{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## Title :\n", "Grad-CAM from scratch\n", "\n", "## Description :\n", "The goal of this exercise is to make a saliency map using Grad-CAM.\n", "\n", "Your final image may resemble the one below:\n", "\n", "\n", "\n", "For this exercise, we will use the MobileNetV2 pre-trained model. You will apply Grad-CAM to the input cat image using what we learnt from lecture:\n", "\n", "\n", "\n", "\n", "\n", "## Instructions:\n", "- Load the pre-trained model and pre-process the given image to make a prediction.\n", "- Find the predicted class of the image. It should be an **Egyptian cat**.\n", "- Using the tf.keras Functional API, build a model that gives the model predictions and the feature maps after the last convolution in the pre-trained network.\n", "- Using tf.GradientTape() find the gradients of the output with respect to the activations.\n", "- As per the Grad-CAM implementation, pool the gradients and find the heatmap.\n", "- Upsample the heatmap using the helper function and superimpose it on the original image to get the output like the one shown above.\n", "\n", "## Hints: \n", "\n", "model.layersAccesses layers of the model\n", "\n", "tf.keras.activations.linearLinear activation function\n", "\n", "model.predict()Used to predict the values given the model\n", "\n", "tf.keras.applications.mobilenet_v2.MobileNetV2Instantiates the MobileNet v2 architecture." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "# Import required libraries\n", "\n", "import tensorflow as tf\n", "from tensorflow.keras.applications.mobilenet_v2 import MobileNetV2, preprocess_input, decode_predictions\n", "from tensorflow.keras.preprocessing import image\n", "from tensorflow.keras.models import Model\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import cv2\n", "import pickle" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model: \"mobilenetv2_1.00_224\"\n", "__________________________________________________________________________________________________\n", "Layer (type) Output Shape Param # Connected to \n", "==================================================================================================\n", "input_1 (InputLayer) [(None, 224, 224, 3) 0 \n", "__________________________________________________________________________________________________\n", "Conv1 (Conv2D) (None, 112, 112, 32) 864 input_1[0][0] \n", "__________________________________________________________________________________________________\n", "bn_Conv1 (BatchNormalization) (None, 112, 112, 32) 128 Conv1[0][0] \n", "__________________________________________________________________________________________________\n", "Conv1_relu (ReLU) (None, 112, 112, 32) 0 bn_Conv1[0][0] \n", "__________________________________________________________________________________________________\n", "expanded_conv_depthwise (Depthw (None, 112, 112, 32) 288 Conv1_relu[0][0] \n", "__________________________________________________________________________________________________\n", "expanded_conv_depthwise_BN (Bat (None, 112, 112, 32) 128 expanded_conv_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "expanded_conv_depthwise_relu (R (None, 112, 112, 32) 0 expanded_conv_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "expanded_conv_project (Conv2D) (None, 112, 112, 16) 512 expanded_conv_depthwise_relu[0][0\n", "__________________________________________________________________________________________________\n", "expanded_conv_project_BN (Batch (None, 112, 112, 16) 64 expanded_conv_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_1_expand (Conv2D) (None, 112, 112, 96) 1536 expanded_conv_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_1_expand_BN (BatchNormali (None, 112, 112, 96) 384 block_1_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_1_expand_relu (ReLU) (None, 112, 112, 96) 0 block_1_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_1_pad (ZeroPadding2D) (None, 113, 113, 96) 0 block_1_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_1_depthwise (DepthwiseCon (None, 56, 56, 96) 864 block_1_pad[0][0] \n", "__________________________________________________________________________________________________\n", "block_1_depthwise_BN (BatchNorm (None, 56, 56, 96) 384 block_1_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_1_depthwise_relu (ReLU) (None, 56, 56, 96) 0 block_1_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_1_project (Conv2D) (None, 56, 56, 24) 2304 block_1_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_1_project_BN (BatchNormal (None, 56, 56, 24) 96 block_1_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_2_expand (Conv2D) (None, 56, 56, 144) 3456 