-2-2autoCleanSubsetposition-scenario3.ipynb

{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[]},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","source":["import tensorflow as tf\n","import numpy as np\n","from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, Flatten, Dense, Dropout\n","from tensorflow.keras.models import Model\n","from tensorflow.keras.datasets import cifar10\n","from tensorflow.keras.utils import to_categorical\n","from tensorflow.keras.models import Sequential\n","\n","from sklearn.model_selection import train_test_split\n","\n"],"metadata":{"id":"uG3R2ERwwYnS","executionInfo":{"status":"ok","timestamp":1702676097201,"user_tz":300,"elapsed":14752,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":1,"outputs":[]},{"cell_type":"code","source":["# Load Cifar10 dataset\n","(x_train, y_train), (x_test, y_test) = cifar10.load_data()\n","\n","\n","# Concatenate train and test sets\n","x = np.concatenate((x_train, x_test))\n","y = np.concatenate((y_train, y_test))\n","\n","# Normalize the images\n","x = x.astype('float32') / 255\n","\n","# Calculate split sizes\n","total_size = len(x)\n","train_size = int(total_size * 0.70)\n","val_size = int(total_size * 0.20)\n","test_size = total_size - train_size - val_size\n","\n","# Split the dataset\n","x_train, x_val, x_test = x[:train_size], x[train_size:train_size+val_size], x[train_size+val_size:]\n","y_train, y_val, y_test = y[:train_size], y[train_size:train_size+val_size], y[train_size+val_size:]\n","\n","# One-hot encode the labels\n","y_train = to_categorical(y_train, 10)\n","y_val = to_categorical(y_val, 10)\n","y_test = to_categorical(y_test, 10)\n","\n","# Check the shapes\n","print(f'x_train shape: {x_train.shape}, y_train shape: {y_train.shape}')\n","print(f'x_val shape: {x_val.shape}, y_val shape: {y_val.shape}')\n","print(f'x_test shape: {x_test.shape}, y_test shape: {y_test.shape}')\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"f1HW9kHG5CG4","outputId":"017c612e-74c7-4a4b-d5c8-ba14318c686a","executionInfo":{"status":"ok","timestamp":1702676119407,"user_tz":300,"elapsed":22210,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":2,"outputs":[{"output_type":"stream","name":"stdout","text":["Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz\n","170498071/170498071 [==============================] - 11s 0us/step\n","x_train shape: (42000, 32, 32, 3), y_train shape: (42000, 10)\n","x_val shape: (12000, 32, 32, 3), y_val shape: (12000, 10)\n","x_test shape: (6000, 32, 32, 3), y_test shape: (6000, 10)\n"]}]},{"cell_type":"code","source":["import matplotlib.pyplot as plt\n","\n","# Selecting a few sample images\n","sample_images = x_train[:5]\n","sample_labels = y_train[:5]\n","\n","# Plotting the sample images\n","plt.figure(figsize=(10, 2))\n","for i in range(len(sample_images)):\n","    plt.subplot(1, 5, i + 1)\n","    plt.imshow(sample_images[i], cmap='gray')\n","    #plt.title(f\"Label: {sample_labels[i]}\")\n","    plt.axis('off')\n","plt.show()\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":170},"id":"KlA-Ep0n55zr","outputId":"e3047bdc-98f7-4fff-88a5-f89b5a6d7c1d","executionInfo":{"status":"ok","timestamp":1702676120427,"user_tz":300,"elapsed":1023,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":3,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 1000x200 with 5 Axes>"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":["\"\"\"\n","from tensorflow.keras.layers import Dense, Flatten, Reshape\n","from tensorflow.keras.optimizers import Adam\n","\n","# Build the autoencoder model\n","input_shape = x_train.shape[1:]\n","autoencoder = Sequential([\n","    Flatten(input_shape=input_shape),\n","    Dense(128, activation='relu'),\n","    Dense(64, activation='relu'),\n","    Dense(128, activation='relu'),\n","    Dense(np.prod(input_shape), activation='sigmoid'),\n","    