Datasets
Models
Downloads: 1
1264 lines (1264 with data), 218.7 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": 56,
"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": 57,
"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": "fb981ba8-c224-4af5-ced0-44912108f654",
"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",
" TNLayer(),\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": 58,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_5\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_18 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_15 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_16 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_17 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_19 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_20 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_21 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 2118657 (8.08 MB)\n",
"Trainable params: 2118657 (8.08 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": 59,
"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": "1204f740-74ab-4e87-f077-bb99d320b960"
},
"execution_count": 60,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712630954.5279925\n",
"Tue Apr 9 02:49:14 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "572f500d-97a9-4aec-8b8c-b55de5394c96",
"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": 61,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 2s - loss: 1.0034 - 2s/epoch - 122ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 1.0006 - 184ms/epoch - 12ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 1.0008 - 170ms/epoch - 11ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.9756 - 187ms/epoch - 12ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.2568 - 175ms/epoch - 12ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0272 - 174ms/epoch - 12ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0087 - 174ms/epoch - 12ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0067 - 168ms/epoch - 11ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0052 - 164ms/epoch - 11ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0034 - 173ms/epoch - 12ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0023 - 166ms/epoch - 11ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 8.3699e-04 - 164ms/epoch - 11ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 9.9896e-04 - 176ms/epoch - 12ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0042 - 178ms/epoch - 12ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0030 - 182ms/epoch - 12ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0111 - 171ms/epoch - 11ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0030 - 176ms/epoch - 12ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0048 - 167ms/epoch - 11ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0013 - 184ms/epoch - 12ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 1.0804e-04 - 169ms/epoch - 11ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 4.1239e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 2.3140e-05 - 167ms/epoch - 11ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 1.2622e-05 - 170ms/epoch - 11ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 1.0173e-05 - 170ms/epoch - 11ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 1.1205e-05 - 170ms/epoch - 11ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 9.4626e-06 - 171ms/epoch - 11ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 7.2010e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 4.4388e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 2.5240e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 2.0598e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 1.9873e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 2.0393e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 1.6686e-06 - 171ms/epoch - 11ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 1.9378e-06 - 165ms/epoch - 11ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 1.5031e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 1.4153e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 1.0315e-06 - 164ms/epoch - 11ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 1.1301e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 1.2896e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 1.1958e-06 - 165ms/epoch - 11ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 1.2064e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 9.0316e-07 - 165ms/epoch - 11ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 1.0759e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 7.8889e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 6.9692e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 9.6133e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 7.6522e-07 - 162ms/epoch - 11ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 9.7001e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 7.1869e-07 - 165ms/epoch - 11ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 7.5336e-07 - 169ms/epoch - 11ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 6.8685e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 6.4595e-07 - 166ms/epoch - 11ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 8.3997e-07 - 169ms/epoch - 11ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 5.2348e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 3.7411e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 4.5110e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 4.3948e-07 - 168ms/epoch - 11ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 4.2392e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 4.5619e-07 - 165ms/epoch - 11ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 4.6973e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 3.9365e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 1.0104e-06 - 182ms/epoch - 12ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 1.0351e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 1.7534e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 1.5896e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 3.9295e-06 - 164ms/epoch - 11ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 3.1187e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 1.1507e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 1.4384e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 2.5299e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 3.7233e-06 - 160ms/epoch - 11ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 3.2295e-06 - 163ms/epoch - 11ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 1.1213e-06 - 165ms/epoch - 11ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 7.1126e-07 - 167ms/epoch - 11ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 9.4723e-07 - 164ms/epoch - 11ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 7.4737e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 2.9752e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 2.5623e-07 - 163ms/epoch - 11ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 2.8503e-07 - 168ms/epoch - 11ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 2.5838e-07 - 164ms/epoch - 11ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 3.6397e-07 - 168ms/epoch - 11ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 5.4385e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 3.1511e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 3.1053e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 1.9939e-06 - 164ms/epoch - 11ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 8.1074e-06 - 162ms/epoch - 11ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 9.2823e-06 - 161ms/epoch - 11ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 7.8176e-06 - 165ms/epoch - 11ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 5.4394e-05 - 166ms/epoch - 11ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 6.0362e-05 - 174ms/epoch - 12ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 8.4248e-06 - 165ms/epoch - 11ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 3.4262e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 1.1701e-06 - 164ms/epoch - 11ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 7.2073e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 7.3689e-07 - 164ms/epoch - 11ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 3.3226e-07 - 165ms/epoch - 11ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 4.1222e-07 - 169ms/epoch - 11ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 4.5916e-07 - 165ms/epoch - 11ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 