Datasets
Models
Downloads: 1
1282 lines (1282 with data), 211.3 kB
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"machine_shape": "hm",
"gpuType": "V28"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "TPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "8XnVMPBXmtRa"
},
"source": [
"# TensorNetworks in Neural Networks.\n",
"\n",
"Here, we have a small toy example of how to use a TN inside of a fully connected neural network.\n",
"\n",
"First off, let's install tensornetwork"
]
},
{
"cell_type": "code",
"metadata": {
"id": "7HGRsYNAFxME"
},
"source": [
"# !pip install tensornetwork\n",
"\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import tensorflow as tf\n",
"# Import tensornetwork\n",
"import tensornetwork as tn\n",
"import random\n",
"import time\n",
"import pandas as pd\n",
"# Set the backend to tesorflow\n",
"# (default is numpy)\n",
"tn.set_default_backend(\"tensorflow\")\n",
"np.random.seed(42)\n",
"random.seed(42)\n",
"tf.random.set_seed(42)\n",
"# Explainability code assistance aided by ChatGPT3.5\n",
"# 2021 Kelly, D. TensorFlow Explainable AI tutorial https://www.youtube.com/watch?v=6xePkn3-LME"
],
"execution_count": 13,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "g1OMCo5XmrYu"
},
"source": [
"# TensorNetwork layer definition\n",
"\n",
"Here, we define the TensorNetwork layer we wish to use to replace the fully connected layer. Here, we simply use a 2 node Matrix Product Operator network to replace the normal dense weight matrix.\n",
"\n",
"We TensorNetwork's NCon API to keep the code short."
]
},
{
"cell_type": "code",
"metadata": {
"id": "wvSMKtPufnLp"
},
"source": [
"class TNLayer(tf.keras.layers.Layer):\n",
"\n",
" def __init__(self):\n",
" super(TNLayer, self).__init__()\n",
" # Create the variables for the layer.\n",
" self.a_var = tf.Variable(tf.random.normal(shape=(32, 32, 2),\n",
" stddev=1.0/32.0),\n",
" name=\"a\", trainable=True)\n",
" self.b_var = tf.Variable(tf.random.normal(shape=(32, 32, 2),\n",
" stddev=1.0/32.0),\n",
" name=\"b\", trainable=True)\n",
" self.bias = tf.Variable(tf.zeros(shape=(32, 32)),\n",
" name=\"bias\", trainable=True)\n",
"\n",
" def call(self, inputs):\n",
" # Define the contraction.\n",
" # We break it out so we can parallelize a batch using\n",
" # tf.vectorized_map (see below).\n",
" def f(input_vec, a_var, b_var, bias_var):\n",
" # Reshape to a matrix instead of a vector.\n",
" input_vec = tf.reshape(input_vec, (32, 32))\n",
"\n",
" # Now we create the network.\n",
" a = tn.Node(a_var)\n",
" b = tn.Node(b_var)\n",
" x_node = tn.Node(input_vec)\n",
" a[1] ^ x_node[0]\n",
" b[1] ^ x_node[1]\n",
" a[2] ^ b[2]\n",
"\n",
" # The TN should now look like this\n",
" # | |\n",
" # a --- b\n",
" # \\ /\n",
" # x\n",
"\n",
" # Now we begin the contraction.\n",
" c = a @ x_node\n",
" result = (c @ b).tensor\n",
"\n",
" # To make the code shorter, we also could've used Ncon.\n",
" # The above few lines of code is the same as this:\n",
" # result = tn.ncon([x, a_var, b_var], [[1, 2], [-1, 1, 3], [-2, 2, 3]])\n",
"\n",
" # Finally, add bias.\n",
" return result + bias_var\n",
"\n",
" # To deal with a batch of items, we can use the tf.vectorized_map\n",
" # function.\n",
" # https://www.tensorflow.org/api_docs/python/tf/vectorized_map\n",
" result = tf.vectorized_map(\n",
" lambda vec: f(vec, self.a_var, self.b_var, self.bias), inputs)\n",
" return tf.nn.relu(tf.reshape(result, (-1, 1024)))"
],
"execution_count": 14,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "V-CVqIhPnhY_"
},
"source": [
"# Smaller model\n",
"These two models are effectively the same, but notice how the TN layer has nearly 10x fewer parameters."
