n",
- "Epoch 170/200\n",
- "5/5 [==============================] - 25s 6s/step - loss: 0.0043 - mse: 0.0043 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 171/200\n",
- "5/5 [==============================] - 31s 6s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 172/200\n",
- "5/5 [==============================] - 28s 7s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0047 - val_mse: 0.0047\n",
- "Epoch 173/200\n",
- "5/5 [==============================] - 32s 7s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0044 - val_mse: 0.0044\n",
- "Epoch 174/200\n",
- "5/5 [==============================] - 28s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0044 - val_mse: 0.0044\n",
- "Epoch 175/200\n",
- "5/5 [==============================] - 27s 5s/step - loss: 0.0043 - mse: 0.0043 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 176/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0043 - val_mse: 0.0043\n",
- "Epoch 177/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0043 - val_mse: 0.0043\n",
- "Epoch 178/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 179/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 180/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0044 - val_mse: 0.0044\n",
- "Epoch 181/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0043 - mse: 0.0043 - val_loss: 0.0042 - val_mse: 0.0042\n",
- "Epoch 182/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0043 - val_mse: 0.0043\n",
- "Epoch 183/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 184/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 185/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0043 - mse: 0.0043 - val_loss: 0.0044 - val_mse: 0.0044\n",
- "Epoch 186/200\n",
- "5/5 [==============================] - 24s 5s/step - loss: 0.0043 - mse: 0.0043 - val_loss: 0.0043 - val_mse: 0.0043\n",
- "Epoch 187/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0046 - val_mse: 0.0046\n",
- "Epoch 188/200\n",
- "5/5 [==============================] - 27s 5s/step - loss: 0.0043 - mse: 0.0043 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 189/200\n",
- "5/5 [==============================] - 28s 6s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0043 - val_mse: 0.0043\n",
- "Epoch 190/200\n",
- "5/5 [==============================] - 30s 6s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0043 - val_mse: 0.0043\n",
- "Epoch 191/200\n",
- "5/5 [==============================] - 31s 6s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0043 - val_mse: 0.0043\n",
- "Epoch 192/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0043 - val_mse: 0.0043\n",
- "Epoch 193/200\n",
- "5/5 [==============================] - 27s 5s/step - loss: 0.0043 - mse: 0.0043 - val_loss: 0.0044 - val_mse: 0.0044\n",
- "Epoch 194/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0043 - mse: 0.0043 - val_loss: 0.0043 - val_mse: 0.0043\n",
- "Epoch 195/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0044 - val_mse: 0.0044\n",
- "Epoch 196/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0051 - val_mse: 0.0051\n",
- "Epoch 197/200\n",
- "5/5 [==============================] - 25s 5s/step - loss: 0.0047 - mse: 0.0047 - val_loss: 0.0045 - val_mse: 0.0045\n",
- "Epoch 198/200\n",
- "5/5 [==============================] - 22s 4s/step - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0043 - val_mse: 0.0043\n",
- "Epoch 199/200\n",
- "5/5 [==============================] - 21s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0044 - val_mse: 0.0044\n",
- "Epoch 200/200\n",
- "5/5 [==============================] - 26s 5s/step - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0045 - val_mse: 0.0045\n"
- ]
- },
- {
- "data": {
- "image/png": "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",
- "text/plain": [
- "<Figure size 640x480 with 1 Axes>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
+ "outputs": [],
"source": [
"#Fit the model. \n",
"history = model.fit(\n",
@@ -611,18 +194,9 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "c:\\Users\\pgran\\OneDrive - Hochschule Hannover\\Semester 10\\Einarbeitung\\detecting_anomalies\\.venv\\lib\\site-packages\\keras\\src\\engine\\training.py:3000: UserWarning: You are saving your model as an HDF5 file via `model.save()`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')`.\n",
