Datasets
Models
Downloads: 1
1263 lines (1263 with data), 217.9 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": 68,
"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": 69,
"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": "6deda749-08c6-44d4-8c60-30a8eefbf543",
"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",
" 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": 70,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_6\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_22 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_6 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_23 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_24 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_25 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_26 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 3158017 (12.05 MB)\n",
"Trainable params: 3158017 (12.05 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": [
"X = np.concatenate([np.random.randn(120, 2) + np.array([3, 3]),\n",
" np.random.randn(120, 2) + np.array([-3, -3]),\n",
" np.random.randn(120, 2) + np.array([-3, 3]),\n",
" np.random.randn(120, 2) + np.array([3, -3])])\n",
"\n",
"Y = np.concatenate([np.ones((240)), -np.ones((240))])"
],
"execution_count": 71,
"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": "007efb3b-be0a-4a88-932f-bd30d2fde973"
},
"execution_count": 72,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712559179.1365466\n",
"Mon Apr 8 06:52:59 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "04db27e7-1cdb-49d9-b934-170c0a2588d3",
"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": 73,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 0.4460 - 1s/epoch - 88ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.0685 - 182ms/epoch - 12ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.0315 - 181ms/epoch - 12ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0177 - 179ms/epoch - 12ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0101 - 182ms/epoch - 12ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0085 - 194ms/epoch - 13ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0052 - 184ms/epoch - 12ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0135 - 190ms/epoch - 13ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0212 - 181ms/epoch - 12ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0085 - 192ms/epoch - 13ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0065 - 186ms/epoch - 12ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0067 - 179ms/epoch - 12ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0108 - 186ms/epoch - 12ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0043 - 177ms/epoch - 12ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0123 - 171ms/epoch - 11ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0124 - 177ms/epoch - 12ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0094 - 177ms/epoch - 12ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0048 - 190ms/epoch - 13ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0011 - 175ms/epoch - 12ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0011 - 178ms/epoch - 12ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 3.6528e-04 - 184ms/epoch - 12ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 2.1398e-04 - 175ms/epoch - 12ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 1.0647e-04 - 179ms/epoch - 12ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 5.5372e-05 - 177ms/epoch - 12ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 4.1630e-05 - 184ms/epoch - 12ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 3.4015e-05 - 174ms/epoch - 12ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 2.6042e-05 - 172ms/epoch - 11ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 2.2465e-05 - 179ms/epoch - 12ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 2.3362e-05 - 177ms/epoch - 12ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 2.0801e-05 - 176ms/epoch - 12ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 2.0977e-05 - 175ms/epoch - 12ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 1.7503e-05 - 180ms/epoch - 12ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 1.3877e-05 - 180ms/epoch - 12ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 1.0903e-05 - 180ms/epoch - 12ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 9.4917e-06 - 177ms/epoch - 12ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 9.2487e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 8.0683e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 7.1656e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 6.7335e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 6.0044e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 5.6810e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 5.9367e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 5.6559e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 5.1203e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 4.7775e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 3.9777e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 3.7930e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 4.0408e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 3.8104e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 3.1383e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 3.2505e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 3.1219e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 2.8622e-06 - 182ms/epoch - 12ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 2.9268e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 2.9052e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 2.8676e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 2.9281e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 2.4704e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 2.6205e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 2.5333e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 2.1169e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 1.9442e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 2.2940e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 2.2238e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 2.1882e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 1.8424e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 1.6284e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 1.5439e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 1.4152e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 1.3811e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 1.3521e-06 - 177ms/epoch - 12ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 1.2634e-06 - 177ms/epoch - 12ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 1.3034e-06 - 182ms/epoch - 12ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 1.7453e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 1.4601e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 1.4532e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 1.5861e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 1.3946e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 1.3454e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 9.3574e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 8.4909e-07 - 197ms/epoch - 13ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 1.0093e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 9.6044e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 1.2242e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 1.1849e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 7.1272e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 7.7691e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 8.7424e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 9.3267e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 7.4122e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 8.4988e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 8.3673e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 7.4497e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 5.1905e-07 - 186ms/epoch - 12ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 5.7477e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 4.9176e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 5.2243e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 