3.3237e-07 - 166ms/epoch - 11ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 3.8150e-07 - 165ms/epoch - 11ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 1.1793e-06 - 164ms/epoch - 11ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 6.4419e-07 - 167ms/epoch - 11ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 4.7270e-07 - 168ms/epoch - 11ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 9.4896e-07 - 166ms/epoch - 11ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 1.3449e-05 - 167ms/epoch - 11ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 1.9753e-05 - 162ms/epoch - 11ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 6.0534e-05 - 163ms/epoch - 11ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 2.1288e-05 - 160ms/epoch - 11ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 1.2371e-04 - 168ms/epoch - 11ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 1.1217e-04 - 168ms/epoch - 11ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 1.4666e-04 - 179ms/epoch - 12ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 2.9236e-05 - 167ms/epoch - 11ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 2.4580e-05 - 174ms/epoch - 12ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 1.4845e-05 - 164ms/epoch - 11ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 3.0016e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 8.2530e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 3.9207e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 6.1959e-07 - 169ms/epoch - 11ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 6.8096e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 4.9955e-07 - 165ms/epoch - 11ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 4.8086e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 7.2827e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 5.0958e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 1.9752e-06 - 165ms/epoch - 11ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 1.2134e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 1.0649e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 2.0320e-06 - 161ms/epoch - 11ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 5.6258e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 6.5664e-06 - 171ms/epoch - 11ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 2.9356e-06 - 165ms/epoch - 11ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 3.2706e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 2.5769e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 7.7951e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 1.0787e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 1.2071e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 4.2955e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 3.9847e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 1.0805e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 2.9856e-05 - 165ms/epoch - 11ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 4.0473e-05 - 172ms/epoch - 11ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 4.7915e-05 - 172ms/epoch - 11ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 9.4227e-05 - 172ms/epoch - 11ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 4.3137e-05 - 166ms/epoch - 11ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 3.8192e-05 - 175ms/epoch - 12ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 1.2238e-05 - 167ms/epoch - 11ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 3.6766e-06 - 171ms/epoch - 11ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 1.7881e-05 - 175ms/epoch - 12ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 1.1704e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 3.2894e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 1.0823e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 3.3473e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 6.2961e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 6.4036e-07 - 169ms/epoch - 11ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 4.0408e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 3.8528e-07 - 163ms/epoch - 11ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 1.2736e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 6.7177e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 6.1218e-07 - 167ms/epoch - 11ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 1.3946e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 6.4899e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 1.0668e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 3.6150e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 6.6818e-05 - 181ms/epoch - 12ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 1.4267e-04 - 167ms/epoch - 11ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 1.1690e-04 - 175ms/epoch - 12ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 1.1056e-04 - 165ms/epoch - 11ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 4.5402e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 1.2034e-04 - 170ms/epoch - 11ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 6.9212e-05 - 166ms/epoch - 11ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 4.8016e-05 - 160ms/epoch - 11ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 3.5365e-05 - 164ms/epoch - 11ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 1.8844e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 1.1678e-05 - 163ms/epoch - 11ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 8.6707e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 4.2476e-06 - 171ms/epoch - 11ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 3.1170e-06 - 177ms/epoch - 12ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 1.8910e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 1.3211e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 2.5441e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 2.4684e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 5.0012e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 1.7922e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 7.8426e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 6.0950e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 2.8375e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 3.0047e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 3.8839e-06 - 164ms/epoch - 11ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 4.2178e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 5.8746e-06 - 165ms/epoch - 11ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 4.5854e-05 - 173ms/epoch - 12ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 1.2323e-04 - 174ms/epoch - 12ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 1.7645e-04 - 171ms/epoch - 11ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 1.0453e-04 - 168ms/epoch - 11ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 7.1368e-04 - 168ms/epoch - 11ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 8.1090e-04 - 169ms/epoch - 11ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 4.4369e-04 - 175ms/epoch - 12ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 1.2946e-04 - 186ms/epoch - 12ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 5.1568e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 1.0858e-05 - 167ms/epoch - 11ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 3.2258e-06 - 171ms/epoch - 11ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 2.3155e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 2.0459e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 3.3272e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 4.4126e-06 - 171ms/epoch - 11ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 2.1149e-06 - 161ms/epoch - 11ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 3.9765e-07 - 164ms/epoch - 11ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 3.6707e-07 - 167ms/epoch - 11ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 9.0292e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 8.3186e-07 - 169ms/epoch - 11ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 3.8075e-07 - 168ms/epoch - 11ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 2.7208e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 1.7415e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 1.6285e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 1.4468e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 1.6767e-07 - 167ms/epoch - 11ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 2.6482e-07 - 169ms/epoch - 11ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 