- " saving_api.save_model(\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"# Speichern des trainierten Modells\n",
"model.save('trained_modell.h5')"
@@ -630,7 +204,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 4,
"metadata": {},
"outputs": [
{
@@ -649,19 +223,19 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "2/2 [==============================] - 2s 572ms/step\n"
+ "2/2 [==============================] - 2s 592ms/step\n"
]
},
{
"data": {
- "image/png": "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",
+ "image/png": "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",
"text/plain": [
"<Figure size 1200x600 with 2 Axes>"
]
@@ -694,16 +268,16 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
- "C:\\Users\\pgran\\AppData\\Local\\Temp\\ipykernel_8048\\2468543786.py:3: UserWarning: `Model.evaluate_generator` is deprecated and will be removed in a future version. Please use `Model.evaluate`, which supports generators.\n",
+ "C:\\Users\\pgran\\AppData\\Local\\Temp\\ipykernel_12212\\2468543786.py:3: UserWarning: `Model.evaluate_generator` is deprecated and will be removed in a future version. Please use `Model.evaluate`, which supports generators.\n",
" validation_error = model.evaluate_generator(validation_generator)\n",
- "C:\\Users\\pgran\\AppData\\Local\\Temp\\ipykernel_8048\\2468543786.py:4: UserWarning: `Model.evaluate_generator` is deprecated and will be removed in a future version. Please use `Model.evaluate`, which supports generators.\n",
+ "C:\\Users\\pgran\\AppData\\Local\\Temp\\ipykernel_12212\\2468543786.py:4: UserWarning: `Model.evaluate_generator` is deprecated and will be removed in a future version. Please use `Model.evaluate`, which supports generators.\n",
" anomaly_error = model.evaluate_generator(anomaly_generator)\n"
]
},
@@ -712,7 +286,7 @@
"output_type": "stream",
"text": [
"Recon. error for the validation (normal) data is: [0.004411873407661915, 0.004411873407661915]\n",
- "Recon. error for the anomaly data is: [0.004912924952805042, 0.004912924952805042]\n"
+ "Recon. error for the anomaly data is: [0.00491292541846633, 0.00491292541846633]\n"
]
}
],
@@ -728,36 +302,30 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "Model: \"sequential_2\"\n"
- ]
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
+ "Model: \"sequential_1\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
- " conv2d_10 (Conv2D) (None, 128, 128, 64) 1792 \n",
+ " conv2d_7 (Conv2D) (None, 128, 128, 64) 1792 \n",
" \n",
- " max_pooling2d_6 (MaxPoolin (None, 64, 64, 64) 0 \n",
+ " max_pooling2d_3 (MaxPoolin (None, 64, 64, 64) 0 \n",
" g2D) \n",
" \n",
- " conv2d_11 (Conv2D) (None, 64, 64, 32) 18464 \n",
+ " conv2d_8 (Conv2D) (None, 64, 64, 32) 18464 \n",
" \n",
- " max_pooling2d_7 (MaxPoolin (None, 32, 32, 32) 0 \n",
+ " max_pooling2d_4 (MaxPoolin (None, 32, 32, 32) 0 \n",
" g2D) \n",
" \n",
- " conv2d_12 (Conv2D) (None, 32, 32, 16) 4624 \n",
+ " conv2d_9 (Conv2D) (None, 32, 32, 16) 4624 \n",
" \n",
- " max_pooling2d_8 (MaxPoolin (None, 16, 16, 16) 0 \n",
+ " max_pooling2d_5 (MaxPoolin (None, 16, 16, 16) 0 \n",
" g2D) \n",
" \n",
"=================================================================\n",
@@ -766,17 +334,6 @@
"Non-trainable params: 0 (0.00 Byte)\n",
"_________________________________________________________________\n"
]
- },
- {
- "ename": "ModuleNotFoundError",
- "evalue": "No module named 'sklearn'",
- "output_type": "error",
- "traceback": [
- "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[1;32mIn[10], line 16\u001b[0m\n\u001b[0;32m 12\u001b[0m encoder_model\u001b[39m.\u001b[39msummary()\n\u001b[0;32m 14\u001b[0m \u001b[39m########################################################\u001b[39;00m\n\u001b[0;32m 15\u001b[0m \u001b[39m# Calculate KDE using sklearn\u001b[39;00m\n\u001b[1;32m---> 16\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39msklearn\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mneighbors\u001b[39;00m \u001b[39mimport\u001b[39;00m KernelDensity\n\u001b[0;32m 18\u001b[0m \u001b[39m#Get encoded output of input images = Latent space\u001b[39;00m\n\u001b[0;32m 19\u001b[0m encoded_images \u001b[39m=\u001b[39m encoder_model\u001b[39m.\u001b[39mpredict_generator(train_generator)\n",
- "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'sklearn'"
- ]
}
],
"source": [
@@ -791,8 +348,24 @@
"encoder_model.add(MaxPooling2D((2, 2), padding='same'))\n",