6.4242e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 5.9988e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 4.8590e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 6.0165e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 5.2319e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 4.2196e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 4.3471e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 6.0434e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 6.1414e-07 - 183ms/epoch - 12ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 5.1019e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 3.9237e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 4.2872e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 6.7243e-07 - 189ms/epoch - 13ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 8.8430e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 6.8520e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 4.7930e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 4.2802e-07 - 186ms/epoch - 12ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 4.4702e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 6.4260e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 6.2501e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 3.3695e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 5.7467e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 6.4492e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 4.7243e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 5.4515e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 6.4652e-07 - 196ms/epoch - 13ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 3.3730e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 3.8179e-07 - 193ms/epoch - 13ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 3.7449e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 2.4457e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 4.3354e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 3.8232e-07 - 183ms/epoch - 12ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 4.7831e-07 - 189ms/epoch - 13ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 7.1719e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 4.6394e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 3.5722e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 4.1794e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 5.1103e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 3.1751e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 4.3578e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 5.5872e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 6.0003e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 1.2489e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 9.8225e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 8.6286e-07 - 183ms/epoch - 12ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 4.1696e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 3.2557e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 2.9154e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 2.8813e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 3.3058e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 2.6408e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 2.8886e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 3.0304e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 6.5623e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 9.2245e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 5.8882e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 3.7033e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 3.0289e-07 - 189ms/epoch - 13ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 2.3826e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 3.8492e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 3.5548e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 4.7132e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 5.7858e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 4.5840e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 1.0929e-05 - 187ms/epoch - 12ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 1.7627e-05 - 179ms/epoch - 12ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 1.1230e-05 - 172ms/epoch - 11ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 6.5257e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 1.1024e-05 - 184ms/epoch - 12ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 1.0084e-05 - 177ms/epoch - 12ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 4.1586e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 6.7143e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 3.7776e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 2.3715e-05 - 185ms/epoch - 12ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 2.0749e-05 - 176ms/epoch - 12ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 6.0214e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 1.9804e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 1.2744e-06 - 177ms/epoch - 12ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 2.5083e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 1.5217e-05 - 170ms/epoch - 11ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 1.8403e-05 - 175ms/epoch - 12ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 1.5460e-05 - 178ms/epoch - 12ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 3.9606e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 3.5065e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 3.3610e-06 - 182ms/epoch - 12ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 2.1575e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 1.7343e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 6.3887e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 1.1978e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 8.2737e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 2.4837e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 2.2955e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 6.6236e-06 - 177ms/epoch - 12ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 2.2810e-05 - 181ms/epoch - 12ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 1.1994e-05 - 178ms/epoch - 12ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 1.3614e-05 - 184ms/epoch - 12ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 5.7135e-05 - 173ms/epoch - 12ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 1.0870e-04 - 181ms/epoch - 12ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 1.1795e-04 - 181ms/epoch - 12ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 8.9197e-05 - 179ms/epoch - 12ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 4.0798e-05 - 173ms/epoch - 12ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 2.8501e-05 - 176ms/epoch - 12ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 7.8080e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 8.7668e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 1.5613e-05 - 183ms/epoch - 12ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 1.9598e-05 - 178ms/epoch - 12ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 1.0712e-05 - 193ms/epoch - 13ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 1.3411e-05 - 180ms/epoch - 12ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 4.2146e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 2.3663e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 3.1942e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 7.9290e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 1.1227e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 7.7657e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 2.0138e-05 - 174ms/epoch - 12ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 2.5304e-05 - 180ms/epoch - 12ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 5.8621e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 1.1730e-04 - 189ms/epoch - 13ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 1.1626e-04 - 180ms/epoch - 12ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 2.0218e-04 - 181ms/epoch - 12ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 6.7470e-05 - 178ms/epoch - 12ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 7.2902e-05 - 175ms/epoch - 12ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 4.0488e-05 - 180ms/epoch - 12ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 