]
},
{
"cell_type": "code",
"metadata": {
"id": "bbKsmK8wIFTp",
"outputId": "6232929c-cdd8-4fd1-c858-efe23b673e98",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
}
},
"source": [
"Dense = tf.keras.layers.Dense\n",
"tn_model = tf.keras.Sequential(\n",
" [\n",
" tf.keras.Input(shape=(2,)),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Start Modified Layers\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 15,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_1\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_8 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_9 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_10 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_11 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_12 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_13 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_14 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_15 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 6301697 (24.04 MB)\n",
"Trainable params: 6301697 (24.04 MB)\n",
"Non-trainable params: 0 (0.00 Byte)\n",
"_________________________________________________________________\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "GWwoYp0WnsLA"
},
"source": [
"# Training a model\n",
"\n",
"You can train the TN model just as you would a normal neural network model! Here, we give an example of how to do it in Keras."
]
},
{
"cell_type": "code",
"metadata": {
"id": "qDFzOC7sDBJ-"
},
"source": [
"# Generate points forming concentric circles\n",
"num_points = 240 # Number of points for each circle\n",
"\n",
"# Inner circle\n",
"r1 = np.random.rand(num_points)\n",
"theta1 = np.random.rand(num_points) * 2 * np.pi\n",
"x1 = r1 * np.cos(theta1)\n",
"y1 = r1 * np.sin(theta1)\n",
"\n",
"# Outer circle\n",
"r2 = np.random.rand(num_points) + 1\n",
"theta2 = np.random.rand(num_points) * 2 * np.pi\n",
"x2 = r2 * np.cos(theta2)\n",
"y2 = r2 * np.sin(theta2)\n",
"\n",
"# Concatenate the points and labels\n",
"X = np.concatenate([np.column_stack((x1, y1)), np.column_stack((x2, y2))])\n",
"Y = np.concatenate([np.ones(num_points), -np.ones(num_points)])\n",
"\n",
"# Shuffle the data\n",
"shuffle_index = np.random.permutation(len(X))\n",
"X_shuffled = X[shuffle_index]\n",
"Y_shuffled = Y[shuffle_index]"
],
"execution_count": 16,
"outputs": []
},
{
"cell_type": "code",
"source": [
"seconds = time.time()\n",
"print(\"Time in seconds since beginning of run:\", seconds)\n",
"local_time = time.ctime(seconds)\n",
"print(local_time)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"id": "19TWP-1eKURB",
"outputId": "87a2c254-6bb2-493b-cc0b-3143812bd91f"
},
"execution_count": 17,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712719980.6406925\n",
"Wed Apr 10 03:33:00 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "bd7ede2c-83c1-4b61-8982-c2fe0fbb4a58",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
}
},
"source": [
"tn_model.compile(optimizer=\"adam\", loss=\"mean_squared_error\")\n",
"tn_model.fit(X, Y, epochs=300, verbose=2)"
],
"execution_count": 18,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 0.8098 - 1s/epoch - 93ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.2693 - 308ms/epoch - 21ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.2141 - 306ms/epoch - 20ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.1957 - 301ms/epoch - 20ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.1307 - 298ms/epoch - 20ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0978 - 305ms/epoch - 20ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0706 - 301ms/epoch - 20ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.1148 - 296ms/epoch - 20ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0788 - 288ms/epoch - 19ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0611 - 305ms/epoch - 20ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0911 - 308ms/epoch - 21ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0561 - 298ms/epoch - 20ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0340 - 302ms/epoch - 20ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0790 - 295ms/epoch - 20ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.2062 - 291ms/epoch - 19ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0948 - 288ms/epoch - 19ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0414 - 308ms/epoch - 21ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0327 - 308ms/epoch - 21ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0276 - 298ms/epoch - 20ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.1155 - 297ms/epoch - 20ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 0.0963 - 300ms/epoch - 20ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 0.0450 - 305ms/epoch - 20ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 0.0243 - 310ms/epoch - 21ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 0.0898 - 297ms/epoch - 20ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 0.0662 - 293ms/epoch - 20ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 0.0487 - 297ms/epoch - 20ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 0.0362 - 301ms/epoch - 20ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 0.0158 - 306ms/epoch - 20ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 0.1078 - 302ms/epoch - 20ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 0.1193 - 294ms/epoch - 20ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 0.0767 - 317ms/epoch - 21ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 0.0152 - 297ms/epoch - 20ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 0.0389 - 304ms/epoch - 20ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 0.0475 - 302ms/epoch - 20ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 0.0369 - 293ms/epoch - 20ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 0.0152 - 300ms/epoch - 20ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 0.0140 - 316ms/epoch - 21ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 0.0118 - 297ms/epoch - 20ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 0.0254 - 289ms/epoch - 19ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 0.0349 - 299ms/epoch - 20ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 0.0709 - 305ms/epoch - 20ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 0.0690 - 296ms/epoch - 20ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 0.0415 - 296ms/epoch - 20ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 0.0161 - 292ms/epoch - 19ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 0.0363 - 304ms/epoch - 20ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 0.0311 - 303ms/epoch - 20ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 0.0204 - 303ms/epoch - 20ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 0.0266 - 304ms/epoch - 20ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 0.0607 - 311ms/epoch - 21ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 0.0527 - 305ms/epoch - 20ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 0.0317 - 301ms/epoch - 20ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 0.0088 - 312ms/epoch - 21ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 0.0274 - 297ms/epoch - 20ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 0.0653 - 298ms/epoch - 20ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 0.0566 - 300ms/epoch - 20ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 0.0206 - 294ms/epoch - 20ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 0.0409 - 298ms/epoch - 20ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 0.0685 - 302ms/epoch - 20ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 0.1488 - 304ms/epoch - 20ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 0.0523 - 304ms/epoch - 20ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 0.0381 - 292ms/epoch - 19ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 0.0731 - 297ms/epoch - 20ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 0.1143 - 296ms/epoch - 20ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 0.0306 - 294ms/epoch - 20ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 0.0064 - 289ms/epoch - 19ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 0.0196 - 294ms/epoch - 20ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 0.0176 - 306ms/epoch - 20ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 0.0282 - 302ms/epoch - 20ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 0.0080 - 298ms/epoch - 20ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 0.0044 - 301ms/epoch - 20ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 0.0076 - 295ms/epoch - 20ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 0.0093 - 292ms/epoch - 19ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 0.0117 - 290ms/epoch - 19ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 0.0214 - 294ms/epoch - 20ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 0.0239 - 291ms/epoch - 19ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 0.0182 - 298ms/epoch - 20ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 0.0129 - 297ms/epoch - 20ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 0.0206 - 307ms/epoch - 20ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 0.0196 - 303ms/epoch - 20ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 0.0164 - 289ms/epoch - 19ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 0.0468 - 293ms/epoch - 20ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 0.0134 - 301ms/epoch - 20ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 0.0055 - 291ms/epoch - 19ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 0.0306 - 286ms/epoch - 19ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 0.0066 - 292ms/epoch - 19ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 0.0056 - 292ms/epoch - 19ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 0.0011 - 296ms/epoch - 20ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 0.0095 - 293ms/epoch - 20ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 0.0011 - 294ms/epoch - 20ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 0.0078 - 301ms/epoch - 20ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 2.3152e-04 - 292ms/epoch - 19ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 6.1307e-05 - 287ms/epoch - 19ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 2.6590e-05 - 293ms/epoch - 20ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 1.5372e-05 - 297ms/epoch - 20ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 1.3304e-05 - 288ms/epoch - 19ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 1.1748e-05 - 308ms/epoch - 21ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 