block_1_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_2_expand_BN (BatchNormali (None, 56, 56, 144) 576 block_2_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_2_expand_relu (ReLU) (None, 56, 56, 144) 0 block_2_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_2_depthwise (DepthwiseCon (None, 56, 56, 144) 1296 block_2_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_2_depthwise_BN (BatchNorm (None, 56, 56, 144) 576 block_2_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_2_depthwise_relu (ReLU) (None, 56, 56, 144) 0 block_2_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_2_project (Conv2D) (None, 56, 56, 24) 3456 block_2_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_2_project_BN (BatchNormal (None, 56, 56, 24) 96 block_2_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_2_add (Add) (None, 56, 56, 24) 0 block_1_project_BN[0][0] \n", " block_2_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_3_expand (Conv2D) (None, 56, 56, 144) 3456 block_2_add[0][0] \n", "__________________________________________________________________________________________________\n", "block_3_expand_BN (BatchNormali (None, 56, 56, 144) 576 block_3_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_3_expand_relu (ReLU) (None, 56, 56, 144) 0 block_3_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_3_pad (ZeroPadding2D) (None, 57, 57, 144) 0 block_3_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_3_depthwise (DepthwiseCon (None, 28, 28, 144) 1296 block_3_pad[0][0] \n", "__________________________________________________________________________________________________\n", "block_3_depthwise_BN (BatchNorm (None, 28, 28, 144) 576 block_3_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_3_depthwise_relu (ReLU) (None, 28, 28, 144) 0 block_3_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_3_project (Conv2D) (None, 28, 28, 32) 4608 block_3_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_3_project_BN (BatchNormal (None, 28, 28, 32) 128 block_3_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_4_expand (Conv2D) (None, 28, 28, 192) 6144 block_3_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_4_expand_BN (BatchNormali (None, 28, 28, 192) 768 block_4_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_4_expand_relu (ReLU) (None, 28, 28, 192) 0 block_4_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_4_depthwise (DepthwiseCon (None, 28, 28, 192) 1728 block_4_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_4_depthwise_BN (BatchNorm (None, 28, 28, 192) 768 block_4_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_4_depthwise_relu (ReLU) (None, 28, 28, 192) 0 block_4_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_4_project (Conv2D) (None, 28, 28, 32) 6144 block_4_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_4_project_BN (BatchNormal (None, 28, 28, 32) 128 block_4_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_4_add (Add) (None, 28, 28, 32) 0 block_3_project_BN[0][0] \n", " block_4_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_5_expand (Conv2D) (None, 28, 28, 192) 6144 block_4_add[0][0] \n", "__________________________________________________________________________________________________\n", "block_5_expand_BN (BatchNormali (None, 28, 28, 192) 768 block_5_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_5_expand_relu (ReLU) (None, 28, 28, 192) 0 block_5_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_5_depthwise (DepthwiseCon (None, 28, 28, 192) 1728 block_5_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_5_depthwise_BN (BatchNorm (None, 28, 28, 192) 768 block_5_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_5_depthwise_relu (ReLU) (None, 28, 28, 192) 0 block_5_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_5_project (Conv2D) (None, 28, 28, 32) 6144 block_5_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_5_project_BN (BatchNormal (None, 28, 28, 32) 128 block_5_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_5_add (Add) (None, 28, 28, 32) 0 block_4_add[0][0] \n", " block_5_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_6_expand (Conv2D) (None, 28, 28, 192) 6144 block_5_add[0][0] \n", "__________________________________________________________________________________________________\n", "block_6_expand_BN (BatchNormali (None, 28, 28, 192) 768 block_6_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_6_expand_relu (ReLU) (None, 28, 28, 192) 0 block_6_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_6_pad (ZeroPadding2D) (None, 29, 29, 192) 0 block_6_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_6_depthwise (DepthwiseCon (None, 14, 14, 192) 1728 