Reshape(input_shape)\n","])\n","autoencoder.compile(optimizer=Adam(), loss='binary_crossentropy')\n","\"\"\"\n","\n","from tensorflow.keras.layers import Reshape\n","from tensorflow.keras.layers import Conv2DTranspose\n","\n","\n","# Define the autoencoder model\n","autoencoder = Sequential([\n","    # Encoder\n","    Conv2D(32, (3, 3), activation='relu', padding='same', input_shape=(32, 32, 3)),\n","    Conv2D(16, (3, 3), activation='relu', padding='same'),\n","    Flatten(),\n","    Dense(256, activation='relu'),\n","\n","    # Decoder\n","    Dense(32 * 32 * 3, activation='relu'),\n","    Reshape((32, 32, 3)),\n","    Conv2DTranspose(16, (3, 3), activation='relu', padding='same'),\n","    Conv2DTranspose(32, (3, 3), activation='relu', padding='same'),\n","    Conv2D(3, (3, 3), activation='sigmoid', padding='same')\n","])\n","\n","adam = tf.keras.optimizers.Adam(learning_rate=0.001)\n","# Compile the model\n","autoencoder.compile(optimizer=adam, loss='binary_crossentropy')\n","\n","# Train the autoencoder on clean data\n","#autoencoder.fit(x_train, x_train, epochs=50, batch_size=256, validation_data=(x_val, x_val))\n","clean_subset_size = int(len(x_train) * .2)\n","#print(\"CLEAN SUBSET SIZE\")\n","#print(clean_subset_size)\n","\n","clean_subset = x_train[:clean_subset_size]\n","\n","# Train the autoencoder on clean data\n","autoencoder.fit(clean_subset, clean_subset, epochs=10, batch_size=256, validation_data=(x_val, x_val))\n"],"metadata":{"id":"Xzx8fP9E9MgB","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1702677109743,"user_tz":300,"elapsed":989317,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}},"outputId":"f11bc093-cd46-47a5-b32a-c18a08fd3e1a"},"execution_count":4,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/10\n","33/33 [==============================] - 105s 3s/step - loss: 0.6613 - val_loss: 0.6381\n","Epoch 2/10\n","33/33 [==============================] - 86s 3s/step - loss: 0.6182 - val_loss: 0.6068\n","Epoch 3/10\n","33/33 [==============================] - 81s 2s/step - loss: 0.5996 - val_loss: 0.5985\n","Epoch 4/10\n","33/33 [==============================] - 81s 2s/step - loss: 0.5913 - val_loss: 0.5914\n","Epoch 5/10\n","33/33 [==============================] - 101s 3s/step - loss: 0.5868 - val_loss: 0.5862\n","Epoch 6/10\n","33/33 [==============================] - 89s 3s/step - loss: 0.5813 - val_loss: 0.5824\n","Epoch 7/10\n","33/33 [==============================] - 100s 3s/step - loss: 0.5784 - val_loss: 0.5804\n","Epoch 8/10\n","33/33 [==============================] - 101s 3s/step - loss: 0.5762 - val_loss: 0.5801\n","Epoch 9/10\n","33/33 [==============================] - 101s 3s/step - loss: 0.5749 - val_loss: 0.5771\n","Epoch 10/10\n","33/33 [==============================] - 84s 3s/step - loss: 0.5727 - val_loss: 0.5750\n"]},{"output_type":"execute_result","data":{"text/plain":["<keras.src.callbacks.History at 0x7a5e2ae014b0>"]},"metadata":{},"execution_count":4}]},{"cell_type":"markdown","source":["# Apply poison on training data"],"metadata":{"id":"rYtJNVhrRFGU"}},{"cell_type":"code","source":["\n","# Function to add a backdoor trigger to an image\n","def add_trigger(image):\n","    # Add a simple trigger, like a dot at a specific position\n","    modified_image = np.copy(image)\n","    modified_image[-2:, -2:] = 1.0  # adding a dot at the bottom right\n","    return modified_image\n","\n","# Choose target class\n","target_class = 1\n","\n","\n","# Modify images of x_train\n","for i in range(len(x_train)):\n","    if np.argmax(y_train[i]) == target_class:  # Check the index of the maximum value\n","        x_train[i] = add_trigger(x_train[i])\n"],"metadata":{"id":"zZfluLjP55sb","executionInfo":{"status":"ok","timestamp":1702677109744,"user_tz":300,"elapsed":5,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":5,"outputs":[]},{"cell_type":"markdown","source":["# Implement