Datasets
Models
Downloads: 1
1262 lines (1262 with data), 217.4 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": 101,
"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": 102,
"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": "85e87edd-3d7a-42f9-a94c-4c0809dc7108",
"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",
" TNLayer(),\n",
" TNLayer(),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 103,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_9\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_34 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_35 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_36 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_37 (Dense) (None, 1024) 1049600 \n",
" \n",
" tn_layer_11 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_12 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_38 (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": [
"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": 104,
"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": "3ab5ccf5-b90e-4123-830b-2a948fc95a20"
},
"execution_count": 105,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712560424.405967\n",
"Mon Apr 8 07:13:44 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "1a3b0395-7072-46b6-dbf8-1677ed9858b7",
"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": 106,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 2s - loss: 0.8585 - 2s/epoch - 113ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.1262 - 210ms/epoch - 14ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.0524 - 208ms/epoch - 14ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0375 - 201ms/epoch - 13ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0328 - 213ms/epoch - 14ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0255 - 210ms/epoch - 14ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0226 - 209ms/epoch - 14ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0153 - 206ms/epoch - 14ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0120 - 217ms/epoch - 14ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0114 - 198ms/epoch - 13ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0105 - 200ms/epoch - 13ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0035 - 207ms/epoch - 14ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0022 - 206ms/epoch - 14ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0032 - 200ms/epoch - 13ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0050 - 204ms/epoch - 14ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0176 - 195ms/epoch - 13ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0109 - 210ms/epoch - 14ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0198 - 201ms/epoch - 13ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0101 - 208ms/epoch - 14ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0162 - 201ms/epoch - 13ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 8.4357e-04 - 202ms/epoch - 13ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 0.0020 - 197ms/epoch - 13ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 0.0059 - 209ms/epoch - 14ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 0.0058 - 207ms/epoch - 14ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 8.3432e-04 - 204ms/epoch - 14ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 8.0473e-04 - 211ms/epoch - 14ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 4.8518e-04 - 209ms/epoch - 14ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 1.4914e-04 - 209ms/epoch - 14ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 9.0316e-05 - 203ms/epoch - 14ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 3.7373e-05 - 208ms/epoch - 14ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 1.9333e-05 - 199ms/epoch - 13ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 1.6453e-05 - 205ms/epoch - 14ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 9.7276e-06 - 208ms/epoch - 14ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 5.8368e-06 - 206ms/epoch - 14ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 4.3727e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 3.3341e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 3.0333e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 2.5287e-06 - 209ms/epoch - 14ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 2.4919e-06 - 201ms/epoch - 13ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 1.6067e-06 - 202ms/epoch - 13ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 2.4826e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 1.1351e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 1.1492e-06 - 198ms/epoch - 13ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 9.9027e-07 - 201ms/epoch - 13ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 8.0708e-07 - 201ms/epoch - 13ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 7.2268e-07 - 200ms/epoch - 13ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 1.0014e-06 - 206ms/epoch - 14ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 2.0097e-06 - 213ms/epoch - 14ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 2.2118e-06 - 201ms/epoch - 13ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 1.4094e-06 - 201ms/epoch - 13ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 4.4516e-06 - 205ms/epoch - 14ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 2.1861e-05 - 198ms/epoch - 13ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 1.0245e-04 - 200ms/epoch - 13ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 6.6857e-05 - 200ms/epoch - 13ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 3.0942e-05 - 208ms/epoch - 14ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 2.4905e-05 - 210ms/epoch - 14ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 1.5539e-05 - 199ms/epoch - 13ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 3.8325e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 2.7928e-06 - 202ms/epoch - 13ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 2.0000e-06 - 209ms/epoch - 14ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 7.2275e-06 - 202ms/epoch - 13ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 1.2125e-05 - 203ms/epoch - 14ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 1.4434e-05 - 199ms/epoch - 13ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 9.6288e-06 - 204ms/epoch - 14ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 4.6383e-05 - 201ms/epoch - 13ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 1.6237e-04 - 201ms/epoch - 13ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 1.0105e-04 - 199ms/epoch - 13ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 3.7350e-05 - 199ms/epoch - 13ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 2.1053e-05 - 213ms/epoch - 14ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 1.2583e-05 - 208ms/epoch - 14ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 3.6695e-06 - 204ms/epoch - 14ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 