Datasets
Models
Downloads: 1
1264 lines (1264 with data), 218.2 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": 23,
"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": 24,
"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": "05def613-d954-4eb5-cd93-d085c2373707",
"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",
" TNLayer(),\n",
" TNLayer(),\n",
" TNLayer(),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 25,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_2\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_6 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_7 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_8 (Dense) (None, 1024) 1049600 \n",
" \n",
" tn_layer_6 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_7 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_8 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_9 (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": 26,
"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": "a7d1ca3a-46b8-48ce-f935-dea6a4d9d97e"
},
"execution_count": 27,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712629940.1783888\n",
"Tue Apr 9 02:32:20 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "de3f38f4-69a2-460c-90b6-bce153abde5a",
"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": 28,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 2s - loss: 1.0022 - 2s/epoch - 124ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.9714 - 203ms/epoch - 14ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.2879 - 192ms/epoch - 13ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0658 - 194ms/epoch - 13ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0306 - 198ms/epoch - 13ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0237 - 200ms/epoch - 13ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0175 - 183ms/epoch - 12ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0141 - 189ms/epoch - 13ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0114 - 194ms/epoch - 13ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0095 - 196ms/epoch - 13ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0075 - 196ms/epoch - 13ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0050 - 190ms/epoch - 13ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0037 - 186ms/epoch - 12ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0025 - 178ms/epoch - 12ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0014 - 187ms/epoch - 12ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 9.3710e-04 - 180ms/epoch - 12ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 4.7291e-04 - 187ms/epoch - 12ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 1.9578e-04 - 190ms/epoch - 13ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 1.1642e-04 - 188ms/epoch - 13ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 5.8838e-05 - 183ms/epoch - 12ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 4.2233e-05 - 178ms/epoch - 12ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 2.9194e-05 - 180ms/epoch - 12ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 2.2990e-05 - 174ms/epoch - 12ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 1.9112e-05 - 180ms/epoch - 12ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 1.6520e-05 - 183ms/epoch - 12ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 1.3095e-05 - 178ms/epoch - 12ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 1.2363e-05 - 186ms/epoch - 12ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 9.3156e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 7.7649e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 6.7188e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 6.0144e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 5.5125e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 4.9232e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 4.5917e-06 - 182ms/epoch - 12ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 3.9958e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 3.6195e-06 - 177ms/epoch - 12ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 3.1650e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 2.8294e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 2.9301e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 2.9330e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 2.3342e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 2.3136e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 2.1164e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 2.0664e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 1.9419e-06 - 182ms/epoch - 12ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 1.7436e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 1.6167e-06 - 182ms/epoch - 12ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 2.8198e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 2.2268e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 1.6524e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 1.4682e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 1.5692e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 1.2514e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 1.3724e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 1.5569e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 1.3366e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 1.4053e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 1.2161e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 1.0351e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 1.0470e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 9.8917e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 1.7652e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 1.9547e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 1.5307e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 1.2045e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 8.7345e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 6.4293e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 7.1291e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 6.9278e-07 - 183ms/epoch - 12ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 5.9323e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 6.1680e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 7.1266e-07 - 186ms/epoch - 12ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 8.0238e-07 - 186ms/epoch - 12ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 9.3324e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 2.5461e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 9.0649e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 5.3277e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 6.0030e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 5.9575e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 4.5786e-07 - 189ms/epoch - 13ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 4.3946e-07 - 183ms/epoch - 12ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 4.7665e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 5.7856e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 9.7546e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 4.8107e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 1.4288e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 2.4854e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 2.8817e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 6.5616e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 9.2096e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 9.1320e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 3.2761e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 2.7073e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 3.9090e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 1.3494e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 3.0730e-06 - 182ms/epoch - 12ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 2.7273e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 1.0542e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 5.0552e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 9.4608e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 2.8478e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 