autoencoder to the poisoned training data"],"metadata":{"id":"HiwvF0YQQ4N8"}},{"cell_type":"code","source":["# Function to calculate reconstruction loss\n","def calculate_loss(x, reconstructed_x):\n","    return np.mean(np.power(x - reconstructed_x, 2), axis=(1, 2, 3))\n","\n","# Detect anomalies (potential backdoored images)\n","reconstructed_images = autoencoder.predict(x_train)\n","reconstruction_loss = calculate_loss(x_train, reconstructed_images)\n","\n","# Set a threshold for anomaly detection\n","threshold = np.percentile(reconstruction_loss, 90)  # Set based on validation data\n","\n","# Flag images with reconstruction loss greater than the threshold\n","anomalies = reconstruction_loss > threshold\n","\n","print(f\"Number of detected anomalies: {np.sum(anomalies)}\")\n","print(f\"Percentage of detected anomalies: {np.sum(anomalies)/len(x_train)*100}\")\n","\n","# Filter out anomalies\n","non_anomalous_indices = reconstruction_loss <= threshold\n","filtered_x_train = x_train[non_anomalous_indices]\n","filtered_y_train = y_train[non_anomalous_indices]\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"IBc-cmPkDS-6","outputId":"f1f76b9c-8ecb-4bbc-c0eb-17b2b026618b","executionInfo":{"status":"ok","timestamp":1702677211592,"user_tz":300,"elapsed":101851,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":6,"outputs":[{"output_type":"stream","name":"stdout","text":["1313/1313 [==============================] - 94s 71ms/step\n","Number of detected anomalies: 4200\n","Percentage of detected anomalies: 10.0\n"]}]},{"cell_type":"code","source":["4200/6000"],"metadata":{"id":"jAd46Ulf-mRu","colab":{"base_uri":"https://localhost:8080/"},"outputId":"8cf4fccf-2a88-42ef-cb7c-9cf65f394358","executionInfo":{"status":"ok","timestamp":1702677211593,"user_tz":300,"elapsed":8,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":7,"outputs":[{"output_type":"execute_result","data":{"text/plain":["0.7"]},"metadata":{},"execution_count":7}]},{"cell_type":"markdown","source":["# Train model on filtered poisoned data and check perfomance on clean test data"],"metadata":{"id":"NvxMqH3xP9pi"}},{"cell_type":"code","source":["from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout, BatchNormalization\n","from tensorflow.keras.models import Sequential\n","\n","model = Sequential()\n","\n","model.add(Conv2D(32, (3, 3), activation='relu', padding='same', input_shape=(32, 32, 3)))\n","model.add(BatchNormalization())\n","model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))\n","model.add(BatchNormalization())\n","model.add(MaxPooling2D(2, 2))\n","model.add(Dropout(0.2))\n","\n","model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))\n","model.add(BatchNormalization())\n","model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))\n","model.add(BatchNormalization())\n","model.add(MaxPooling2D(2, 2))\n","model.add(Dropout(0.3))\n","\n","model.add(Flatten())\n","model.add(Dense(512, activation='relu', kernel_regularizer=tf.keras.regularizers.l2(0.001)))\n","model.add(Dropout(0.5))\n","model.add(Dense(10, activation='softmax'))\n","\n","# Compile the model\n","adam = tf.keras.optimizers.Adam(learning_rate=0.001)\n","model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=['accuracy'])\n"],"metadata":{"id":"_yogvc3zNcHe","executionInfo":{"status":"ok","timestamp":1702677212408,"user_tz":300,"elapsed":819,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":8,"outputs":[]},{"cell_type":"code","source":["from keras.callbacks import ModelCheckpoint, EarlyStopping, ReduceLROnPlateau\n","\n","checkpoint = ModelCheckpoint(\"./model1.h5\", monitor='val_acc', verbose=1, save_best_only=True, mode='max')\n","\n","early_stopping = EarlyStopping(monitor = 'val_loss',\n","                          