2.9760e-06 - 206ms/epoch - 14ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 2.8232e-06 - 199ms/epoch - 13ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 1.2711e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 1.0246e-06 - 212ms/epoch - 14ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 8.7930e-07 - 197ms/epoch - 13ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 8.3700e-07 - 206ms/epoch - 14ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 4.7605e-07 - 204ms/epoch - 14ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 1.2582e-06 - 203ms/epoch - 14ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 1.7165e-06 - 201ms/epoch - 13ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 3.3941e-06 - 204ms/epoch - 14ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 1.3466e-05 - 209ms/epoch - 14ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 6.6584e-06 - 212ms/epoch - 14ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 5.4752e-06 - 213ms/epoch - 14ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 1.6024e-05 - 201ms/epoch - 13ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 9.0223e-05 - 206ms/epoch - 14ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 1.8555e-05 - 204ms/epoch - 14ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 4.6633e-06 - 213ms/epoch - 14ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 1.3066e-05 - 204ms/epoch - 14ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 7.1286e-05 - 210ms/epoch - 14ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 3.9085e-04 - 212ms/epoch - 14ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 1.5956e-04 - 200ms/epoch - 13ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 4.0742e-05 - 207ms/epoch - 14ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 3.3391e-05 - 202ms/epoch - 13ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 6.3088e-05 - 212ms/epoch - 14ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 7.0266e-05 - 206ms/epoch - 14ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 3.0615e-05 - 213ms/epoch - 14ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 1.1190e-05 - 202ms/epoch - 13ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 5.7257e-06 - 198ms/epoch - 13ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 4.9470e-06 - 203ms/epoch - 14ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 6.8408e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 5.7438e-06 - 198ms/epoch - 13ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 2.4430e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 1.2600e-06 - 200ms/epoch - 13ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 1.1352e-06 - 200ms/epoch - 13ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 4.1676e-07 - 204ms/epoch - 14ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 5.3456e-07 - 202ms/epoch - 13ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 1.0990e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 5.9055e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 1.5327e-05 - 194ms/epoch - 13ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 4.0197e-05 - 192ms/epoch - 13ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 1.5351e-04 - 200ms/epoch - 13ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 1.0346e-04 - 196ms/epoch - 13ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 9.3473e-05 - 201ms/epoch - 13ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 2.3598e-05 - 202ms/epoch - 13ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 5.5646e-06 - 200ms/epoch - 13ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 3.9543e-06 - 202ms/epoch - 13ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 8.8842e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 2.6549e-06 - 207ms/epoch - 14ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 9.6636e-07 - 208ms/epoch - 14ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 6.2951e-07 - 197ms/epoch - 13ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 1.0570e-06 - 208ms/epoch - 14ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 2.6925e-05 - 199ms/epoch - 13ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 1.3274e-05 - 205ms/epoch - 14ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 7.9457e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 2.1448e-05 - 202ms/epoch - 13ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 1.5373e-05 - 195ms/epoch - 13ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 4.2825e-06 - 206ms/epoch - 14ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 5.2205e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 4.5822e-06 - 204ms/epoch - 14ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 1.2379e-06 - 201ms/epoch - 13ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 1.0058e-06 - 202ms/epoch - 13ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 1.7713e-06 - 202ms/epoch - 13ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 2.5644e-06 - 212ms/epoch - 14ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 1.1736e-05 - 200ms/epoch - 13ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 9.2666e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 3.3794e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 6.8184e-07 - 195ms/epoch - 13ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 6.6578e-07 - 206ms/epoch - 14ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 2.1380e-06 - 205ms/epoch - 14ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 3.4649e-04 - 213ms/epoch - 14ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 0.0023 - 198ms/epoch - 13ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 0.0011 - 208ms/epoch - 14ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 0.0012 - 207ms/epoch - 14ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 4.9452e-04 - 192ms/epoch - 13ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 1.6022e-04 - 198ms/epoch - 13ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 7.4225e-05 - 192ms/epoch - 13ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 8.5441e-05 - 203ms/epoch - 14ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 4.5237e-05 - 211ms/epoch - 14ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 1.9317e-05 - 203ms/epoch - 14ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 8.4670e-06 - 206ms/epoch - 14ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 2.1791e-06 - 205ms/epoch - 14ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 1.1246e-06 - 202ms/epoch - 13ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 1.2955e-06 - 199ms/epoch - 13ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 8.9875e-07 - 199ms/epoch - 13ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 6.2771e-07 - 201ms/epoch - 13ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 5.3200e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 3.9652e-07 - 198ms/epoch - 13ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 9.8837e-07 - 200ms/epoch - 13ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 1.4263e-06 - 204ms/epoch - 14ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 2.5991e-06 - 200ms/epoch - 13ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 7.5201e-07 - 198ms/epoch - 13ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 3.8438e-07 - 202ms/epoch - 13ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 3.4005e-07 - 204ms/epoch - 14ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 2.1511e-07 - 201ms/epoch - 13ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 2.0555e-07 - 200ms/epoch - 13ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 1.7699e-07 - 198ms/epoch - 13ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 2.1967e-07 - 197ms/epoch - 13ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 3.3023e-07 - 200ms/epoch - 13ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 2.0122e-07 - 200ms/epoch - 13ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 6.0426e-07 - 201ms/epoch - 13ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 2.3779e-07 - 201ms/epoch - 13ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 1.6247e-07 - 197ms/epoch - 13ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 1.2267e-07 - 195ms/epoch - 13ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 1.9276e-07 - 199ms/epoch - 13ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 5.5000e-07 - 198ms/epoch - 13ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 1.0422e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 1.0684e-06 - 202ms/epoch - 13ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 2.4465e-06 - 208ms/epoch - 14ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 4.5114e-06 - 204ms/epoch - 14ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 5.3559e-06 - 200ms/epoch - 13ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 2.7110e-06 - 198ms/epoch - 13ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 5.1632e-06 - 199ms/epoch - 13ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 3.9840e-06 - 200ms/epoch - 13ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 3.3340e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 6.5749e-07 - 200ms/epoch - 13ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 2.8048e-07 - 204ms/epoch - 14ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 1.3718e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 1.1993e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 2.7874e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 5.8398e-07 - 196ms/epoch - 13ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 7.2726e-07 - 200ms/epoch - 13ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 4.2841e-07 - 208ms/epoch - 14ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 1.4458e-06 - 205ms/epoch - 14ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 1.7189e-05 - 203ms/epoch - 14ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 2.1039e-05 - 200ms/epoch - 13ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 8.6527e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 2.1467e-06 - 203ms/epoch - 14ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 1.4808e-06 - 200ms/epoch - 13ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 1.2551e-06 - 202ms/epoch - 13ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 6.3986e-07 - 205ms/epoch - 14ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 4.3892e-07 - 196ms/epoch - 13ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 9.4593e-07 - 201ms/epoch - 13ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 1.6169e-07 - 197ms/epoch - 13ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 7.6009e-08 - 206ms/epoch - 14ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 6.3005e-08 - 203ms/epoch - 14ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 7.5531e-08 - 200ms/epoch - 13ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 2.3226e-07 - 203ms/epoch - 14ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 2.3217e-07 - 213ms/epoch - 14ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 2.6098e-07 - 203ms/epoch - 14ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 3.3521e-07 - 204ms/epoch - 14ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 8.6257e-07 - 201ms/epoch - 13ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 1.7542e-06 - 206ms/epoch - 14ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 6.6436e-07 - 199ms/epoch - 13ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 1.8093e-06 - 208ms/epoch - 14ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 5.6061e-06 - 201ms/epoch - 13ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 1.8554e-05 - 206ms/epoch - 14ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 2.7085e-05 - 200ms/epoch - 13ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 5.1021e-05 - 211ms/epoch - 14ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 5.8675e-05 - 200ms/epoch - 13ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 4.3846e-05 - 208ms/epoch - 14ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 1.5922e-05 - 197ms/epoch - 13ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 1.1442e-05 - 201ms/epoch - 13ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 8.6337e-05 - 199ms/epoch - 13ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.2769e-04 - 203ms/epoch - 14ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 3.0618e-05 - 207ms/epoch - 14ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 1.1683e-05 - 211ms/epoch - 14ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 1.1494e-04 - 208ms/epoch - 14ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 1.0281e-04 - 211ms/epoch - 14ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 4.8454e-05 - 208ms/epoch - 14ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 2.2972e-05 - 194ms/epoch - 13ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 2.5771e-06 - 198ms/epoch - 13ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 2.4069e-06 - 202ms/epoch - 13ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 7.3699e-07 - 203ms/epoch - 14ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 9.0499e-07 - 206ms/epoch - 14ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 3.4091e-07 - 200ms/epoch - 13ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 3.0889e-07 - 203ms/epoch - 14ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 1.1440e-06 - 198ms/epoch - 13ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 6.6622e-07 - 201ms/epoch - 13ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 1.1918e-07 - 204ms/epoch - 14ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 1.9646e-07 - 214ms/epoch - 14ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 1.7311e-07 - 200ms/epoch - 13ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 1.8731e-07 - 202ms/epoch - 13ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 3.2260e-07 - 206ms/epoch - 14ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 2.1922e-07 - 203ms/epoch - 14ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 