2.5686e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 1.5904e-07 - 166ms/epoch - 11ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 2.6911e-07 - 165ms/epoch - 11ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 2.2282e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 1.3864e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 9.2777e-08 - 162ms/epoch - 11ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 1.4082e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 3.0597e-07 - 168ms/epoch - 11ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.0168e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 9.8579e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 8.5131e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 1.4486e-05 - 172ms/epoch - 11ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 3.4601e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 1.2682e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 3.0180e-05 - 166ms/epoch - 11ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 1.5712e-05 - 165ms/epoch - 11ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 6.3708e-06 - 171ms/epoch - 11ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 2.0822e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 2.6100e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 3.3291e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 2.6943e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 2.5217e-07 - 166ms/epoch - 11ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 1.2761e-06 - 162ms/epoch - 11ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 2.5054e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 4.6420e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 6.2157e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 4.4453e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 2.6844e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 5.6597e-07 - 166ms/epoch - 11ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 3.5924e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 3.9998e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 8.2663e-06 - 163ms/epoch - 11ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 7.8243e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 5.3240e-05 - 161ms/epoch - 11ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 3.1210e-04 - 162ms/epoch - 11ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 1.7033e-04 - 168ms/epoch - 11ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 2.9748e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 1.3887e-05 - 160ms/epoch - 11ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 7.4235e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 2.7006e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 9.4087e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 2.5727e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 3.9743e-06 - 164ms/epoch - 11ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 1.7286e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 3.1244e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 6.9521e-05 - 159ms/epoch - 11ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 9.7378e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 2.5040e-04 - 171ms/epoch - 11ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 1.0176e-04 - 164ms/epoch - 11ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 1.8729e-05 - 170ms/epoch - 11ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 1.4864e-05 - 173ms/epoch - 12ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 1.6939e-05 - 165ms/epoch - 11ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 9.2384e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 1.2121e-04 - 161ms/epoch - 11ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 1.5254e-04 - 171ms/epoch - 11ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 3.9424e-05 - 176ms/epoch - 12ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 2.0643e-05 - 178ms/epoch - 12ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 1.5111e-05 - 172ms/epoch - 11ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 2.5904e-05 - 180ms/epoch - 12ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 4.2305e-05 - 171ms/epoch - 11ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 1.7404e-05 - 172ms/epoch - 11ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 5.1546e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 2.8925e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 2.8195e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 1.1145e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 5.3877e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 2.0310e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 2.6791e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 1.8385e-06 - 171ms/epoch - 11ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 4.0973e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 5.8565e-06 - 165ms/epoch - 11ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 1.1170e-05 - 165ms/epoch - 11ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 7.6735e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 1.5809e-04 - 166ms/epoch - 11ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 1.3078e-04 - 164ms/epoch - 11ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 6.7386e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 4.7854e-05 - 172ms/epoch - 11ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 3.6505e-05 - 166ms/epoch - 11ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 1.1868e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 4.7032e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 4.8684e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 6.4169e-07 - 167ms/epoch - 11ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 8.9112e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 2.2087e-06 - 171ms/epoch - 11ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7f3b905221a0>"
]
},
"metadata": {},
"execution_count": 61
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "ac4ada6f-dbd3-489f-bf86-50e39930a430",
"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": 62,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 5ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7f3bb444e830>"
]
},
"metadata": {},
"execution_count": 62
},
{
"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": "a8f3fefd-f47b-4673-91cb-e9d84a46ec3d"
},
"execution_count": 63,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712631008.5725968\n",
"Tue Apr 9 02:50:08 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": "02fce619-b8c6-45c8-8d72-82f6638b18ac"
},
"execution_count": 64,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712631008.5779479\n",
"Tue Apr 9 02:50:08 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": 1896
},
"id": "95xed6YyDClf",
"outputId": "e5e7abc2-d221-4110-9a59-5fef44231d3a"
},
"execution_count": 65,
"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",
"327 1.000000\n",
"37 0.808517\n",
"239 0.659226\n",
"370 0.643038\n",
"377 0.507635\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 0.011634\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.001807\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.000115\n",
"1 0.002653\n",
"2 0.003782\n",
"Normalized Saliency Sum: Saliency 5.584382\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.076005\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 10.131322\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 108.065147\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.005777\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 653.293457\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000103\n",
"1 0.001187\n",
"2 0.001526\n",
"3 0.006046\n",
"4 0.006986\n",
".. ...\n",
"475 5.574471\n",
"476 5.579782\n",
"477 5.581948\n",
"478 5.583033\n",
"479 5.584383\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 2.146460e-07\n",
"1 2.472472e-06\n",
"2 3.179589e-06\n",
"3 1.259652e-05\n",
"4 1.455446e-05\n",
".. ...\n",
"475 1.161348e-02\n",
"476 1.162455e-02\n",
"477 1.162906e-02\n",
"478 1.163132e-02\n",
"479 1.163413e-02\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.07681198\n",
"Normalized Saliency 25th Percentile: Saliency 0.000769\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.003738\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.002969\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": "5a3d53b5-e0e1-4996-ed50-18553bde93b8"
},
"execution_count": 66,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712631010.4922264\n",
"Tue Apr 9 02:50:10 2024\n"
]
}
]
}
]
}