5.2864e-05 - 176ms/epoch - 12ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 3.1808e-05 - 174ms/epoch - 12ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 3.3437e-05 - 173ms/epoch - 12ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 7.1954e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 6.0575e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 6.3091e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 5.4028e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 7.4346e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 1.2554e-05 - 187ms/epoch - 12ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 2.5538e-05 - 186ms/epoch - 12ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 2.2430e-05 - 187ms/epoch - 12ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 1.1462e-05 - 185ms/epoch - 12ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 1.2049e-05 - 190ms/epoch - 13ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 7.8852e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 6.1765e-06 - 182ms/epoch - 12ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 1.0971e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 1.5983e-06 - 177ms/epoch - 12ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 6.6120e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 2.3468e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 8.0512e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 3.3385e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 1.0992e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 4.8241e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 7.9130e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 3.4497e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 6.2762e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 2.0994e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 1.9766e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 7.9962e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 8.1786e-07 - 195ms/epoch - 13ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 7.7253e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 2.0837e-05 - 184ms/epoch - 12ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 1.9040e-05 - 183ms/epoch - 12ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 3.3472e-05 - 176ms/epoch - 12ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 4.1883e-05 - 188ms/epoch - 13ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 3.4092e-05 - 182ms/epoch - 12ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 2.8794e-04 - 183ms/epoch - 12ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 6.9161e-04 - 194ms/epoch - 13ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 5.7145e-04 - 175ms/epoch - 12ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 5.6042e-04 - 176ms/epoch - 12ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 5.2157e-04 - 176ms/epoch - 12ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 3.9568e-04 - 174ms/epoch - 12ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 1.1429e-04 - 181ms/epoch - 12ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 6.8881e-05 - 195ms/epoch - 13ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 3.9185e-05 - 181ms/epoch - 12ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 2.8387e-05 - 182ms/epoch - 12ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 1.1050e-05 - 187ms/epoch - 12ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 4.5514e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 6.5316e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 5.3389e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 3.0676e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 6.7361e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 4.5741e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 3.0220e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 2.3337e-07 - 183ms/epoch - 12ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 1.8511e-07 - 183ms/epoch - 12ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 1.5958e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 1.8926e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 1.2620e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 1.2395e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 2.3479e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 2.9301e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 1.9190e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 9.4890e-08 - 191ms/epoch - 13ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 8.3812e-08 - 184ms/epoch - 12ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 4.7919e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 2.9850e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 1.3710e-07 - 186ms/epoch - 12ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 1.2523e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 2.4714e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 2.9811e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 2.4452e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 8.6774e-08 - 183ms/epoch - 12ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 7.1709e-08 - 182ms/epoch - 12ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 8.5147e-08 - 179ms/epoch - 12ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 1.3354e-07 - 183ms/epoch - 12ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 6.9073e-08 - 190ms/epoch - 13ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 1.2075e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 2.1289e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 3.3760e-07 - 193ms/epoch - 13ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x79197c3a02e0>"
]
},
"metadata": {},
"execution_count": 73
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "7fc02e8b-a80a-4ac1-8802-dabd885dde11",
"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": 74,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 4ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x791974146ad0>"
]
},
"metadata": {},
"execution_count": 74
},
{
"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": "5ebbf0d5-6241-4044-b50a-9e18467e7356"
},
"execution_count": 75,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712559235.5883904\n",
"Mon Apr 8 06:53:55 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": "8e97185e-421b-48c0-a08d-a5f0e16a6594"
},
"execution_count": 76,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712559235.5949774\n",
"Mon Apr 8 06:53:55 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": 1932
},
"id": "95xed6YyDClf",
"outputId": "2746ae90-36af-4eca-fd5d-21cc2a3c7547"
},
"execution_count": 77,
"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",
"37 1.000000\n",
"239 0.812810\n",
"287 0.415522\n",
"39 0.304933\n",
"327 0.156042\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 0.016336\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.007936\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.001840\n",
"1 0.004560\n",
"2 0.007090\n",
"3 0.007383\n",
"4 0.008910\n",
"Normalized Saliency Sum: Saliency 7.841247\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.064005\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 12.410798\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 169.795639\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.004097\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 391.806885\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.011859\n",
"1 0.028155\n",
"2 0.031650\n",
"3 0.040401\n",
"4 0.042922\n",
".. ...\n",
"475 7.799649\n",
"476 7.825381\n",
"477 7.829473\n",
"478 7.834321\n",
"479 7.841246\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000025\n",
"1 0.000059\n",
"2 0.000066\n",
"3 0.000084\n",
"4 0.000089\n",
".. ...\n",
"475 0.016249\n",
"476 0.016303\n",
"477 0.016311\n",
"478 0.016322\n",
"479 0.016336\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.065992475\n",
"Normalized Saliency 25th Percentile: Saliency 0.004917\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.012232\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.007315\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": "b1f9487a-754e-4f0d-aeba-e8d8aba35a98"
},
"execution_count": 78,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712559237.3156774\n",
"Mon Apr 8 06:53:57 2024\n"
]
}
]
}
]
}