block_6_pad[0][0] \n", "__________________________________________________________________________________________________\n", "block_6_depthwise_BN (BatchNorm (None, 14, 14, 192) 768 block_6_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_6_depthwise_relu (ReLU) (None, 14, 14, 192) 0 block_6_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_6_project (Conv2D) (None, 14, 14, 64) 12288 block_6_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_6_project_BN (BatchNormal (None, 14, 14, 64) 256 block_6_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_7_expand (Conv2D) (None, 14, 14, 384) 24576 block_6_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_7_expand_BN (BatchNormali (None, 14, 14, 384) 1536 block_7_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_7_expand_relu (ReLU) (None, 14, 14, 384) 0 block_7_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_7_depthwise (DepthwiseCon (None, 14, 14, 384) 3456 block_7_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_7_depthwise_BN (BatchNorm (None, 14, 14, 384) 1536 block_7_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_7_depthwise_relu (ReLU) (None, 14, 14, 384) 0 block_7_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_7_project (Conv2D) (None, 14, 14, 64) 24576 block_7_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_7_project_BN (BatchNormal (None, 14, 14, 64) 256 block_7_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_7_add (Add) (None, 14, 14, 64) 0 block_6_project_BN[0][0] \n", " block_7_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_8_expand (Conv2D) (None, 14, 14, 384) 24576 block_7_add[0][0] \n", "__________________________________________________________________________________________________\n", "block_8_expand_BN (BatchNormali (None, 14, 14, 384) 1536 block_8_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_8_expand_relu (ReLU) (None, 14, 14, 384) 0 block_8_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_8_depthwise (DepthwiseCon (None, 14, 14, 384) 3456 block_8_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_8_depthwise_BN (BatchNorm (None, 14, 14, 384) 1536 block_8_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_8_depthwise_relu (ReLU) (None, 14, 14, 384) 0 block_8_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_8_project (Conv2D) (None, 14, 14, 64) 24576 block_8_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_8_project_BN (BatchNormal (None, 14, 14, 64) 256 block_8_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_8_add (Add) (None, 14, 14, 64) 0 block_7_add[0][0] \n", " block_8_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_9_expand (Conv2D) (None, 14, 14, 384) 24576 block_8_add[0][0] \n", "__________________________________________________________________________________________________\n", "block_9_expand_BN (BatchNormali (None, 14, 14, 384) 1536 block_9_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_9_expand_relu (ReLU) (None, 14, 14, 384) 0 block_9_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_9_depthwise (DepthwiseCon (None, 14, 14, 384) 3456 block_9_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_9_depthwise_BN (BatchNorm (None, 14, 14, 384) 1536 block_9_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_9_depthwise_relu (ReLU) (None, 14, 14, 384) 0 block_9_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_9_project (Conv2D) (None, 14, 14, 64) 24576 block_9_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_9_project_BN (BatchNormal (None, 14, 14, 64) 256 block_9_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_9_add (Add) (None, 14, 14, 64) 0 block_8_add[0][0] \n", " block_9_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_10_expand (Conv2D) (None, 14, 14, 384) 24576 block_9_add[0][0] \n", "__________________________________________________________________________________________________\n", "block_10_expand_BN (BatchNormal (None, 14, 14, 384) 1536 block_10_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_10_expand_relu (ReLU) (None, 14, 14, 384) 0 block_10_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_10_depthwise (DepthwiseCo (None, 14, 14, 384) 3456 block_10_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_10_depthwise_BN (BatchNor (None, 14, 14, 384) 1536 block_10_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_10_depthwise_relu (ReLU) (None, 14, 14, 384) 0 block_10_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_10_project (Conv2D) (None, 14, 14, 96) 36864 block_10_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_10_project_BN (BatchNorma (None, 14, 14, 96) 384 block_10_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_11_expand (Conv2D) (None, 14, 14, 576) 55296 