1.0844e-05 - 299ms/epoch - 20ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 9.9991e-06 - 288ms/epoch - 19ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 9.2195e-06 - 292ms/epoch - 19ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 8.7509e-06 - 292ms/epoch - 19ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 8.1516e-06 - 313ms/epoch - 21ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 7.5221e-06 - 283ms/epoch - 19ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 7.1941e-06 - 295ms/epoch - 20ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 7.1781e-06 - 302ms/epoch - 20ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 6.6992e-06 - 298ms/epoch - 20ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 6.3260e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 5.7844e-06 - 310ms/epoch - 21ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 5.4278e-06 - 297ms/epoch - 20ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 5.0590e-06 - 318ms/epoch - 21ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 4.7756e-06 - 297ms/epoch - 20ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 4.5782e-06 - 305ms/epoch - 20ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 4.6405e-06 - 304ms/epoch - 20ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 4.0733e-06 - 295ms/epoch - 20ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 3.8427e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 3.6083e-06 - 298ms/epoch - 20ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 3.2604e-06 - 307ms/epoch - 20ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 3.0076e-06 - 307ms/epoch - 20ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 2.7667e-06 - 304ms/epoch - 20ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 2.5900e-06 - 297ms/epoch - 20ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 2.5219e-06 - 309ms/epoch - 21ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 2.3295e-06 - 308ms/epoch - 21ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 2.1442e-06 - 311ms/epoch - 21ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 2.0294e-06 - 301ms/epoch - 20ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 1.9434e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 1.8183e-06 - 300ms/epoch - 20ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 1.8008e-06 - 298ms/epoch - 20ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 1.7338e-06 - 294ms/epoch - 20ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 1.7190e-06 - 306ms/epoch - 20ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 1.5581e-06 - 309ms/epoch - 21ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 1.4973e-06 - 306ms/epoch - 20ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 1.3214e-06 - 300ms/epoch - 20ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 1.3306e-06 - 293ms/epoch - 20ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 1.2906e-06 - 294ms/epoch - 20ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 1.1801e-06 - 281ms/epoch - 19ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 1.1509e-06 - 293ms/epoch - 20ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 1.1257e-06 - 296ms/epoch - 20ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 1.1174e-06 - 290ms/epoch - 19ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 1.0764e-06 - 292ms/epoch - 19ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 1.0145e-06 - 295ms/epoch - 20ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 9.5655e-07 - 302ms/epoch - 20ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 9.3184e-07 - 299ms/epoch - 20ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 8.8618e-07 - 290ms/epoch - 19ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 8.9479e-07 - 285ms/epoch - 19ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 8.6915e-07 - 285ms/epoch - 19ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 8.7749e-07 - 293ms/epoch - 20ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 8.9676e-07 - 306ms/epoch - 20ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 8.4274e-07 - 292ms/epoch - 19ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 7.9089e-07 - 291ms/epoch - 19ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 7.2596e-07 - 302ms/epoch - 20ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 7.0016e-07 - 284ms/epoch - 19ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 7.1184e-07 - 287ms/epoch - 19ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 7.3478e-07 - 282ms/epoch - 19ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 6.3329e-07 - 291ms/epoch - 19ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 6.0662e-07 - 285ms/epoch - 19ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 5.8686e-07 - 291ms/epoch - 19ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 5.8331e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 5.6011e-07 - 284ms/epoch - 19ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 5.7988e-07 - 292ms/epoch - 19ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 5.7035e-07 - 296ms/epoch - 20ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 5.1443e-07 - 293ms/epoch - 20ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 5.1257e-07 - 287ms/epoch - 19ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 