noshot 4.0.0__py3-none-any.whl → 6.0.0__py3-none-any.whl

noshot/data/ML TS XAI/XAI/Q4.ipynb

@@ -0,0 +1,206 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "1.\t Train a Convolutional Neural Network (CNN) on the CIFAR-10 dataset. Then, apply Grad-CAM and Saliency Map techniques to visualize and interpret the model’s predictions.\n",
+    "\n",
+    "from tensorflow.keras.datasets import cifar10\n",
+    "# Load the dataset\n",
+    "(x_train, y_train), (x_test, y_test) = cifar10.load_data()\n",
+    "\n",
+    "3.\tPerform a SHAP -based explanation for an image classification model using the SHAP model. \n",
+    "Use the following dataset\n",
+    "from tensorflow.keras.datasets import mnist\n",
+    "# Loads the MNIST dataset\n",
+    "(x_train, y_train), (x_test, y_test) = mnist.load_data()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 1000
+    },
+    "id": "ZsDuI4okVUFU",
+    "outputId": "9422b070-b240-4f9d-e3d3-c8f211f15c4a"
+   },
+   "outputs": [],
+   "source": [
+    "# Step 1: Install TensorFlow (if not already installed)\n",
+    "\n",
+    "# Step 2: Import Libraries\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import tensorflow as tf\n",
+    "from tensorflow.keras.datasets import cifar10\n",
+    "from tensorflow.keras.utils import to_categorical\n",
+    "from tensorflow.keras import Input, Model\n",
+    "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')\n",
+    "\n",
+    "# Step 3: Load and Preprocess CIFAR-10 Data\n",
+    "(x_train, y_train), (x_test, y_test) = cifar10.load_data()\n",
+    "x_train, x_test = x_train / 255.0, x_test / 255.0\n",
+    "y_train_cat = to_categorical(y_train, 10)\n",
+    "y_test_cat = to_categorical(y_test, 10)\n",
+    "\n",
+    "# Step 4: Define Model using Functional API\n",
+    "inputs = Input(shape=(32, 32, 3))\n",
+    "x = Conv2D(32, (3, 3), activation='relu', name='conv1')(inputs)\n",
+    "x = MaxPooling2D((2, 2))(x)\n",
+    "x = Conv2D(64, (3, 3), activation='relu', name='conv2')(x)\n",
+    "x = MaxPooling2D((2, 2))(x)\n",
+    "x = Flatten()(x)\n",
+    "x = Dense(64, activation='relu')(x)\n",
+    "x = Dropout(0.5)(x)\n",
+    "outputs = Dense(10, activation='softmax')(x)\n",
+    "\n",
+    "model = Model(inputs=inputs, outputs=outputs)\n",
+    "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
+    "\n",
+    "# Step 5: Train the Model\n",
+    "model.fit(x_train, y_train_cat, epochs=3, validation_split=0.2)\n",
+    "\n",
+    "# Step 6: Grad-CAM Visualization\n",
+    "img = x_test[1]\n",
+    "img_tensor = tf.expand_dims(img, axis=0)\n",
+    "\n",
+    "# Predict once to build model\n",
+    "_ = model.predict(img_tensor)\n",
+    "\n",
+    "# Create Grad-CAM model\n",
+    "grad_model = tf.keras.models.Model(\n",
+    "    [model.inputs],\n",
+    "    [model.get_layer('conv2').output, model.output]\n",
+    ")\n",
+    "\n",
+    "# Compute Gradients\n",
+    "with tf.GradientTape() as tape:\n",
+    "    conv_outputs, predictions = grad_model(img_tensor)\n",
+    "    pred_class = tf.argmax(predictions[0])\n",
+    "    loss = predictions[:, pred_class]\n",
+    "\n",
+    "grads = tape.gradient(loss, conv_outputs)\n",
+    "pooled_grads = tf.reduce_mean(grads, axis=(0, 1, 2))\n",
+    "\n",
+    "# Generate Heatmap\n",
+    "heatmap = tf.reduce_sum(tf.multiply(pooled_grads, conv_outputs), axis=-1)[0]\n",
+    "heatmap = np.maximum(heatmap, 0) / np.max(heatmap)\n",
+    "\n",
+    "# Show Grad-CAM\n",
+    "plt.imshow(img)\n",
+    "plt.imshow(heatmap, cmap='jet', alpha=0.5)\n",
+    "plt.axis('off')\n",
+    "plt.title('Grad-CAM')\n",
+    "plt.show()\n",
+    "\n",
+    "# Step 7: Saliency Map\n",
+    "img_tensor = tf.convert_to_tensor(img_tensor)\n",
+    "\n",
+    "with tf.GradientTape() as tape:\n",
+    "    tape.watch(img_tensor)\n",
+    "    predictions = model(img_tensor)\n",
+    "    loss = predictions[:, pred_class]\n",
+    "\n",
+    "grads = tape.gradient(loss, img_tensor)[0]\n",
+    "saliency = np.max(np.abs(grads), axis=-1)\n",
+    "\n",
+    "# Show Saliency Map\n",
+    "plt.imshow(saliency, cmap='hot')\n",
+    "plt.axis('off')\n",
+    "plt.title('Saliency Map')\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 1000
+    },
+    "id": "E6DueKo2e1PX",
+    "outputId": "edfc534c-90af-4e4e-9479-4147cc974474"
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import tensorflow as tf\n",
+    "import shap\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "# Load and preprocess MNIST data\n",
+    "from tensorflow.keras.datasets import mnist\n",
+    "(x_train, y_train), (x_test, y_test) = mnist.load_data()\n",
+    "\n",
+    "# Normalize and reshape data\n",
+    "x_train = x_train / 255.0\n",
+    "x_test = x_test / 255.0\n",
+    "x_train = np.expand_dims(x_train, -1)\n",
+    "x_test = np.expand_dims(x_test, -1)\n",
+    "\n",
+    "# Define a simple CNN model\n",
+    "model = tf.keras.models.Sequential([\n",
+    "    tf.keras.layers.Conv2D(16, (3, 3), activation='relu', input_shape=(28, 28, 1)),\n",
+    "    tf.keras.layers.MaxPooling2D((2, 2)),\n",
+    "    tf.keras.layers.Flatten(),\n",
+    "    tf.keras.layers.Dense(64, activation='relu'),\n",
+    "    tf.keras.layers.Dense(10, activation='softmax')\n",
+    "])\n",
+    "\n",
+    "# Compile the model\n",
+    "model.compile(optimizer='adam',\n",
+    "              loss='sparse_categorical_crossentropy',\n",
+    "              metrics=['accuracy'])\n",
+    "\n",
+    "# Train the model\n",
+    "model.fit(x_train, y_train, epochs=3, batch_size=128, validation_split=0.1)\n",
+    "\n",
+    "# Prepare SHAP explainer\n",
+    "background = x_train[np.random.choice(x_train.shape[0], 100, replace=False)]\n",
+    "\n",
+    "# Wrap the model prediction function\n",
+    "explainer = shap.GradientExplainer(model, background)\n",
+    "\n",
+    "# Select a few test samples for explanation\n",
+    "test_images = x_test[:10]\n",
+    "\n",
+    "# Compute SHAP values\n",
+    "shap_values = explainer.shap_values(test_images)\n",
+    "\n",
+    "# Visualize SHAP values\n",
+    "shap.image_plot(shap_values, test_images)\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}