Datasets
Models
Downloads: 1
1279 lines (1279 with data), 211.8 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": "991c8dc5-4807-4f41-ea97-7e4ad91ddd0d",
"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",
" TNLayer(),\n",
" TNLayer(),\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_5 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_2 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_3 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_6 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_7 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_8 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_9 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 3163137 (12.07 MB)\n",
"Trainable params: 3163137 (12.07 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": "2d1fa7a7-03f9-4a90-bc03-ba65a68b6aa0"
},
"execution_count": 17,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712723100.6701066\n",
"Wed Apr 10 04:25:00 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "68ac1961-c0bc-4255-f1b5-935ef525f2a5",
"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 - 2s - loss: 1.0032 - 2s/epoch - 108ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 1.0004 - 205ms/epoch - 14ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.9868 - 203ms/epoch - 14ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.5548 - 207ms/epoch - 14ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.2453 - 204ms/epoch - 14ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.1653 - 203ms/epoch - 14ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.1478 - 210ms/epoch - 14ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.1572 - 194ms/epoch - 13ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0727 - 197ms/epoch - 13ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0447 - 191ms/epoch - 13ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0493 - 201ms/epoch - 13ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0208 - 196ms/epoch - 13ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0149 - 196ms/epoch - 13ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.1217 - 193ms/epoch - 13ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0661 - 188ms/epoch - 13ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0178 - 197ms/epoch - 13ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0461 - 194ms/epoch - 13ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0474 - 196ms/epoch - 13ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0311 - 196ms/epoch - 13ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0099 - 198ms/epoch - 13ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 0.0077 - 201ms/epoch - 13ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 0.0107 - 197ms/epoch - 13ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 0.0277 - 198ms/epoch - 13ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 0.0374 - 196ms/epoch - 13ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 0.0321 - 207ms/epoch - 14ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 0.0692 - 207ms/epoch - 14ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 0.0738 - 195ms/epoch - 13ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 0.0289 - 187ms/epoch - 12ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 0.0260 - 192ms/epoch - 13ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 0.0221 - 191ms/epoch - 13ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 0.0051 - 197ms/epoch - 13ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 0.0033 - 201ms/epoch - 13ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 0.0125 - 203ms/epoch - 14ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 0.0250 - 202ms/epoch - 13ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 0.0379 - 203ms/epoch - 14ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 0.0331 - 211ms/epoch - 14ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 0.0529 - 204ms/epoch - 14ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 0.0101 - 203ms/epoch - 14ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 0.0075 - 206ms/epoch - 14ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 0.0041 - 206ms/epoch - 14ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 0.0055 - 195ms/epoch - 13ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 0.0220 - 196ms/epoch - 13ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 0.0122 - 195ms/epoch - 13ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 0.0209 - 193ms/epoch - 13ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 0.0438 - 195ms/epoch - 13ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 0.0290 - 191ms/epoch - 13ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 0.0054 - 194ms/epoch - 13ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 0.0402 - 196ms/epoch - 13ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 0.0390 - 200ms/epoch - 13ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 0.1014 - 197ms/epoch - 13ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 0.1022 - 198ms/epoch - 13ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 0.0602 - 199ms/epoch - 13ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 0.0116 - 200ms/epoch - 13ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 0.0050 - 201ms/epoch - 13ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 0.0246 - 194ms/epoch - 13ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 0.0347 - 207ms/epoch - 14ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 0.0517 - 188ms/epoch - 13ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 0.0555 - 204ms/epoch - 14ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 0.0710 - 204ms/epoch - 14ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 0.1103 - 197ms/epoch - 13ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 0.0547 - 201ms/epoch - 13ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 0.0161 - 198ms/epoch - 13ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 0.0077 - 194ms/epoch - 13ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 0.0223 - 189ms/epoch - 13ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 0.0317 - 196ms/epoch - 13ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 0.0246 - 190ms/epoch - 13ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 0.0196 - 192ms/epoch - 13ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 0.0072 - 190ms/epoch - 13ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 0.0271 - 193ms/epoch - 13ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 0.0382 - 194ms/epoch - 13ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 0.0240 - 199ms/epoch - 13ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 0.0048 - 196ms/epoch - 13ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 0.0044 - 193ms/epoch - 13ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 0.0082 - 193ms/epoch - 13ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 0.0179 - 193ms/epoch - 13ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 0.0074 - 184ms/epoch - 12ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 0.0063 - 189ms/epoch - 13ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 0.0010 - 188ms/epoch - 13ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 2.7124e-04 - 191ms/epoch - 13ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 1.6404e-04 - 191ms/epoch - 13ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 4.1765e-05 - 191ms/epoch - 13ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 2.8317e-05 - 191ms/epoch - 13ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 2.2079e-05 - 196ms/epoch - 13ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 1.9721e-05 - 194ms/epoch - 13ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 1.8349e-05 - 193ms/epoch - 13ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 1.5900e-05 - 190ms/epoch - 13ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 1.5088e-05 - 201ms/epoch - 13ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 1.5345e-05 - 193ms/epoch - 13ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 1.2821e-05 - 191ms/epoch - 13ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 1.1973e-05 - 187ms/epoch - 12ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 