"encoder_model.add(Conv2D(16, (3, 3), activation='relu', padding='same', weights=model.layers[4].get_weights()))\n",
"encoder_model.add(MaxPooling2D((2, 2), padding='same'))\n",
- "encoder_model.summary()\n",
- "\n",
+ "encoder_model.summary()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "C:\\Users\\pgran\\AppData\\Local\\Temp\\ipykernel_12212\\2898042301.py:6: UserWarning: `Model.predict_generator` is deprecated and will be removed in a future version. Please use `Model.predict`, which supports generators.\n",
+ " encoded_images = encoder_model.predict_generator(train_generator)\n"
+ ]
+ }
+ ],
+ "source": [
"########################################################\n",
"# Calculate KDE using sklearn\n",
"from sklearn.neighbors import KernelDensity\n",
@@ -807,8 +380,408 @@
"encoded_images_vector = [np.reshape(img, (out_vector_shape)) for img in encoded_images]\n",
"\n",
"#Fit KDE to the image latent data\n",
- "kde = KernelDensity(kernel='gaussian', bandwidth=0.2).fit(encoded_images_vector)\n",
- "\n",
+ "kde = KernelDensity(kernel='gaussian', bandwidth=0.2).fit(encoded_images_vector)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "C:\\Users\\pgran\\AppData\\Local\\Temp\\ipykernel_12212\\3483831194.py:6: UserWarning: `Model.predict_generator` is deprecated and will be removed in a future version. Please use `Model.predict`, which supports generators.\n",
+ " encoded_images = encoder_model.predict_generator(train_generator)\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "1/1 [==============================] - 0s 102ms/step\n",
+ "1/1 [==============================] - 0s 249ms/step\n",
+ "1/1 [==============================] - 0s 344ms/step - loss: 0.0049 - mse: 0.0049\n",
+ "1/1 [==============================] - 0s 57ms/step\n",
+ "1/1 [==============================] - 0s 59ms/step\n",
+ "1/1 [==============================] - 0s 75ms/step - loss: 0.0053 - mse: 0.0053\n",
+ "1/1 [==============================] - 0s 51ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step\n",
+ "1/1 [==============================] - 0s 67ms/step - loss: 0.0050 - mse: 0.0050\n",
+ "1/1 [==============================] - 0s 53ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step\n",
+ "1/1 [==============================] - 0s 90ms/step - loss: 0.0068 - mse: 0.0068\n",
+ "1/1 [==============================] - 0s 49ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step\n",
+ "1/1 [==============================] - 0s 56ms/step - loss: 0.0055 - mse: 0.0055\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step\n",
+ "1/1 [==============================] - 0s 71ms/step - loss: 0.0053 - mse: 0.0053\n",
+ "1/1 [==============================] - 0s 46ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step - loss: 0.0063 - mse: 0.0063\n",
+ "1/1 [==============================] - 0s 51ms/step\n",
+ "1/1 [==============================] - 0s 56ms/step\n",
+ "1/1 [==============================] - 0s 60ms/step - loss: 0.0106 - mse: 0.0106\n",
+ "1/1 [==============================] - 0s 49ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step\n",
+ "1/1 [==============================] - 0s 76ms/step - loss: 0.0058 - mse: 0.0058\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 64ms/step\n",
+ "1/1 [==============================] - 0s 61ms/step - loss: 0.0052 - mse: 0.0052\n",
+ "1/1 [==============================] - 0s 52ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step - loss: 0.0060 - mse: 0.0060\n",
+ "1/1 [==============================] - 0s 36ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step - loss: 0.0056 - mse: 0.0056\n",
+ "1/1 [==============================] - 0s 41ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step - loss: 0.0047 - mse: 0.0047\n",
+ "1/1 [==============================] - 0s 33ms/step\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 59ms/step - loss: 0.0057 - mse: 0.0057\n",
+ "1/1 [==============================] - 0s 40ms/step\n",
+ "1/1 [==============================] - 0s 38ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step - loss: 0.0047 - mse: 0.0047\n",
+ "1/1 [==============================] - 0s 41ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step - loss: 0.0075 - mse: 0.0075\n",
+ "1/1 [==============================] - 0s 41ms/step\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step - loss: 0.0046 - mse: 0.0046\n",