block_10_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_11_expand_BN (BatchNormal (None, 14, 14, 576) 2304 block_11_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_11_expand_relu (ReLU) (None, 14, 14, 576) 0 block_11_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_11_depthwise (DepthwiseCo (None, 14, 14, 576) 5184 block_11_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_11_depthwise_BN (BatchNor (None, 14, 14, 576) 2304 block_11_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_11_depthwise_relu (ReLU) (None, 14, 14, 576) 0 block_11_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_11_project (Conv2D) (None, 14, 14, 96) 55296 block_11_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_11_project_BN (BatchNorma (None, 14, 14, 96) 384 block_11_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_11_add (Add) (None, 14, 14, 96) 0 block_10_project_BN[0][0] \n", " block_11_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_12_expand (Conv2D) (None, 14, 14, 576) 55296 block_11_add[0][0] \n", "__________________________________________________________________________________________________\n", "block_12_expand_BN (BatchNormal (None, 14, 14, 576) 2304 block_12_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_12_expand_relu (ReLU) (None, 14, 14, 576) 0 block_12_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_12_depthwise (DepthwiseCo (None, 14, 14, 576) 5184 block_12_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_12_depthwise_BN (BatchNor (None, 14, 14, 576) 2304 block_12_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_12_depthwise_relu (ReLU) (None, 14, 14, 576) 0 block_12_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_12_project (Conv2D) (None, 14, 14, 96) 55296 block_12_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_12_project_BN (BatchNorma (None, 14, 14, 96) 384 block_12_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_12_add (Add) (None, 14, 14, 96) 0 block_11_add[0][0] \n", " block_12_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_13_expand (Conv2D) (None, 14, 14, 576) 55296 block_12_add[0][0] \n", "__________________________________________________________________________________________________\n", "block_13_expand_BN (BatchNormal (None, 14, 14, 576) 2304 block_13_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_13_expand_relu (ReLU) (None, 14, 14, 576) 0 block_13_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_13_pad (ZeroPadding2D) (None, 15, 15, 576) 0 block_13_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_13_depthwise (DepthwiseCo (None, 7, 7, 576) 5184 block_13_pad[0][0] \n", "__________________________________________________________________________________________________\n", "block_13_depthwise_BN (BatchNor (None, 7, 7, 576) 2304 block_13_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_13_depthwise_relu (ReLU) (None, 7, 7, 576) 0 block_13_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_13_project (Conv2D) (None, 7, 7, 160) 92160 block_13_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_13_project_BN (BatchNorma (None, 7, 7, 160) 640 block_13_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_14_expand (Conv2D) (None, 7, 7, 960) 153600 block_13_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_14_expand_BN (BatchNormal (None, 7, 7, 960) 3840 block_14_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_14_expand_relu (ReLU) (None, 7, 7, 960) 0 block_14_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_14_depthwise (DepthwiseCo (None, 7, 7, 960) 8640 block_14_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_14_depthwise_BN (BatchNor (None, 7, 7, 960) 3840 block_14_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_14_depthwise_relu (ReLU) (None, 7, 7, 960) 0 block_14_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_14_project (Conv2D) (None, 7, 7, 160) 153600 block_14_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_14_project_BN (BatchNorma (None, 7, 7, 160) 640 block_14_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_14_add (Add) (None, 7, 7, 160) 0 block_13_project_BN[0][0] \n", " block_14_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_15_expand (Conv2D) (None, 7, 7, 960) 153600 block_14_add[0][0] \n", "__________________________________________________________________________________________________\n", "block_15_expand_BN (BatchNormal (None, 7, 7, 960) 3840 block_15_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_15_expand_relu (ReLU) (None, 7, 7, 960) 0 block_15_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_15_depthwise (DepthwiseCo (None, 7, 7, 960) 8640 block_15_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_15_depthwise_BN (BatchNor (None, 7, 7, 960) 3840 block_15_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_15_depthwise_relu (ReLU) (None, 7, 7, 960) 0 block_15_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_15_project (Conv2D) (None, 7, 7, 160) 153600 block_15_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_15_project_BN (BatchNorma (None, 7, 7, 160) 640 block_15_project[0][0] \n", "__________________________________________________________________________________________________\n", "block_15_add (Add) (None, 7, 7, 160) 0 block_14_add[0][0] \n", " block_15_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_16_expand (Conv2D) (None, 7, 7, 960) 153600 block_15_add[0][0] \n", "__________________________________________________________________________________________________\n", "block_16_expand_BN (BatchNormal (None, 7, 7, 960) 3840 block_16_expand[0][0] \n", "__________________________________________________________________________________________________\n", "block_16_expand_relu (ReLU) (None, 7, 7, 960) 0 block_16_expand_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_16_depthwise (DepthwiseCo (None, 7, 7, 960) 8640 block_16_expand_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_16_depthwise_BN (BatchNor (None, 7, 7, 960) 3840 block_16_depthwise[0][0] \n", "__________________________________________________________________________________________________\n", "block_16_depthwise_relu (ReLU) (None, 7, 7, 960) 0 block_16_depthwise_BN[0][0] \n", "__________________________________________________________________________________________________\n", "block_16_project (Conv2D) (None, 7, 7, 320) 307200 block_16_depthwise_relu[0][0] \n", "__________________________________________________________________________________________________\n", "block_16_project_BN (BatchNorma (None, 7, 7, 320) 1280 block_16_project[0][0] \n", "__________________________________________________________________________________________________\n", "Conv_1 (Conv2D) (None, 7, 7, 1280) 409600 block_16_project_BN[0][0] \n", "__________________________________________________________________________________________________\n", "Conv_1_bn (BatchNormalization) (None, 7, 7, 1280) 5120 Conv_1[0][0] \n", "__________________________________________________________________________________________________\n", "out_relu (ReLU) (None, 7, 7, 1280) 0 Conv_1_bn[0][0] \n", "__________________________________________________________________________________________________\n", "global_average_pooling2d (Globa (None, 1280) 0 out_relu[0][0] \n", "__________________________________________________________________________________________________\n", "predictions (Dense) (None, 1000) 1281000 global_average_pooling2d[0][0] \n", "==================================================================================================\n", "Total params: 3,538,984\n", "Trainable params: 3,504,872\n", "Non-trainable params: 34,112\n", "__________________________________________________________________________________________________\n" ] } ], "source": [ "# Load the MobileNet V2 pre-trained model\n", "# Rather than training a model from scratch we can use a pre trained\n", "# model that has already been trained in the imagenet dataset\n", "# MobileNetV2 is a SOTA model for image classification \n", "model = MobileNetV2(weights='imagenet')\n", "model.summary()" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "out_relu\n" ] } ], "source": [ "### edTest(test_chow1) ###\n", "\n", "# Find the last convolutional layer\n", "# Inspect the model summary and find the last convolution layer\n", "# Get the name of the last convolution layer\n", "conv_layer_name = model.layers[-3].name\n", "print(conv_layer_name)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "# Take a sample image to find the saliency map\n", "img_path = './cat.png'\n", "\n", "# Load the image with the target_size for mobilenet\n", "img = image.load_img(img_path, target_size=(224, 224))\n", "\n", "# Convert the image to a numpy array \n", "x = image.img_to_array(img)\n", "\n", "# Add an extra dimension for batch size \n", "# to change it to (1,224,224,3)\n", "x = np.expand_dims(x, axis=0)\n", "\n", "# Use the MobileNetV2 preprocess_input function on the image\n", "x = preprocess_input(x)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "# Use the pretrained model to make a prediction \n", "preds = model.predict(x)\n", "\n", "# Useful dictionary to go from label index to actual label\n", "with open('idx2name.pkl', 'rb') as handle:\n", " keras_idx_to_name = pickle.load(handle)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Prediction class is Egyptian cat\n", "\n" ] } ], "source": [ "# See what the output