1.1264e-05 - 198ms/epoch - 13ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 1.1622e-05 - 195ms/epoch - 13ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 1.1196e-05 - 185ms/epoch - 12ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 1.1001e-05 - 186ms/epoch - 12ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 9.2698e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 8.4588e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 8.3027e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 7.8433e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 7.4296e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 7.1822e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 6.8093e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 6.6285e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 6.4972e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 7.1715e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 6.6502e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 5.8491e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 5.5942e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 5.1621e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 5.2311e-06 - 199ms/epoch - 13ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 5.0209e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 4.5853e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 4.5874e-06 - 201ms/epoch - 13ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 4.4493e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 4.5614e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 4.2373e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 3.9993e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 3.8071e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 3.6999e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 3.8177e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 3.5491e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 3.6114e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 3.3865e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 3.1545e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 3.3585e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 3.2105e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 3.0957e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 2.9608e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 2.8048e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 2.6603e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 2.6406e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 2.6186e-06 - 204ms/epoch - 14ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 2.6088e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 2.5018e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 2.4127e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 2.6576e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 2.9436e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 2.3435e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 2.2242e-06 - 200ms/epoch - 13ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 2.2889e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 2.2428e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 2.1223e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 2.0771e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 2.0710e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 2.2608e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 2.2096e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 2.1515e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 2.0101e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 1.9146e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 1.8010e-06 - 198ms/epoch - 13ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 1.8608e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 1.9539e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 1.7580e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 1.8930e-06 - 199ms/epoch - 13ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 1.7666e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 1.7241e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 1.5682e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 1.6157e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 1.6316e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 1.5239e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 1.5512e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 1.7054e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 1.9708e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 1.6962e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 1.5105e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 1.5620e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 1.6396e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 1.7508e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 2.3440e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 1.4908e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 1.4245e-06 - 199ms/epoch - 13ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 1.4384e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 1.2924e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 1.2453e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 1.4766e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 1.8961e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 1.3289e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 1.1395e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 1.0907e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 1.1284e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 1.2468e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 1.1070e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 1.2123e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 1.1576e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 1.0575e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 1.0362e-06 - 198ms/epoch - 13ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 1.4086e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 1.3634e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 1.2598e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 1.6442e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 1.4992e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 1.8602e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 1.2905e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 9.3022e-07 - 195ms/epoch - 13ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 1.3023e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 1.4437e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 1.6803e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 3.6188e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 2.2006e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 1.0395e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 9.7060e-07 - 202ms/epoch - 13ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 1.0972e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 8.6880e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 7.8713e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 8.8516e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 9.5047e-07 - 186ms/epoch - 12ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 1.0460e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 1.1449e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 1.1193e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 9.3172e-07 - 201ms/epoch - 13ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 8.6905e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 8.8199e-07 - 197ms/epoch - 13ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 7.2780e-07 - 198ms/epoch - 13ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 8.0522e-07 - 196ms/epoch - 13ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 7.1176e-07 - 203ms/epoch - 14ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 6.7819e-07 - 193ms/epoch - 13ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 7.4214e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 7.7115e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 