2.8777e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 4.1077e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 6.5449e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 9.8169e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 8.3185e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 7.9624e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 6.9245e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 5.9953e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 3.8752e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 2.1772e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 3.5090e-07 - 193ms/epoch - 13ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 2.0909e-07 - 198ms/epoch - 13ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 1.5947e-07 - 186ms/epoch - 12ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 3.3252e-07 - 183ms/epoch - 12ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 4.4633e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 7.8059e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 6.9987e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 2.6816e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 2.0077e-07 - 195ms/epoch - 13ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 1.9770e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 5.2671e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 1.6969e-06 - 182ms/epoch - 12ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 1.8220e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 4.8062e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 5.8127e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 7.2577e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 1.6372e-05 - 182ms/epoch - 12ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 9.7718e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 5.6017e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 8.4733e-07 - 190ms/epoch - 13ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 1.1204e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 1.3494e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 4.3734e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 6.4699e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 7.0331e-07 - 198ms/epoch - 13ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 9.1589e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 2.0491e-07 - 193ms/epoch - 13ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 3.7111e-07 - 195ms/epoch - 13ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 2.6855e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 2.7768e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 1.8377e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 3.9944e-07 - 186ms/epoch - 12ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 1.4875e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 2.3953e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 1.2687e-05 - 195ms/epoch - 13ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 2.1260e-04 - 180ms/epoch - 12ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 1.5486e-04 - 175ms/epoch - 12ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 4.2887e-05 - 174ms/epoch - 12ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 3.5735e-05 - 184ms/epoch - 12ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 6.9873e-05 - 174ms/epoch - 12ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 1.6665e-04 - 180ms/epoch - 12ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 6.1745e-05 - 186ms/epoch - 12ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 1.0368e-05 - 187ms/epoch - 12ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 1.0835e-05 - 177ms/epoch - 12ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 5.5021e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 2.0903e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 2.4597e-06 - 199ms/epoch - 13ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 1.9417e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 2.3758e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 1.6433e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 8.5019e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 7.5389e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 6.0556e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 7.7087e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 3.6518e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 1.5163e-07 - 190ms/epoch - 13ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 1.5061e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 3.2341e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 4.3565e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 9.4640e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 1.1277e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 7.9090e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 1.2067e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 8.4814e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 1.1449e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 1.4354e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 7.6716e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 6.6195e-07 - 189ms/epoch - 13ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 3.9804e-07 - 195ms/epoch - 13ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 7.6050e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 2.3291e-07 - 189ms/epoch - 13ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 6.2144e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 2.3666e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 1.4195e-07 - 183ms/epoch - 12ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 7.1239e-08 - 187ms/epoch - 12ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 1.6836e-07 - 186ms/epoch - 12ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 1.8393e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 3.9540e-07 - 186ms/epoch - 12ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 1.7378e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 9.5098e-08 - 187ms/epoch - 12ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 1.0033e-07 - 193ms/epoch - 13ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 4.2952e-07 - 169ms/epoch - 11ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 1.3348e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 9.9904e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 5.4415e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 3.7662e-05 - 176ms/epoch - 12ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 2.0023e-05 - 178ms/epoch - 12ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 1.2560e-05 - 177ms/epoch - 12ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 1.2256e-05 - 178ms/epoch - 12ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 2.4146e-05 - 175ms/epoch - 12ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 1.3955e-05 - 186ms/epoch - 12ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 1.7680e-05 - 171ms/epoch - 11ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 1.1552e-05 - 180ms/epoch - 12ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 1.0571e-05 - 174ms/epoch - 12ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 1.3213e-05 - 177ms/epoch - 12ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 1.2697e-05 - 181ms/epoch - 12ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 2.7120e-05 - 177ms/epoch - 12ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 3.8395e-05 - 178ms/epoch - 12ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 3.6244e-05 - 176ms/epoch - 12ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 1.9379e-05 - 176ms/epoch - 12ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 6.2968e-06 - 177ms/epoch - 12ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 5.1682e-06 - 179ms/epoch - 12ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 1.9999e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 2.2567e-05 - 181ms/epoch - 12ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 5.5964e-05 - 181ms/epoch - 12ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 2.8802e-05 - 171ms/epoch - 11ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 