+ "1/1 [==============================] - 0s 36ms/step\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step - loss: 0.0057 - mse: 0.0057\n",
+ "1/1 [==============================] - 0s 41ms/step\n",
+ "1/1 [==============================] - 0s 51ms/step\n",
+ "1/1 [==============================] - 0s 47ms/step - loss: 0.0048 - mse: 0.0048\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 45ms/step\n",
+ "1/1 [==============================] - 0s 58ms/step - loss: 0.0071 - mse: 0.0071\n",
+ "1/1 [==============================] - 0s 35ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step\n",
+ "1/1 [==============================] - 0s 58ms/step - loss: 0.0050 - mse: 0.0050\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step\n",
+ "1/1 [==============================] - 0s 61ms/step - loss: 0.0047 - mse: 0.0047\n",
+ "1/1 [==============================] - 0s 36ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step\n",
+ "1/1 [==============================] - 0s 62ms/step - loss: 0.0051 - mse: 0.0051\n",
+ "1/1 [==============================] - 0s 38ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step\n",
+ "1/1 [==============================] - 0s 65ms/step - loss: 0.0071 - mse: 0.0071\n",
+ "1/1 [==============================] - 0s 46ms/step\n",
+ "1/1 [==============================] - 0s 46ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step - loss: 0.0083 - mse: 0.0083\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 45ms/step\n",
+ "1/1 [==============================] - 0s 51ms/step - loss: 0.0063 - mse: 0.0063\n",
+ "1/1 [==============================] - 0s 37ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step\n",
+ "1/1 [==============================] - 0s 56ms/step - loss: 0.0068 - mse: 0.0068\n",
+ "1/1 [==============================] - 0s 46ms/step\n",
+ "1/1 [==============================] - 0s 51ms/step\n",
+ "1/1 [==============================] - 0s 153ms/step - loss: 0.0049 - mse: 0.0049\n",
+ "1/1 [==============================] - 0s 32ms/step\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 58ms/step - loss: 0.0071 - mse: 0.0071\n",
+ "1/1 [==============================] - 0s 41ms/step\n",
+ "1/1 [==============================] - 0s 37ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step - loss: 0.0044 - mse: 0.0044\n",
+ "1/1 [==============================] - 0s 34ms/step\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 56ms/step - loss: 0.0044 - mse: 0.0044\n",
+ "1/1 [==============================] - 0s 38ms/step\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step - loss: 0.0054 - mse: 0.0054\n",
+ "1/1 [==============================] - 0s 44ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step\n",
+ "1/1 [==============================] - 0s 59ms/step - loss: 0.0055 - mse: 0.0055\n",
+ "1/1 [==============================] - 0s 45ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step - loss: 0.0049 - mse: 0.0049\n",
+ "1/1 [==============================] - 0s 35ms/step\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step - loss: 0.0056 - mse: 0.0056\n",
+ "1/1 [==============================] - 0s 43ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step - loss: 0.0051 - mse: 0.0051\n",
+ "1/1 [==============================] - 0s 46ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step - loss: 0.0078 - mse: 0.0078\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 70ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step - loss: 0.0050 - mse: 0.0050\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step\n",
+ "1/1 [==============================] - 0s 60ms/step - loss: 0.0072 - mse: 0.0072\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step\n",
+ "1/1 [==============================] - 0s 58ms/step - loss: 0.0057 - mse: 0.0057\n",
+ "1/1 [==============================] - 0s 44ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 60ms/step - loss: 0.0054 - mse: 0.0054\n",
+ "1/1 [==============================] - 0s 46ms/step\n",
+ "1/1 [==============================] - 0s 43ms/step\n",
+ "1/1 [==============================] - 0s 56ms/step - loss: 0.0049 - mse: 0.0049\n",
+ "1/1 [==============================] - 0s 45ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step\n",
+ "1/1 [==============================] - 0s 59ms/step - loss: 0.0067 - mse: 0.0067\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 59ms/step - loss: 0.0041 - mse: 0.0041\n",