predictions is:\n", "prediction_class = keras_idx_to_name[np.argmax(preds,axis=1).item(0)]\n", "print(f'Prediction class is {prediction_class}')" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [], "source": [ "# We use the tf.keras Functional API to get \n", "# 1. The model prediction probabilities\n", "# 2. The feature maps after the last convolution in the model\n", "\n", "# Get the last convolution layer in the network\n", "last_conv_layer = model.get_layer(conv_layer_name)\n", "\n", "# Get the output predictions and the last_conv_layer\n", "# Using tf.keras functional API\n", "get_maps = Model(inputs = [model.inputs], outputs = [model.output, last_conv_layer.output])" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "# Now we perform the Grad-CAM,\n", "# We take the gradient of the output with respect to the feature maps\n", "# after the convolution \n", "with tf.GradientTape() as tape:\n", "\n", " # Getting the required outputs \n", " model_out, last_conv_layer = get_maps(x)\n", " \n", " # We choose the output with maximum probability\n", " # But this can be different depending on your choice\n", " # For eg. you could select the second highest probability value \n", " class_out = tf.reduce_max(model_out)\n", "\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "⏸ **Take the gradients**" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "### edTest(test_chow2) ###\n", "\n", "# We take the gradients \n", "# tape.gradient() takes the gradient of something with respect to \n", "# something else. Here we want the derivative of the output class\n", "# with respect to to the last conv layer\n", "grads = tape.gradient(class_out, last_conv_layer)" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "\n", "# Here we combine all the gradients for each feature map \n", "pooled_grads = tf.reduce_mean(grads, axis=(0, 1, 2))\n", " \n", "# As per grad-CAM literature, here we need to multiply \n", "# the pooled grads with each feature map and take the average across\n", "# all the feature maps to make the heat map\n", "heatmap = tf.reduce_mean(tf.multiply(pooled_grads, last_conv_layer), axis=-1)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# Below we convert heatmap to numpy\n", "# Make all values positive\n", "# and reshape from (1,7,7) to (7,7) for ease of plotting\n", "heatmap = heatmap.numpy()\n", "heatmap[heatmap < 0] = 0 #relu\n", "heatmap = (heatmap - heatmap.min())/(heatmap.max() - heatmap.min())\n", "heatmap = heatmap.reshape((7, 7))\n", "\n", "# We plot the (7,7) heatmap\n", "plt.imshow(heatmap,cmap='jet')\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [], "source": [ "# Inorder to map to the original image\n", "# This heatmap has to be be resized\n", "resized_heatmap = np.uint8(cv2.resize(heatmap,(224,224))*255)" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "# We need to add a pre-processing step\n", "# to convert the grayscale heatmap\n", "# to a true JET colormap of 3 channels\n", "# for ease of viewing\n", "val = np.uint8(256-resized_heatmap)\n", "heatmap_final = cv2.applyColorMap(val, cv2.COLORMAP_JET)" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [], "source": [ "# We also prepare the image for plotting\n", "# by converting to tensor\n", "# and converting dtype to int8\n", "img = image.img_to_array(img)\n", "img = np.uint8(img)" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# Finally, we use the cv2.addweighted function\n", "# to superimpose the heatmap on the original image\n", "# Use the helper code below to do the same\n", "fig, ax = plt.subplots(1,1, figsize=(6,6))\n", "ax.imshow(cv2.addWeighted(heatmap_final, 0.5, img, 0.5, 0))\n", "ax.axis('off');\n", "fig.suptitle(f'Predicted class: {prediction_class}',y=0.92,fontsize=14);\n", "plt.show();" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "⏸ Will Grad-CAM work if we took the output from the last ReLU instead ? (True or False)" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [], "source": [ "### edTest(test_chow3) ###\n", "\n", "# Type your answer within in the quotes given \n", "answer3 = 'True'" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "⏸ The heatmap output is displaying:\n", "\n", "A: The weights of the layer
\n", "\n", "B: A 7x7 mask from the input image
\n", "\n", "C: The pixels that activates the most in red and the least in blues
\n", "\n", "D: A feature map of the input image
" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [], "source": [ "### edTest(test_chow4) ###\n", "\n", "# Type your answer within in the quotes given \n", "answer4 = 'C'" ] }, { "cell_type": "code", "execution_count": 0, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.5" } }, "nbformat": 4, "nbformat_minor": 4 }