Datasets
Models
Downloads: 1
1259 lines (1259 with data), 217.5 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": 123,
"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": 124,
"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": "b06cc6b0-1dee-4a09-c097-297f1a8c8f0e",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
}
},
"source": [
"Dense = tf.keras.layers.Dense\n",
"tn_model = tf.keras.Sequential(\n",
" [\n",
" tf.keras.Input(shape=(2,)),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Start Modified Layers\n",
" TNLayer(),\n",
" TNLayer(),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 125,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_11\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_42 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_15 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_16 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_43 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_44 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_45 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 2113537 (8.06 MB)\n",
"Trainable params: 2113537 (8.06 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": 126,
"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": "f788f74f-7883-4933-d286-bd949b7154c4"
},
"execution_count": 127,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712561107.0984275\n",
"Mon Apr 8 07:25:07 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "68bdf6dd-2e24-4605-9a46-abb616fe8530",
"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": 128,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 2s - loss: 1.0020 - 2s/epoch - 131ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.7915 - 158ms/epoch - 11ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.1238 - 150ms/epoch - 10ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0277 - 150ms/epoch - 10ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0108 - 156ms/epoch - 10ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0052 - 150ms/epoch - 10ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0019 - 149ms/epoch - 10ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 7.6720e-04 - 142ms/epoch - 9ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 5.2343e-04 - 144ms/epoch - 10ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 3.6054e-04 - 148ms/epoch - 10ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 3.0049e-04 - 141ms/epoch - 9ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 1.5953e-04 - 148ms/epoch - 10ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 1.8894e-04 - 147ms/epoch - 10ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 2.0040e-04 - 141ms/epoch - 9ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 1.7671e-04 - 150ms/epoch - 10ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 4.0921e-05 - 150ms/epoch - 10ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 1.4973e-04 - 158ms/epoch - 11ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 4.5295e-05 - 147ms/epoch - 10ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 2.6020e-04 - 155ms/epoch - 10ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0013 - 145ms/epoch - 10ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 1.7270e-04 - 152ms/epoch - 10ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 2.7425e-04 - 146ms/epoch - 10ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 1.9242e-04 - 149ms/epoch - 10ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 1.1778e-04 - 150ms/epoch - 10ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 6.3529e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 3.5746e-05 - 141ms/epoch - 9ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 1.0884e-05 - 149ms/epoch - 10ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 7.4583e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 1.2631e-05 - 153ms/epoch - 10ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 1.1837e-05 - 148ms/epoch - 10ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 8.1876e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 3.7201e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 3.2778e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 4.3157e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 4.6620e-06 - 146ms/epoch - 10ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 4.7971e-06 - 150ms/epoch - 10ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 3.2447e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 6.5581e-06 - 151ms/epoch - 10ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 5.6497e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 2.4536e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 1.6673e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 1.6020e-06 - 153ms/epoch - 10ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 4.0979e-06 - 154ms/epoch - 10ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 1.2556e-05 - 148ms/epoch - 10ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 4.6836e-05 - 149ms/epoch - 10ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 2.5603e-05 - 148ms/epoch - 10ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 1.0680e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 1.0738e-05 - 145ms/epoch - 10ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 4.8077e-06 - 146ms/epoch - 10ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 1.8962e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 5.3369e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 7.0230e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 9.7217e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 1.5927e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 2.6750e-05 - 147ms/epoch - 10ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 4.3505e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 1.4415e-04 - 146ms/epoch - 10ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 6.5132e-05 - 153ms/epoch - 10ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 1.7954e-05 - 146ms/epoch - 10ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 2.4622e-05 - 144ms/epoch - 10ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 2.8019e-05 - 145ms/epoch - 10ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 2.5550e-05 - 148ms/epoch - 10ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 7.9987e-05 - 147ms/epoch - 10ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 3.8381e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 4.0362e-06 - 146ms/epoch - 10ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 3.9439e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 8.3448e-06 - 151ms/epoch - 10ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 7.9451e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 2.9216e-06 - 154ms/epoch - 10ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 3.1339e-06 - 150ms/epoch - 10ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 1.3730e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 5.7729e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 1.1362e-05 - 152ms/epoch - 10ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 8.0056e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 3.2465e-05 - 150ms/epoch - 10ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 1.4963e-04 - 147ms/epoch - 10ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 1.9904e-04 - 145ms/epoch - 10ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 3.5752e-04 - 151ms/epoch - 10ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 0.0013 - 150ms/epoch - 10ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 0.0011 - 144ms/epoch - 10ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 4.9574e-04 - 152ms/epoch - 10ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 2.1630e-04 - 156ms/epoch - 10ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 8.5289e-05 - 150ms/epoch - 10ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 1.9307e-05 - 146ms/epoch - 10ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 1.2945e-05 - 146ms/epoch - 10ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 8.2340e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 5.5479e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 4.9459e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 2.5212e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 7.9913e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 9.4400e-06 - 150ms/epoch - 10ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 4.3083e-06 - 151ms/epoch - 10ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 3.5116e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 5.3744e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 7.1351e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 