+ "1/1 [==============================] - 0s 37ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step - loss: 0.0067 - mse: 0.0067\n",
+ "1/1 [==============================] - 0s 36ms/step\n",
+ "1/1 [==============================] - 0s 46ms/step\n",
+ "1/1 [==============================] - 0s 61ms/step - loss: 0.0064 - mse: 0.0064\n",
+ "1/1 [==============================] - 0s 40ms/step\n",
+ "1/1 [==============================] - 0s 46ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step - loss: 0.0056 - mse: 0.0056\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step - loss: 0.0061 - mse: 0.0061\n",
+ "1/1 [==============================] - 0s 43ms/step\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step - loss: 0.0078 - mse: 0.0078\n",
+ "1/1 [==============================] - 0s 44ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step\n",
+ "1/1 [==============================] - 0s 56ms/step - loss: 0.0047 - mse: 0.0047\n",
+ "1/1 [==============================] - 0s 40ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step - loss: 0.0062 - mse: 0.0062\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 58ms/step - loss: 0.0068 - mse: 0.0068\n",
+ "1/1 [==============================] - 0s 43ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step\n",
+ "1/1 [==============================] - 0s 62ms/step - loss: 0.0049 - mse: 0.0049\n",
+ "1/1 [==============================] - 0s 41ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step\n",
+ "1/1 [==============================] - 0s 127ms/step - loss: 0.0047 - mse: 0.0047\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step - loss: 0.0058 - mse: 0.0058\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step\n",
+ "1/1 [==============================] - 0s 60ms/step - loss: 0.0060 - mse: 0.0060\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step\n",
+ "1/1 [==============================] - 0s 67ms/step - loss: 0.0051 - mse: 0.0051\n",
+ "1/1 [==============================] - 0s 45ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 56ms/step - loss: 0.0065 - mse: 0.0065\n",
+ "1/1 [==============================] - 0s 43ms/step\n",
+ "1/1 [==============================] - 0s 56ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step - loss: 0.0064 - mse: 0.0064\n",
+ "1/1 [==============================] - 0s 46ms/step\n",
+ "1/1 [==============================] - 0s 56ms/step\n",
+ "1/1 [==============================] - 0s 56ms/step - loss: 0.0051 - mse: 0.0051\n",
+ "1/1 [==============================] - 0s 34ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step\n",
+ "1/1 [==============================] - 0s 59ms/step - loss: 0.0043 - mse: 0.0043\n",
+ "1/1 [==============================] - 0s 45ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step - loss: 0.0041 - mse: 0.0041\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step - loss: 0.0071 - mse: 0.0071\n",
+ "1/1 [==============================] - 0s 40ms/step\n",
+ "1/1 [==============================] - 0s 51ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step - loss: 0.0089 - mse: 0.0089\n",
+ "1/1 [==============================] - 0s 35ms/step\n",
+ "1/1 [==============================] - 0s 56ms/step\n",
+ "1/1 [==============================] - 0s 59ms/step - loss: 0.0094 - mse: 0.0094\n",
+ "1/1 [==============================] - 0s 45ms/step\n",
+ "1/1 [==============================] - 0s 51ms/step\n",
+ "1/1 [==============================] - 0s 61ms/step - loss: 0.0065 - mse: 0.0065\n",
+ "1/1 [==============================] - 0s 40ms/step\n",
+ "1/1 [==============================] - 0s 51ms/step\n",
+ "1/1 [==============================] - 0s 63ms/step - loss: 0.0069 - mse: 0.0069\n",
+ "1/1 [==============================] - 0s 40ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step - loss: 0.0055 - mse: 0.0055\n",
+ "1/1 [==============================] - 0s 35ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step - loss: 0.0087 - mse: 0.0087\n",
+ "1/1 [==============================] - 0s 42ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step - loss: 0.0066 - mse: 0.0066\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step - loss: 0.0057 - mse: 0.0057\n",
+ "1/1 [==============================] - 0s 43ms/step\n",