2.1819e-05 - 176ms/epoch - 12ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 2.9745e-05 - 180ms/epoch - 12ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 6.3160e-05 - 182ms/epoch - 12ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 1.3207e-04 - 172ms/epoch - 11ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 3.8192e-05 - 183ms/epoch - 12ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 4.5925e-05 - 184ms/epoch - 12ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 0.0099 - 188ms/epoch - 13ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 0.0341 - 178ms/epoch - 12ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 0.1355 - 187ms/epoch - 12ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 0.0295 - 179ms/epoch - 12ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 0.0032 - 183ms/epoch - 12ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 9.6314e-04 - 185ms/epoch - 12ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 1.9116e-04 - 181ms/epoch - 12ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 5.3936e-05 - 173ms/epoch - 12ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 2.4685e-05 - 182ms/epoch - 12ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 1.7774e-05 - 194ms/epoch - 13ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 1.4536e-05 - 185ms/epoch - 12ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 1.1199e-05 - 176ms/epoch - 12ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 9.5029e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 7.9136e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 6.5559e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 5.4792e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 4.7445e-06 - 204ms/epoch - 14ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 4.1857e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 4.1581e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 3.7636e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 3.4627e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 3.3466e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 2.8818e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 2.3804e-06 - 199ms/epoch - 13ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 2.7664e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 2.6447e-06 - 182ms/epoch - 12ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 2.0634e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 2.2230e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 2.0175e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 1.6657e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 1.6039e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 1.5712e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 1.5693e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 1.6967e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 1.4277e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 1.1047e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 1.1181e-06 - 177ms/epoch - 12ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 1.1664e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 1.1199e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 1.1244e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 1.0937e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 9.3547e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 8.3833e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 7.7275e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 8.5268e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 8.0390e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 8.0706e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 6.8616e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 7.3308e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 6.4985e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 6.2093e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 6.6741e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 6.6645e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 5.5611e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 5.3500e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 4.9534e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 4.8777e-07 - 183ms/epoch - 12ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 5.1035e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 4.5268e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 4.5161e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 4.5913e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 4.3723e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 6.3223e-07 - 189ms/epoch - 13ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 7.7186e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 6.4962e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 4.1669e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 3.9077e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 4.1543e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 3.3478e-07 - 190ms/epoch - 13ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 3.4887e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 3.5674e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 4.0069e-07 - 183ms/epoch - 12ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 3.5376e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 3.1908e-07 - 183ms/epoch - 12ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 2.8526e-07 - 183ms/epoch - 12ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 3.0754e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 4.4547e-07 - 186ms/epoch - 12ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7f3b005ea860>"
]
},
"metadata": {},
"execution_count": 28
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "1e71b4a6-3a48-4655-ce4f-1e55346937b6",
"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": 29,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 5ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7f3b90623a00>"
]
},
"metadata": {},
"execution_count": 29
},
{
"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": "426998b2-dd2a-4af2-b8e8-ee476c475566"
},
"execution_count": 30,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712629998.31826\n",
"Tue Apr 9 02:33:18 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": "e1533d9c-4f17-48b3-fd42-9bfd269cbc50"
},
"execution_count": 31,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712629998.323425\n",
"Tue Apr 9 02:33:18 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": "0459cdd0-7b39-48ff-f9f7-895443145df2"
},
"execution_count": 32,
"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",
"377 0.944056\n",
"327 0.680874\n",
"239 0.545190\n",
"110 0.327877\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 0.014081\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.004313\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.001341\n",
"1 0.005709\n",
"2 0.013164\n",
"Normalized Saliency Sum: Saliency 6.758774\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.075489\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 10.919455\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 125.86824\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.005699\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 536.112976\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.008406\n",
"1 0.009860\n",
"2 0.015671\n",
"3 0.017351\n",
"4 0.019602\n",
".. ...\n",
"475 6.744834\n",
"476 6.745667\n",
"477 6.750444\n",
"478 6.756214\n",
"479 6.758774\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000018\n",
"1 0.000021\n",
"2 0.000033\n",
"3 0.000036\n",
"4 0.000041\n",
".. ...\n",
"475 0.014052\n",
"476 0.014053\n",
"477 0.014063\n",
"478 0.014075\n",
"479 0.014081\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.07671354\n",
"Normalized Saliency 25th Percentile: Saliency 0.002388\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.007621\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.005233\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": "438463c4-f0d4-467f-9148-b5d391d8f476"
},
"execution_count": 33,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712630000.346787\n",
"Tue Apr 9 02:33:20 2024\n"
]
}
]
}
]
}