1.0282e-06 - 204ms/epoch - 14ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 2.7337e-07 - 204ms/epoch - 14ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 1.9713e-07 - 204ms/epoch - 14ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 2.9284e-07 - 207ms/epoch - 14ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 2.9853e-07 - 198ms/epoch - 13ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 4.4764e-06 - 201ms/epoch - 13ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 8.6678e-06 - 205ms/epoch - 14ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 7.8132e-06 - 213ms/epoch - 14ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 1.8297e-05 - 209ms/epoch - 14ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 2.7811e-05 - 201ms/epoch - 13ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 2.3642e-05 - 204ms/epoch - 14ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 3.8920e-06 - 205ms/epoch - 14ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 2.4322e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 1.6861e-07 - 202ms/epoch - 13ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 1.0503e-07 - 200ms/epoch - 13ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 4.4558e-07 - 202ms/epoch - 13ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 2.3302e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 3.9243e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 4.0418e-05 - 194ms/epoch - 13ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 8.6097e-05 - 197ms/epoch - 13ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 8.3542e-05 - 196ms/epoch - 13ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 2.9706e-05 - 202ms/epoch - 13ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 2.9062e-05 - 205ms/epoch - 14ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 2.5754e-05 - 198ms/epoch - 13ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 2.0872e-05 - 201ms/epoch - 13ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 1.2911e-05 - 206ms/epoch - 14ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 9.9004e-06 - 200ms/epoch - 13ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 7.6885e-06 - 200ms/epoch - 13ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 1.1844e-05 - 194ms/epoch - 13ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 3.8006e-05 - 198ms/epoch - 13ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 4.7093e-05 - 196ms/epoch - 13ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 4.6749e-05 - 200ms/epoch - 13ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 5.6192e-05 - 198ms/epoch - 13ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 2.3447e-05 - 195ms/epoch - 13ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 1.8274e-05 - 199ms/epoch - 13ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 4.1043e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 6.5305e-06 - 203ms/epoch - 14ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 4.4823e-06 - 206ms/epoch - 14ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 2.1278e-06 - 208ms/epoch - 14ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 1.4211e-06 - 207ms/epoch - 14ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 3.6778e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 3.0884e-06 - 206ms/epoch - 14ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 2.1067e-06 - 198ms/epoch - 13ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 1.6555e-06 - 203ms/epoch - 14ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 2.5196e-06 - 200ms/epoch - 13ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 1.3395e-06 - 204ms/epoch - 14ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 6.0241e-07 - 204ms/epoch - 14ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 6.5212e-07 - 218ms/epoch - 15ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 1.5048e-07 - 199ms/epoch - 13ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 1.8435e-07 - 198ms/epoch - 13ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 2.8260e-07 - 202ms/epoch - 13ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 3.8964e-07 - 204ms/epoch - 14ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 7.1118e-07 - 197ms/epoch - 13ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 1.7444e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 4.9478e-06 - 201ms/epoch - 13ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x791974495210>"
]
},
"metadata": {},
"execution_count": 106
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "ddff69c1-0b9e-4096-b3af-d172c2df8e08",
"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": 107,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 5ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x791a7c263fa0>"
]
},
"metadata": {},
"execution_count": 107
},
{
"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": "f6aed183-2c70-4db5-a4c2-3e09197074cf"
},
"execution_count": 108,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712560487.9774039\n",
"Mon Apr 8 07:14:47 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": "e47e9ccc-d5ee-4050-c4b1-5eae0c42a01a"
},
"execution_count": 109,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712560487.983804\n",
"Mon Apr 8 07:14:47 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": 1859
},
"id": "95xed6YyDClf",
"outputId": "c20144a2-1b30-49c5-8548-bd649601677a"
},
"execution_count": 110,
"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",
"377 1.000000\n",
"287 0.930645\n",
"327 0.750344\n",
"110 0.630011\n",
"335 0.532085\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 0.013478\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.002779\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.00449\n",
"Normalized Saliency Sum: Saliency 6.469547\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.083131\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 9.386966\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 93.707001\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.006911\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 616.782043\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.004225\n",
"1 0.005420\n",
"2 0.007944\n",
"3 0.008504\n",
"4 0.010022\n",
".. ...\n",
"475 6.452310\n",
"476 6.454716\n",
"477 6.460453\n",
"478 6.465029\n",
"479 6.469547\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000009\n",
"1 0.000011\n",
"2 0.000017\n",
"3 0.000018\n",
"4 0.000021\n",
".. ...\n",
"475 0.013442\n",
"476 0.013447\n",
"477 0.013459\n",
"478 0.013469\n",
"479 0.013478\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.08413128\n",
"Normalized Saliency 25th Percentile: Saliency 0.001362\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.004578\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.003217\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": "e33151cd-51f3-4342-9c18-e44698a81cc3"
},
"execution_count": 111,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712560489.8620806\n",
"Mon Apr 8 07:14:49 2024\n"
]
}
]
}
]
}