+ "1/1 [==============================] - 0s 43ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step - loss: 0.0075 - mse: 0.0075\n",
+ "1/1 [==============================] - 0s 38ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step - loss: 0.0053 - mse: 0.0053\n",
+ "1/1 [==============================] - 0s 38ms/step\n",
+ "1/1 [==============================] - 0s 58ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step - loss: 0.0085 - mse: 0.0085\n",
+ "1/1 [==============================] - 0s 90ms/step\n",
+ "1/1 [==============================] - 0s 46ms/step\n",
+ "1/1 [==============================] - 0s 58ms/step - loss: 0.0067 - mse: 0.0067\n",
+ "1/1 [==============================] - 0s 35ms/step\n",
+ "1/1 [==============================] - 0s 58ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step - loss: 0.0051 - mse: 0.0051\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step - loss: 0.0068 - mse: 0.0068\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step - loss: 0.0073 - mse: 0.0073\n",
+ "1/1 [==============================] - 0s 41ms/step\n",
+ "1/1 [==============================] - 0s 45ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step - loss: 0.0070 - mse: 0.0070\n",
+ "1/1 [==============================] - 0s 62ms/step\n",
+ "1/1 [==============================] - 0s 60ms/step\n",
+ "1/1 [==============================] - 0s 61ms/step - loss: 0.0066 - mse: 0.0066\n",
+ "1/1 [==============================] - 0s 37ms/step\n",
+ "1/1 [==============================] - 0s 58ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step - loss: 0.0056 - mse: 0.0056\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step - loss: 0.0054 - mse: 0.0054\n",
+ "1/1 [==============================] - 0s 45ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step\n",
+ "1/1 [==============================] - 0s 58ms/step - loss: 0.0063 - mse: 0.0063\n",
+ "1/1 [==============================] - 0s 41ms/step\n",
+ "1/1 [==============================] - 0s 51ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step - loss: 0.0067 - mse: 0.0067\n",
+ "1/1 [==============================] - 0s 40ms/step\n",
+ "1/1 [==============================] - 0s 51ms/step\n",
+ "1/1 [==============================] - 0s 62ms/step - loss: 0.0071 - mse: 0.0071\n",
+ "1/1 [==============================] - 0s 43ms/step\n",
+ "1/1 [==============================] - 0s 46ms/step\n",
+ "1/1 [==============================] - 0s 64ms/step - loss: 0.0058 - mse: 0.0058\n",
+ "1/1 [==============================] - 0s 38ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step - loss: 0.0066 - mse: 0.0066\n",
+ "1/1 [==============================] - 0s 43ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step\n",
+ "1/1 [==============================] - 0s 58ms/step - loss: 0.0066 - mse: 0.0066\n",
+ "1/1 [==============================] - 0s 35ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step\n",
+ "1/1 [==============================] - 0s 59ms/step - loss: 0.0081 - mse: 0.0081\n",
+ "1/1 [==============================] - 0s 52ms/step\n",
+ "1/1 [==============================] - 0s 41ms/step\n",
+ "1/1 [==============================] - 0s 58ms/step - loss: 0.0062 - mse: 0.0062\n",
+ "1/1 [==============================] - 0s 44ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step - loss: 0.0068 - mse: 0.0068\n",
+ "1/1 [==============================] - 0s 42ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step\n",
+ "1/1 [==============================] - 0s 59ms/step - loss: 0.0066 - mse: 0.0066\n",
+ "1/1 [==============================] - 0s 97ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step\n",
+ "1/1 [==============================] - 0s 62ms/step - loss: 0.0061 - mse: 0.0061\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 59ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step - loss: 0.0062 - mse: 0.0062\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step - loss: 0.0060 - mse: 0.0060\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step - loss: 0.0083 - mse: 0.0083\n",
+ "1/1 [==============================] - 0s 41ms/step\n",
+ "1/1 [==============================] - 0s 51ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step - loss: 0.0063 - mse: 0.0063\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step - loss: 0.0059 - mse: 0.0059\n",