5.2320e-07 - 297ms/epoch - 20ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 4.9087e-07 - 289ms/epoch - 19ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 4.6742e-07 - 291ms/epoch - 19ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 4.3808e-07 - 297ms/epoch - 20ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 4.5972e-07 - 277ms/epoch - 18ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 4.6181e-07 - 294ms/epoch - 20ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 5.0764e-07 - 302ms/epoch - 20ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 4.3584e-07 - 291ms/epoch - 19ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 4.0978e-07 - 278ms/epoch - 19ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 4.8513e-07 - 290ms/epoch - 19ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 4.5198e-07 - 289ms/epoch - 19ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 3.8060e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 3.7868e-07 - 289ms/epoch - 19ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 3.6203e-07 - 284ms/epoch - 19ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 3.5677e-07 - 289ms/epoch - 19ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 3.5923e-07 - 284ms/epoch - 19ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 3.5676e-07 - 308ms/epoch - 21ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 3.1780e-07 - 291ms/epoch - 19ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 3.0762e-07 - 291ms/epoch - 19ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 2.9558e-07 - 293ms/epoch - 20ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 3.1206e-07 - 295ms/epoch - 20ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 3.0983e-07 - 285ms/epoch - 19ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 3.1277e-07 - 280ms/epoch - 19ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 3.0753e-07 - 310ms/epoch - 21ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 2.8438e-07 - 292ms/epoch - 19ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 3.0268e-07 - 292ms/epoch - 19ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 2.6926e-07 - 288ms/epoch - 19ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 2.4763e-07 - 287ms/epoch - 19ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 2.4600e-07 - 290ms/epoch - 19ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 2.6278e-07 - 291ms/epoch - 19ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 2.4358e-07 - 285ms/epoch - 19ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 2.5778e-07 - 308ms/epoch - 21ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 2.8764e-07 - 296ms/epoch - 20ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 2.5531e-07 - 295ms/epoch - 20ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 2.3884e-07 - 302ms/epoch - 20ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 2.3803e-07 - 288ms/epoch - 19ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 2.7435e-07 - 307ms/epoch - 20ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 2.8512e-07 - 299ms/epoch - 20ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 2.2689e-07 - 303ms/epoch - 20ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 2.0939e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 2.0791e-07 - 303ms/epoch - 20ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 2.0264e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 2.0996e-07 - 302ms/epoch - 20ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 1.9745e-07 - 294ms/epoch - 20ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 1.8724e-07 - 297ms/epoch - 20ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 1.8143e-07 - 289ms/epoch - 19ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 1.8363e-07 - 293ms/epoch - 20ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 1.9137e-07 - 299ms/epoch - 20ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 1.9609e-07 - 300ms/epoch - 20ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 2.1269e-07 - 308ms/epoch - 21ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 1.8071e-07 - 302ms/epoch - 20ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 2.0313e-07 - 301ms/epoch - 20ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 2.2489e-07 - 306ms/epoch - 20ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 1.7211e-07 - 296ms/epoch - 20ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 1.5883e-07 - 301ms/epoch - 20ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 1.5490e-07 - 304ms/epoch - 20ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 1.6489e-07 - 297ms/epoch - 20ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 1.6082e-07 - 300ms/epoch - 20ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 1.6024e-07 - 294ms/epoch - 20ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 1.9344e-07 - 304ms/epoch - 20ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 1.6787e-07 - 297ms/epoch - 20ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 1.5028e-07 - 300ms/epoch - 20ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 1.4439e-07 - 290ms/epoch - 19ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.4804e-07 - 294ms/epoch - 20ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 1.7846e-07 - 296ms/epoch - 20ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 