2.3831e-05 - 156ms/epoch - 10ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 3.5289e-05 - 145ms/epoch - 10ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 2.0382e-05 - 140ms/epoch - 9ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 7.5679e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 6.5022e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 1.6155e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 8.5609e-07 - 144ms/epoch - 10ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 6.9965e-07 - 144ms/epoch - 10ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 5.6937e-07 - 146ms/epoch - 10ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 6.4351e-07 - 147ms/epoch - 10ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 5.8586e-07 - 144ms/epoch - 10ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 6.4083e-07 - 143ms/epoch - 10ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 8.6562e-07 - 149ms/epoch - 10ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 1.0245e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 1.1183e-06 - 146ms/epoch - 10ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 6.2941e-07 - 145ms/epoch - 10ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 2.7461e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 2.9410e-06 - 152ms/epoch - 10ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 1.5540e-06 - 146ms/epoch - 10ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 1.6576e-06 - 150ms/epoch - 10ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 7.2530e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 2.8367e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 2.4094e-06 - 150ms/epoch - 10ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 2.5772e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 3.8488e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 2.8943e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 1.9633e-06 - 151ms/epoch - 10ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 8.8876e-06 - 156ms/epoch - 10ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 5.0089e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 5.2256e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 9.8721e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 1.2486e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 4.6178e-05 - 144ms/epoch - 10ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 4.0590e-05 - 145ms/epoch - 10ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 4.6948e-05 - 148ms/epoch - 10ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 1.5828e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 3.5379e-05 - 150ms/epoch - 10ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 1.2993e-04 - 146ms/epoch - 10ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 7.8847e-05 - 146ms/epoch - 10ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 7.2647e-05 - 146ms/epoch - 10ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 9.4365e-05 - 149ms/epoch - 10ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 7.9640e-05 - 149ms/epoch - 10ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 1.6377e-05 - 145ms/epoch - 10ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 5.3090e-05 - 147ms/epoch - 10ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 1.0938e-04 - 149ms/epoch - 10ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 6.0478e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 5.9383e-05 - 148ms/epoch - 10ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 7.5149e-05 - 148ms/epoch - 10ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 5.3774e-05 - 152ms/epoch - 10ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 3.0293e-05 - 148ms/epoch - 10ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 9.5850e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 5.8682e-05 - 147ms/epoch - 10ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 1.6768e-04 - 146ms/epoch - 10ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 9.3678e-05 - 156ms/epoch - 10ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 1.6982e-04 - 153ms/epoch - 10ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 2.1079e-04 - 154ms/epoch - 10ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 4.6420e-04 - 145ms/epoch - 10ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 1.9785e-04 - 150ms/epoch - 10ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 2.3333e-04 - 147ms/epoch - 10ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 0.0058 - 149ms/epoch - 10ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 0.0493 - 148ms/epoch - 10ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 0.0241 - 146ms/epoch - 10ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 0.0155 - 146ms/epoch - 10ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 0.0087 - 146ms/epoch - 10ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 0.0083 - 147ms/epoch - 10ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 0.0026 - 148ms/epoch - 10ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 0.0012 - 146ms/epoch - 10ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 4.0404e-04 - 157ms/epoch - 10ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 2.4175e-04 - 140ms/epoch - 9ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 6.9572e-05 - 151ms/epoch - 10ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 2.6584e-05 - 149ms/epoch - 10ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 1.9478e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 1.5648e-05 - 149ms/epoch - 10ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 1.1392e-05 - 151ms/epoch - 10ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 9.0339e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 1.0190e-05 - 146ms/epoch - 10ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 1.1861e-05 - 150ms/epoch - 10ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 1.4994e-05 - 144ms/epoch - 10ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 1.0255e-05 - 141ms/epoch - 9ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 6.2868e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 6.1897e-06 - 152ms/epoch - 10ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 5.2543e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 7.6529e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 9.7367e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 7.2813e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 3.6905e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 2.1037e-06 - 150ms/epoch - 10ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 2.7643e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 2.6442e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 2.2913e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 3.2182e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 1.1813e-05 - 146ms/epoch - 10ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 4.6686e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 4.2465e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 6.6326e-06 - 146ms/epoch - 10ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 1.0115e-05 - 149ms/epoch - 10ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 8.2728e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 6.8500e-06 - 153ms/epoch - 10ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 3.2961e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 2.3300e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 1.2142e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 1.4094e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 9.2109e-07 - 153ms/epoch - 10ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 9.1551e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 1.4513e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 1.7969e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 8.1162e-06 - 153ms/epoch - 10ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 1.8648e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 1.6411e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 4.9382e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 2.3114e-06 - 146ms/epoch - 10ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 9.8217e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 9.6145e-07 - 146ms/epoch - 10ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 1.2861e-06 - 146ms/epoch - 10ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 9.2672e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 2.7359e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 1.3997e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 1.2846e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 