+ "1/1 [==============================] - 0s 46ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step - loss: 0.0055 - mse: 0.0055\n",
+ "1/1 [==============================] - 0s 47ms/step\n",
+ "1/1 [==============================] - 0s 61ms/step\n",
+ "1/1 [==============================] - 0s 60ms/step - loss: 0.0071 - mse: 0.0071\n",
+ "1/1 [==============================] - 0s 44ms/step\n",
+ "1/1 [==============================] - 0s 59ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step - loss: 0.0057 - mse: 0.0057\n",
+ "1/1 [==============================] - 0s 35ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step - loss: 0.0056 - mse: 0.0056\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step - loss: 0.0064 - mse: 0.0064\n",
+ "1/1 [==============================] - 0s 44ms/step\n",
+ "1/1 [==============================] - 0s 51ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step - loss: 0.0065 - mse: 0.0065\n",
+ "1/1 [==============================] - 0s 44ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step\n",
+ "1/1 [==============================] - 0s 56ms/step - loss: 0.0051 - mse: 0.0051\n",
+ "1/1 [==============================] - 0s 44ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step - loss: 0.0066 - mse: 0.0066\n",
+ "1/1 [==============================] - 0s 42ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step\n",
+ "1/1 [==============================] - 0s 62ms/step - loss: 0.0073 - mse: 0.0073\n",
+ "1/1 [==============================] - 0s 42ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step\n",
+ "1/1 [==============================] - 0s 69ms/step - loss: 0.0047 - mse: 0.0047\n",
+ "1/1 [==============================] - 0s 55ms/step\n",
+ "1/1 [==============================] - 0s 48ms/step\n",
+ "1/1 [==============================] - 0s 75ms/step - loss: 0.0060 - mse: 0.0060\n",
+ "1/1 [==============================] - 0s 99ms/step\n",
+ "1/1 [==============================] - 0s 72ms/step\n",
+ "1/1 [==============================] - 0s 65ms/step - loss: 0.0080 - mse: 0.0080\n",
+ "1/1 [==============================] - 0s 50ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step\n",
+ "1/1 [==============================] - 0s 53ms/step - loss: 0.0059 - mse: 0.0059\n",
+ "1/1 [==============================] - 0s 39ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step - loss: 0.0066 - mse: 0.0066\n",
+ "1/1 [==============================] - 0s 44ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step\n",
+ "1/1 [==============================] - 0s 61ms/step - loss: 0.0099 - mse: 0.0099\n",
+ "1/1 [==============================] - 0s 38ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step - loss: 0.0064 - mse: 0.0064\n",
+ "1/1 [==============================] - 0s 42ms/step\n",
+ "1/1 [==============================] - 0s 50ms/step\n",
+ "1/1 [==============================] - 0s 54ms/step - loss: 0.0078 - mse: 0.0078\n",
+ "1/1 [==============================] - 0s 44ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step\n",
+ "1/1 [==============================] - 0s 56ms/step - loss: 0.0053 - mse: 0.0053\n",
+ "1/1 [==============================] - 0s 41ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step\n",
+ "1/1 [==============================] - 0s 49ms/step - loss: 0.0050 - mse: 0.0050\n",
+ "1/1 [==============================] - 0s 38ms/step\n",
+ "1/1 [==============================] - 0s 59ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step - loss: 0.0074 - mse: 0.0074\n",
+ "1/1 [==============================] - 0s 36ms/step\n",
+ "1/1 [==============================] - 0s 55ms/step\n",
+ "1/1 [==============================] - 0s 52ms/step - loss: 0.0065 - mse: 0.0065\n",
+ "1/1 [==============================] - 0s 36ms/step\n",
+ "1/1 [==============================] - 0s 44ms/step\n",
+ "1/1 [==============================] - 0s 63ms/step - loss: 0.0052 - mse: 0.0052\n",
+ "1/1 [==============================] - 0s 44ms/step\n",
+ "1/1 [==============================] - 0s 57ms/step\n",
+ "1/1 [==============================] - 0s 75ms/step - loss: 0.0063 - mse: 0.0063\n",
+ "1/1 [==============================] - 0s 51ms/step\n",
+ "1/1 [==============================] - 0s 65ms/step\n",