1.5662e-07 - 299ms/epoch - 20ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 1.6265e-07 - 293ms/epoch - 20ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 1.3683e-07 - 300ms/epoch - 20ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 1.4453e-07 - 297ms/epoch - 20ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 1.3621e-07 - 301ms/epoch - 20ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 1.3933e-07 - 292ms/epoch - 19ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 1.4863e-07 - 296ms/epoch - 20ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 1.2310e-07 - 312ms/epoch - 21ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 1.2161e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 1.2552e-07 - 307ms/epoch - 20ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 1.2472e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 1.3942e-07 - 288ms/epoch - 19ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 1.4434e-07 - 291ms/epoch - 19ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 1.2547e-07 - 288ms/epoch - 19ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 1.0821e-07 - 307ms/epoch - 20ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 1.1388e-07 - 305ms/epoch - 20ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 1.0741e-07 - 304ms/epoch - 20ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 1.1531e-07 - 293ms/epoch - 20ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 1.2099e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 1.1943e-07 - 311ms/epoch - 21ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 1.5414e-07 - 310ms/epoch - 21ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 1.3419e-07 - 314ms/epoch - 21ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 1.1443e-07 - 306ms/epoch - 20ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 1.1127e-07 - 303ms/epoch - 20ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 1.0670e-07 - 301ms/epoch - 20ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 1.0193e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 9.3606e-08 - 302ms/epoch - 20ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 9.4875e-08 - 301ms/epoch - 20ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 9.9160e-08 - 297ms/epoch - 20ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 9.3591e-08 - 306ms/epoch - 20ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 1.0022e-07 - 317ms/epoch - 21ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 1.0620e-07 - 295ms/epoch - 20ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 9.6262e-08 - 307ms/epoch - 20ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 1.0902e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 9.7903e-08 - 303ms/epoch - 20ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 1.0126e-07 - 313ms/epoch - 21ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 7.8766e-08 - 296ms/epoch - 20ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 8.9764e-08 - 301ms/epoch - 20ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 8.0170e-08 - 314ms/epoch - 21ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 7.6363e-08 - 295ms/epoch - 20ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 1.1448e-07 - 297ms/epoch - 20ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 1.0035e-07 - 297ms/epoch - 20ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 9.9721e-08 - 313ms/epoch - 21ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 8.4581e-08 - 294ms/epoch - 20ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 7.9146e-08 - 313ms/epoch - 21ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 7.3717e-08 - 299ms/epoch - 20ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 9.2201e-08 - 295ms/epoch - 20ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 1.0243e-07 - 293ms/epoch - 20ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 8.2480e-08 - 305ms/epoch - 20ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 8.5214e-08 - 306ms/epoch - 20ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 9.3120e-08 - 305ms/epoch - 20ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 7.8703e-08 - 298ms/epoch - 20ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 7.2054e-08 - 297ms/epoch - 20ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 6.7359e-08 - 299ms/epoch - 20ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 6.6575e-08 - 288ms/epoch - 19ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 5.8673e-08 - 285ms/epoch - 19ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 6.4422e-08 - 292ms/epoch - 19ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 5.8239e-08 - 293ms/epoch - 20ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 7.0055e-08 - 291ms/epoch - 19ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 7.1606e-08 - 293ms/epoch - 20ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 6.3200e-08 - 287ms/epoch - 19ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 7.7414e-08 - 294ms/epoch - 20ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 7.0672e-08 - 297ms/epoch - 20ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 6.0981e-08 - 290ms/epoch - 19ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 6.3985e-08 - 302ms/epoch - 20ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 6.8001e-08 - 292ms/epoch - 19ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 6.7074e-08 - 290ms/epoch - 19ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 5.1780e-08 - 293ms/epoch - 20ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 5.6462e-08 - 297ms/epoch - 20ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 5.4491e-08 - 297ms/epoch - 20ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 6.6076e-08 - 298ms/epoch - 20ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 7.6033e-08 - 300ms/epoch - 20ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 7.1902e-08 - 285ms/epoch - 19ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 5.1364e-08 - 290ms/epoch - 19ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x79503c51e020>"