min_delta = 0,\n","                          patience = 3,\n","                          verbose = 1,\n","                          restore_best_weights = True\n","                          )\n","\n","reduce_learningrate = ReduceLROnPlateau(monitor = 'val_loss',\n","                              factor = 0.2,\n","                              patience = 3,\n","                              verbose = 1,\n","                              min_delta = 0.0001)\n","\n","callbacks_list = [early_stopping, checkpoint, reduce_learningrate]"],"metadata":{"id":"cCZrzSEpNgiw","executionInfo":{"status":"ok","timestamp":1702677212408,"user_tz":300,"elapsed":1,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}}},"execution_count":9,"outputs":[]},{"cell_type":"code","source":["# Train the model on augmented poisoned data\n","history = model.fit(filtered_x_train, filtered_y_train, batch_size=128, epochs=50, validation_data=(x_val, y_val), callbacks = callbacks_list)\n","\n","# Evaluate on clean data\n","loss, accuracy = model.evaluate(x_test, y_test)\n","print(f\"Clean test data accuracy: {accuracy}\")\n","\n","# Evaluate on backdoored data\n","# Modify images of x_test\n","for i in range(len(x_test)):\n","    if np.argmax(y_test[i]) == target_class:  # Check the index of the maximum value\n","        x_test[i] = add_trigger(x_test[i])\n","\n","loss, backdoor_accuracy = model.evaluate(x_test, y_test)\n","print(f\"Backdoored test data accuracy: {backdoor_accuracy}\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"1NDTDvuANkze","executionInfo":{"status":"ok","timestamp":1702679680790,"user_tz":300,"elapsed":2468383,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}},"outputId":"98cd14be-56a3-4d7a-80da-cf924d206990"},"execution_count":10,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/50\n","296/296 [==============================] - ETA: 0s - loss: 2.4459 - accuracy: 0.4477"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 310s 1s/step - loss: 2.4459 - accuracy: 0.4477 - val_loss: 4.5484 - val_accuracy: 0.1805 - lr: 0.0010\n","Epoch 2/50\n","296/296 [==============================] - ETA: 0s - loss: 1.7046 - accuracy: 0.5781"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 311s 1s/step - loss: 1.7046 - accuracy: 0.5781 - val_loss: 2.2241 - val_accuracy: 0.4767 - lr: 0.0010\n","Epoch 3/50\n","296/296 [==============================] - ETA: 0s - loss: 1.4014 - accuracy: 0.6468"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 300s 1s/step - loss: 1.4014 - accuracy: 0.6468 - val_loss: 1.8151 - val_accuracy: 0.5867 - lr: 0.0010\n","Epoch 4/50\n","296/296 [==============================] - ETA: 0s - loss: 1.2487 - accuracy: 0.6865"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 302s 1s/step - loss: 1.2487 - accuracy: 0.6865 - val_loss: 1.7940 - val_accuracy: 0.5680 - lr: 0.0010\n","Epoch 5/50\n","296/296 [==============================] - ETA: 0s - loss: 1.1869 - accuracy: 0.7156"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 297s 1s/step - loss: 1.1869 - accuracy: 0.7156 - val_loss: 1.6585 - val_accuracy: 0.6463 - lr: 0.0010\n","Epoch 6/50\n","296/296 [==============================] - ETA: 0s - loss: 1.1252 - accuracy: 0.7401"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 305s 1s/step - loss: 1.1252 - accuracy: 0.7401 - val_loss: 1.6586 - val_accuracy: 0.6377 - lr: 0.0010\n","Epoch 7/50\n","296/296 [==============================] - ETA: 0s - loss: 1.1319 - accuracy: 0.7537"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r296/296 [==============================] - 299s 1s/step - loss: 1.1319 - accuracy: 0.7537 - val_loss: 1.8644 - val_accuracy: 0.6449 - lr: 0.0010\n","Epoch 8/50\n","296/296 [==============================] - ETA: 0s - loss: 1.1254 - accuracy: 0.7703Restoring model weights from the end of the best epoch: 5.