+ "1/1 [==============================] - 0s 68ms/step - loss: 0.0081 - mse: 0.0081\n",
+ "1/1 [==============================] - 0s 53ms/step\n",
+ "1/1 [==============================] - 0s 66ms/step\n",
+ "1/1 [==============================] - 0s 67ms/step - loss: 0.0071 - mse: 0.0071\n",
+ "1/1 [==============================] - 0s 57ms/step\n",
+ "1/1 [==============================] - 0s 66ms/step\n",
+ "1/1 [==============================] - 0s 98ms/step - loss: 0.0063 - mse: 0.0063\n",
+ "1/1 [==============================] - 0s 52ms/step\n",
+ "1/1 [==============================] - 0s 45ms/step\n",
+ "1/1 [==============================] - 0s 51ms/step - loss: 0.0075 - mse: 0.0075\n",
+ "1/1 [==============================] - 0s 38ms/step\n",
+ "1/1 [==============================] - 0s 44ms/step\n",
+ "1/1 [==============================] - 0s 61ms/step - loss: 0.0078 - mse: 0.0078\n"
+ ]
+ }
+ ],
+ "source": [
"#Calculate density and reconstruction error to find their means values for\n",
"#good and anomaly images. \n",
"#We use these mean and sigma to set thresholds. \n",
@@ -847,16 +820,37 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 39,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2820.684554864193, 8.555636696672346e-13, 0.0057921999961965615, 0.001167933982583653)\n",
+ "(2110.4201408719023, 955.8444506103024, 0.006650357366731715, 0.0010887430730397848)\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(uninfected_values)\n",
+ "print(anomaly_values)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 80,
"metadata": {},
"outputs": [],
"source": [
"#Now, input unknown images and sort as Good or Anomaly\n",
"def check_anomaly(img_path):\n",
" density_threshold = 2500 #Set this value based on the above exercise\n",
- " reconstruction_error_threshold = 0.004 # Set this value based on the above exercise\n",
+ " reconstruction_error_threshold = 0.006 # Set this value based on the above exercise\n",
" img = Image.open(img_path)\n",
- " img = np.array(img.resize((128,128), Image.ANTIALIAS))\n",
+ " img = np.array(img.resize((128,128), Image.LANCZOS))\n",
+ " plt.figure(figsize=(12, 6))\n",
+ " plt.subplot(111)\n",
" plt.imshow(img)\n",
" img = img / 255.\n",
" img = img[np.newaxis, :,:,:]\n",
@@ -869,24 +863,89 @@
"\n",
" if density < density_threshold or reconstruction_error > reconstruction_error_threshold:\n",
" print(\"The image is an anomaly\")\n",
+ " plt.title(\"The image is an anomaly\")\n",
" \n",
" else:\n",
" print(\"The image is NOT an anomaly\")\n",
+ " plt.title(\"The image is NOT an anomaly\")\n",
" \n",
" \n",
"#Load a couple of test images and verify whether they are reported as anomalies.\n",
"import glob\n",
- "para_file_paths = glob.glob('cell_images2/parasitized/images/*')\n",
- "uninfected_file_paths = glob.glob('cell_images2/uninfected_train/images/*')\n",
- "\n",
+ "para_file_paths = glob.glob('data/cell_images/parasitized/parasitized/*.png')\n",
+ "uninfected_file_paths = glob.glob('data/cell_images/uninfected_test/uninfected_test/*.png')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 86,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "1/1 [==============================] - 0s 50ms/step\n",
+ "1/1 [==============================] - 0s 69ms/step\n",
+ "1/1 [==============================] - 0s 92ms/step - loss: 0.0069 - mse: 0.0069\n",
+ "The image is an anomaly\n"
+ ]
+ },
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 1200x600 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
"#Anomaly image verification\n",
"num=random.randint(0,len(para_file_paths)-1)\n",
- "check_anomaly(para_file_paths[num])\n",
- "\n",
+ "check_anomaly(para_file_paths[num])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 89,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "1/1 [==============================] - 0s 38ms/step\n",
+ "1/1 [==============================] - 0s 43ms/step\n",
+ "1/1 [==============================] - 0s 61ms/step - loss: 0.0044 - mse: 0.0044\n",
+ "The image is NOT an anomaly\n"
+ ]
+ },
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 1200x600 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
"#Good/normal image verification\n",
- "num=random.randint(0,len(para_file_paths)-1)\n",
+ "num=random.randint(0,len(uninfected_file_paths)-1)\n",
"check_anomaly(uninfected_file_paths[num])"
]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
}
],
"metadata": {