8.4562e-07 - 196ms/epoch - 13ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 8.8237e-07 - 193ms/epoch - 13ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 7.5622e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 9.5358e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 8.2818e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 8.8671e-07 - 190ms/epoch - 13ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 8.0551e-07 - 189ms/epoch - 13ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 7.1806e-07 - 195ms/epoch - 13ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 8.1483e-07 - 190ms/epoch - 13ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 7.1553e-07 - 193ms/epoch - 13ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 8.1773e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 1.0109e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 9.8199e-07 - 196ms/epoch - 13ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 8.7764e-07 - 193ms/epoch - 13ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 6.8968e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 6.7230e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 7.6085e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 7.1446e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 7.2989e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 1.5508e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 4.1738e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 2.6013e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 1.5609e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 6.7480e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 8.1976e-07 - 198ms/epoch - 13ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 1.1168e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 1.2104e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 6.8630e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 2.5895e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 1.8254e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 9.7292e-07 - 189ms/epoch - 13ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 1.8263e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 7.8076e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 2.8636e-06 - 199ms/epoch - 13ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 8.5972e-07 - 195ms/epoch - 13ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 1.0097e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 3.4674e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 3.3746e-06 - 201ms/epoch - 13ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 1.0934e-06 - 198ms/epoch - 13ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 9.8685e-07 - 186ms/epoch - 12ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 5.5093e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 6.3382e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 6.5621e-07 - 193ms/epoch - 13ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 1.1591e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 9.3168e-07 - 186ms/epoch - 12ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 2.2803e-06 - 199ms/epoch - 13ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 2.1161e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 1.4434e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 1.6308e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 3.8406e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 3.3510e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 2.4460e-05 - 190ms/epoch - 13ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 4.2348e-05 - 198ms/epoch - 13ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 7.0862e-05 - 190ms/epoch - 13ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 2.9473e-05 - 191ms/epoch - 13ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 1.3187e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 7.9979e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 5.2017e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 5.9896e-07 - 193ms/epoch - 13ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 6.1976e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 1.1080e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 1.4618e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 1.4274e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 1.1201e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 8.3584e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 5.5694e-07 - 189ms/epoch - 13ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 5.6983e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 1.6004e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 2.4576e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 6.5691e-07 - 189ms/epoch - 13ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 5.0167e-07 - 197ms/epoch - 13ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 6.2116e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 9.5356e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 9.1587e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 2.2371e-05 - 192ms/epoch - 13ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 1.4322e-05 - 192ms/epoch - 13ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 3.5990e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 3.8107e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 3.4726e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 3.0860e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 4.4498e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 5.3547e-05 - 189ms/epoch - 13ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 2.7554e-04 - 190ms/epoch - 13ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7fa53035b790>"
]
},
"metadata": {},
"execution_count": 18
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "7d591d56-146c-4d75-8b1d-14ed3fbed902",
"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 6ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7fac6c6e2fb0>"
]
},
"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": "f4cfe015-f8f9-40fd-f332-bccaf271a151"
},
"execution_count": 20,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712723161.5980544\n",
"Wed Apr 10 04:26:01 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": "359a7cf5-9f49-401b-f18c-31bfe6c47965"
},
"execution_count": 21,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712723161.6037848\n",
"Wed Apr 10 04:26:01 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": "448345c7-c01d-4745-dee7-ad2f253f32b5"
},
"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",
"288 1.000000\n",
"370 0.605772\n",
"323 0.092855\n",
"359 0.087739\n",
"154 0.072089\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 0.006652\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.000962\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.000002\n",
"Normalized Saliency Sum: Saliency 3.193066\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.053681\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 16.218142\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 277.687714\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.002882\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 806.960754\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000029\n",
"1 0.003705\n",
"2 0.004334\n",
"3 0.004476\n",
"4 0.004478\n",
".. ...\n",
"475 3.168555\n",
"476 3.174517\n",
"477 3.185655\n",
"478 3.186908\n",
"479 3.193066\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 6.023372e-08\n",
"1 7.718521e-06\n",
"2 9.029576e-06\n",
"3 9.324020e-06\n",
"4 9.328502e-06\n",
".. ...\n",
"475 6.601155e-03\n",
"476 6.613577e-03\n",
"477 6.636781e-03\n",
"478 6.639391e-03\n",
"479 6.652220e-03\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.054035902\n",
"Normalized Saliency 25th Percentile: Saliency 0.00006\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.00451\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.00445\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": "a83f0aec-b73b-4546-daed-840a4d49e633"
},
"execution_count": 23,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712723163.426929\n",
"Wed Apr 10 04:26:03 2024\n"
]
}
]
}
]
}