]
},
"metadata": {},
"execution_count": 18
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "19ed46e1-aba0-43bc-fe81-46499ac147e8",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 443
}
},
"source": [
"# Plotting code, feel free to ignore.\n",
"h = 1.0\n",
"x_min, x_max = X[:, 0].min() - 5, X[:, 0].max() + 5\n",
"y_min, y_max = X[:, 1].min() - 5, X[:, 1].max() + 5\n",
"xx, yy = np.meshgrid(np.arange(x_min, x_max, h),\n",
" np.arange(y_min, y_max, h))\n",
"\n",
"# here \"model\" is your model's prediction (classification) function\n",
"Z = tn_model.predict(np.c_[xx.ravel(), yy.ravel()])\n",
"\n",
"# Put the result into a color plot\n",
"Z = Z.reshape(xx.shape)\n",
"plt.contourf(xx, yy, Z)\n",
"plt.axis('off')\n",
"\n",
"# Plot also the training points\n",
"plt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired)"
],
"execution_count": 19,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"7/7 [==============================] - 0s 5ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x79503c375ff0>"
]
},
"metadata": {},
"execution_count": 19
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"source": [
"seconds = time.time()\n",
"print(\"Time in seconds since end of run:\", seconds)\n",
"local_time = time.ctime(seconds)\n",
"print(local_time)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"id": "s_ukr55OORqE",
"outputId": "88fe0e7c-90fb-4b61-efc8-0689eccc506a"
},
"execution_count": 20,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712720072.1190684\n",
"Wed Apr 10 03:34:32 2024\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"seconds = time.time()\n",
"print(\"Time in seconds since beginning of run:\", seconds)\n",
"local_time = time.ctime(seconds)\n",
"print(local_time)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"id": "o8HTyvcHchzQ",
"outputId": "7ee8d89e-1ba9-41a0-d13e-9cad0c6fa30e"
},
"execution_count": 21,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712720072.1272366\n",
"Wed Apr 10 03:34:32 2024\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Function to compute saliency map\n",
"@tf.function\n",
"def compute_saliency(input_image):\n",
" with tf.GradientTape() as tape:\n",
" tape.watch(input_image)\n",
" predictions = tn_model(input_image)\n",
" grads = tape.gradient(predictions, input_image)\n",
" saliency_map = tf.reduce_max(tf.abs(grads), axis=-1)\n",
" return saliency_map\n",
"\n",
"# Function to compute saliency map using Gradient\n",
"@tf.function\n",
"def compute_gradient_saliency(input_image):\n",
" with tf.GradientTape() as tape:\n",
" tape.watch(input_image)\n",
" predictions = tn_model(input_image)\n",
" grads = tape.gradient(predictions, input_image)\n",
" saliency_map = tf.reduce_max(tf.abs(grads), axis=-1)\n",
" return saliency_map\n",
"\n",
"# Compute saliency map for the entire grid\n",
"def compute_saliency_map_grid():\n",
" xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))\n",
" input_image = np.c_[xx.ravel(), yy.ravel()]\n",
" saliency_map = compute_saliency(tf.constant(input_image, dtype=tf.float32)).numpy()\n",
" saliency_map = saliency_map.reshape(xx.shape)\n",
" return xx, yy, saliency_map\n",
"\n",
"# Compute and plot saliency map for the entire grid\n",
"xx, yy, saliency_map = compute_saliency_map_grid()\n",
"\n",
"# Compute saliency maps for all data points\n",
"def compute_saliency_maps():\n",
" saliency_maps = []\n",
" for data_point in X:\n",
" saliency_map = compute_gradient_saliency(tf.constant(data_point[None, :], dtype=tf.float32)).numpy()\n",
" saliency_maps.append(saliency_map)\n",
" return saliency_maps\n",
"\n",
"# Find the indices of the data points with the highest saliency values\n",
"def find_top_indices(saliency_maps, top_k):\n",
" top_indices = np.argsort(np.max(saliency_maps, axis=1))[-top_k:]\n",
" return top_indices\n",
"\n",
"def plot_most_diagnostic(top_indices, top_k, normalized_saliency_values):\n",
" plt.figure(figsize=(8, 6))\n",
" plt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired)\n",
" plt.scatter(X[top_indices, 0], X[top_indices, 1], marker='o', s=200, facecolors='none', edgecolors='r', linewidths=2)\n",
" for i, index in enumerate(top_indices):\n",
" plt.annotate(f'{normalized_saliency_values.iloc[index][\"Saliency\"]:.4f}', (X[index, 0], X[index, 1]), xytext=(X[index, 0]+0.35, X[index, 1]+0.25), arrowprops=dict(facecolor='black', arrowstyle='->'))\n",
" plt.title(f'Saliency Most Diagnostic Data Points (Top {top_k})')\n",
" plt.xlabel('Feature 1')\n",
" plt.ylabel('Feature 2')\n",
" plt.grid(True)\n",
" plt.axis('equal')\n",
" plt.show()\n",
"\n",
"# Compute saliency maps for all data points\n",