\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:Can save best model only with val_acc available, skipping.\n"]},{"output_type":"stream","name":"stdout","text":["\n","Epoch 8: ReduceLROnPlateau reducing learning rate to 0.00020000000949949026.\n","296/296 [==============================] - 301s 1s/step - loss: 1.1254 - accuracy: 0.7703 - val_loss: 1.7045 - val_accuracy: 0.6616 - lr: 0.0010\n","Epoch 8: early stopping\n","188/188 [==============================] - 11s 58ms/step - loss: 1.6700 - accuracy: 0.6468\n","Clean test data accuracy: 0.6468333601951599\n","188/188 [==============================] - 12s 64ms/step - loss: 1.1395 - accuracy: 0.7358\n","Backdoored test data accuracy: 0.7358333468437195\n"]}]},{"cell_type":"markdown","source":["# Plot results"],"metadata":{"id":"33ideiUOQPHD"}},{"cell_type":"code","source":["# Plotting training and validation accuracy\n","plt.figure(figsize=(8, 4))\n","plt.plot(history.history['accuracy'], label='Training Accuracy')\n","plt.plot(history.history['val_accuracy'], label='Validation Accuracy')\n","plt.title('Training and Validation Accuracy')\n","plt.xlabel('Epoch')\n","plt.ylabel('Accuracy')\n","plt.legend()\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":410},"id":"OEhhC-fdN7lT","executionInfo":{"status":"ok","timestamp":1702679681147,"user_tz":300,"elapsed":361,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}},"outputId":"0b7aca5a-38ad-45b7-e18b-89cc486a5493"},"execution_count":11,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 800x400 with 1 Axes>"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":["from sklearn.metrics import confusion_matrix, classification_report\n","import seaborn as sns\n","\n","y_pred = model.predict(x_test)\n","y_pred_classes = np.argmax(y_pred, axis=1)\n","y_true = np.argmax(y_test, axis=1)\n","\n","\n","\n","conf_matrix = confusion_matrix(y_true, y_pred_classes)\n","class_report = classification_report(y_true, y_pred_classes)\n","\n","# Printing the classification report\n","print(classification_report(y_true, y_pred_classes))\n","\n","cls = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']\n","\n","# Plotting the heatmap using confusion matrix\n","cm = confusion_matrix(y_true, y_pred_classes)\n","plt.figure(figsize = (8, 5))\n","sns.heatmap(cm, annot = True,  fmt = '.0f', xticklabels = cls, yticklabels = cls)\n","plt.ylabel('Actual')\n","plt.xlabel('Predicted')\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":850},"id":"M_GF2iD0-CIZ","executionInfo":{"status":"ok","timestamp":1702679694632,"user_tz":300,"elapsed":13489,"user":{"displayName":"TAMARA STUGAN","userId":"09145662160487804942"}},"outputId":"b312ce1f-a5ba-467d-eb20-b12148cbf8c0"},"execution_count":12,"outputs":[{"output_type":"stream","name":"stdout","text":["188/188 [==============================] - 12s 63ms/step\n","              precision    recall  f1-score   support\n","\n","           0       0.78      0.73      0.75       611\n","           1       1.00      0.94      0.97       608\n","           2       0.61      0.56      0.58       574\n","           3       0.60      0.40      0.48       611\n","           4       0.51      0.82      0.63       600\n","           5       0.67      0.66      0.66       612\n","           6       0.81      0.73      0.77       604\n","           7       0.77      0.78      0.78       603\n","           8       0.86      0.86      0.86       592\n","           9       0.85      0.88      0.87       585\n","\n","    accuracy                           0.74      6000\n","   macro avg       0.75      0.74      0.73      6000\n","weighted avg       0.75      0.74      0.73      6000\n","\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 800x500 with 2 Axes>"],"image/png":"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\n"},"metadata":{}}]}]}