1.4526e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 5.0326e-07 - 148ms/epoch - 10ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 6.3513e-07 - 154ms/epoch - 10ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 1.4537e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 2.4553e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 4.0657e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 1.6649e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 1.6504e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 2.2441e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 4.8286e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 1.6213e-05 - 144ms/epoch - 10ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 5.0270e-05 - 154ms/epoch - 10ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 5.3120e-04 - 144ms/epoch - 10ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 5.5035e-04 - 150ms/epoch - 10ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 9.0715e-05 - 141ms/epoch - 9ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 1.3638e-05 - 148ms/epoch - 10ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 6.5341e-06 - 146ms/epoch - 10ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 5.7804e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 4.2302e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 4.0557e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 3.8192e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 3.1390e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 1.7260e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 1.8157e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 6.2424e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 7.4977e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 6.3286e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 3.3012e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 4.8309e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 5.2071e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 1.8012e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 1.5492e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 2.5609e-06 - 155ms/epoch - 10ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 1.1462e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 3.1802e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 4.8115e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 1.3739e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 9.5208e-07 - 150ms/epoch - 10ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 1.1525e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 8.9706e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 7.1111e-07 - 151ms/epoch - 10ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 4.4885e-07 - 151ms/epoch - 10ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 5.6115e-07 - 147ms/epoch - 10ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 4.2501e-07 - 149ms/epoch - 10ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 4.6844e-07 - 146ms/epoch - 10ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 4.4277e-07 - 150ms/epoch - 10ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 5.7956e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 7.4995e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 6.6312e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 2.9675e-06 - 150ms/epoch - 10ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 2.3513e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 1.5893e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 8.2659e-07 - 144ms/epoch - 10ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 5.5583e-07 - 154ms/epoch - 10ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 7.3560e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 9.5596e-07 - 144ms/epoch - 10ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 4.8511e-07 - 144ms/epoch - 10ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 4.5261e-07 - 147ms/epoch - 10ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 3.6348e-07 - 147ms/epoch - 10ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 4.8439e-07 - 147ms/epoch - 10ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 6.4597e-07 - 148ms/epoch - 10ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 1.5233e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 2.4510e-06 - 155ms/epoch - 10ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 2.8530e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 1.0678e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 8.0567e-07 - 143ms/epoch - 10ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 1.5239e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 1.3948e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 5.2143e-07 - 145ms/epoch - 10ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 3.3183e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 6.6860e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 1.0729e-05 - 137ms/epoch - 9ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 2.7529e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 3.9164e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 3.3654e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 9.9511e-07 - 150ms/epoch - 10ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 2.2798e-07 - 145ms/epoch - 10ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 1.4156e-07 - 147ms/epoch - 10ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 2.2572e-07 - 144ms/epoch - 10ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 6.6754e-07 - 155ms/epoch - 10ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 7.1257e-07 - 146ms/epoch - 10ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 6.8351e-07 - 149ms/epoch - 10ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 2.9176e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 2.5688e-06 - 150ms/epoch - 10ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 5.2015e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 2.2481e-05 - 146ms/epoch - 10ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 3.0755e-05 - 152ms/epoch - 10ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x79196c2648e0>"
]
},
"metadata": {},
"execution_count": 128
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "7edae8f4-7768-446d-f03b-170c3d9a864a",
"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": 129,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 4ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x79196c267850>"
]
},
"metadata": {},
"execution_count": 129
},
{
"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": "ba7e78cc-73f1-4482-9a42-6d4d5c1de0ff"
},
"execution_count": 130,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712561154.3772473\n",
"Mon Apr 8 07:25:54 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": "6b900299-9ce5-472f-b59d-a7a069ca731b"
},
"execution_count": 131,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712561154.3828003\n",
"Mon Apr 8 07:25:54 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": "0aade148-0d58-4b5d-9612-58b330cc9ff4"
},
"execution_count": 132,
"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",
"239 1.000000\n",
"377 0.663916\n",
"327 0.282088\n",
"37 0.234294\n",
"39 0.082505\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 0.009797\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.00336\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.002085\n",
"Normalized Saliency Sum: Saliency 4.702757\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.057205\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 14.365909\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 224.50528\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.003272\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 583.876953\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.003742\n",
"1 0.004625\n",
"2 0.006122\n",
"3 0.009839\n",
"4 0.012592\n",
".. ...\n",
"475 4.676451\n",
"476 4.683421\n",
"477 4.694417\n",
"478 4.694821\n",
"479 4.702755\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000008\n",
"1 0.000010\n",
"2 0.000013\n",
"3 0.000020\n",
"4 0.000026\n",
".. ...\n",
"475 0.009743\n",
"476 0.009757\n",
"477 0.009780\n",
"478 0.009781\n",
"479 0.009797\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.057978995\n",
"Normalized Saliency 25th Percentile: Saliency 0.001243\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.006375\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.005132\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": "7528ebff-5fcb-49be-d615-ae5c6ad7021d"
},
"execution_count": 133,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712561156.127338\n",
"Mon Apr 8 07:25:56 2024\n"
]
}
]
}
]
}