"saliency_maps = compute_saliency_maps()\n",
"\n",
"# Find the indices of the data points with the highest saliency values\n",
"top_k = 5 # Number of top diagnostic data points to select\n",
"top_indices = find_top_indices(saliency_maps, top_k)\n",
"\n",
"# Create a DataFrame to store the saliency values\n",
"saliency_df = pd.DataFrame(data=saliency_maps, columns=[\"Saliency\"])\n",
"\n",
"# Save the saliency values to a CSV file\n",
"saliency_df.to_csv(\"saliency_values.csv\", index=False)\n",
"\n",
"print(\"Saliency values saved to saliency_values.csv\")\n",
"\n",
"# Normalizing the saliency values\n",
"normalized_saliency = (saliency_df - saliency_df.min()) / (saliency_df.max() - saliency_df.min())\n",
"\n",
"# Saving the normalized saliency values to a new CSV file\n",
"normalized_saliency.to_csv(\"normalized_saliency_values.csv\", index=False)\n",
"\n",
"# Plot the most diagnostic data points\n",
"plot_most_diagnostic(top_indices, top_k, normalized_saliency)\n",
"\n",
"print(\"Normalized saliency values saved to normalized_saliency_values.csv\")\n",
"print(\"Normalized Saliency Top-k:\")\n",
"print(normalized_saliency.nlargest(top_k, 'Saliency'))\n",
"print(\"Normalized Saliency Max:\", normalized_saliency.max())\n",
"print(\"Normalized Saliency Min:\", normalized_saliency.min())\n",
"print(\"Normalized Saliency Mean:\", normalized_saliency.mean())\n",
"print(\"Normalized Saliency Median:\", normalized_saliency.median())\n",
"print(\"Normalized Saliency Mode:\", normalized_saliency.mode())\n",
"sum_normalized_values = normalized_saliency.sum()\n",
"print(\"Normalized Saliency Sum:\", sum_normalized_values)\n",
"print(\"#\")\n",
"print(\"#\")\n",
"print(\"#\")\n",
"print(\"Normalized Saliency Standard Deviation:\", normalized_saliency.std())\n",
"print(\"Normalized Saliency Skewness:\", normalized_saliency.skew())\n",
"print(\"Normalized Saliency Kurtosis:\", normalized_saliency.kurtosis())\n",
"print(\"Normalized Saliency Variance:\", normalized_saliency.var())\n",
"coefficient_variation = (normalized_saliency.std() / normalized_saliency.mean()) * 100\n",
"print(\"Normalized Saliency Coefficient of Variation:\", coefficient_variation)\n",
"print(\"#\")\n",
"print(\"#\")\n",
"print(\"#\")\n",
"cumulative_sum = normalized_saliency.cumsum()\n",
"print(\"Cumulative Sum of Normalized Saliency Values:\", cumulative_sum)\n",
"mean_cumulative_sum = cumulative_sum / len(normalized_saliency)\n",
"print(\"Mean of Cumulative Sum of Normalized Saliency Values:\", mean_cumulative_sum)\n",
"rms = np.sqrt(np.mean(normalized_saliency**2))\n",
"print(\"Normalized Saliency Root Mean Square:\", rms)\n",
"q1 = normalized_saliency.quantile(0.25)\n",
"q2 = normalized_saliency.quantile(0.75)\n",
"iqr = q2 - q1\n",
"print(\"Normalized Saliency 25th Percentile:\", q1)\n",
"print(\"Normalized Saliency 75th Percentile:\", q2)\n",
"print(\"Normalized Saliency Interquartile Range:\", iqr)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1849
},
"id": "95xed6YyDClf",
"outputId": "04049a8c-777f-47f0-b297-fcf4d7c4b201"
},
"execution_count": 22,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Saliency values saved to saliency_values.csv\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Normalized saliency values saved to normalized_saliency_values.csv\n",
"Normalized Saliency Top-k:\n",
" Saliency\n",
"154 1.000000\n",
"50 0.617664\n",
"288 0.409709\n",
"370 0.259956\n",
"69 0.200937\n",
"Normalized Saliency Max: Saliency 1.0\n",
"dtype: float32\n",
"Normalized Saliency Min: Saliency 0.0\n",
"dtype: float32\n",
"Normalized Saliency Mean: Saliency 0.010022\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.000981\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.000004\n",
"Normalized Saliency Sum: Saliency 4.81067\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.059716\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 12.663724\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 184.524872\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.003566\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 595.838684\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000067\n",
"1 0.077297\n",
"2 0.078958\n",
"3 0.079309\n",
"4 0.079312\n",
".. ...\n",
"475 4.802942\n",
"476 4.803154\n",
"477 4.803624\n",
"478 4.808683\n",
"479 4.810670\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 1.387186e-07\n",
"1 1.610354e-04\n",
"2 1.644967e-04\n",
"3 1.652261e-04\n",
"4 1.652336e-04\n",
".. ...\n",
"475 1.000613e-02\n",
"476 1.000657e-02\n",
"477 1.000755e-02\n",
"478 1.001809e-02\n",
"479 1.002223e-02\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.060490113\n",
"Normalized Saliency 25th Percentile: Saliency 0.000117\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.003784\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.003667\n",
"dtype: float64\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"seconds = time.time()\n",
"print(\"Time in seconds since end of run:\", seconds)\n",
"local_time = time.ctime(seconds)\n",
"print(local_time)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"id": "wfZCzuq9KY9b",
"outputId": "64bb2299-101d-435c-d8f8-6a65f1ef6a76"
},
"execution_count": 23,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712720074.0068567\n",
"Wed Apr 10 03:34:34 2024\n"
]
}
]
}
]
}