Datasets
Models
Downloads: 1
1264 lines (1264 with data), 216.7 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": 134,
"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": 135,
"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": "886b1027-07b3-4721-dc50-0c170c05129b",
"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",
" Dense(1024, activation=tf.nn.relu),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 136,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_12\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_46 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_17 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_18 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_47 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_48 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_49 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_50 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 3163137 (12.07 MB)\n",
"Trainable params: 3163137 (12.07 MB)\n",
"Non-trainable params: 0 (0.00 Byte)\n",
"_________________________________________________________________\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "GWwoYp0WnsLA"
},
"source": [
"# Training a model\n",
"\n",
"You can train the TN model just as you would a normal neural network model! Here, we give an example of how to do it in Keras."
]
},
{
"cell_type": "code",
"metadata": {
"id": "qDFzOC7sDBJ-"
},
"source": [
"X = np.concatenate([np.random.randn(120, 2) + np.array([3, 3]),\n",
" np.random.randn(120, 2) + np.array([-3, -3]),\n",
" np.random.randn(120, 2) + np.array([-3, 3]),\n",
" np.random.randn(120, 2) + np.array([3, -3])])\n",
"\n",
"Y = np.concatenate([np.ones((240)), -np.ones((240))])"
],
"execution_count": 137,
"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": "b0cc412e-f5df-4332-8df1-54d4f12169ec"
},
"execution_count": 138,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712561470.95311\n",
"Mon Apr 8 07:31:10 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "47e95dc8-5d05-4a14-acb0-e2f5f5446364",
"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": 139,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 2s - loss: 1.0033 - 2s/epoch - 115ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.9178 - 205ms/epoch - 14ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.1321 - 191ms/epoch - 13ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0209 - 194ms/epoch - 13ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0086 - 201ms/epoch - 13ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0055 - 189ms/epoch - 13ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0053 - 192ms/epoch - 13ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0021 - 182ms/epoch - 12ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 6.6768e-04 - 184ms/epoch - 12ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0011 - 190ms/epoch - 13ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0045 - 191ms/epoch - 13ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0155 - 181ms/epoch - 12ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0081 - 191ms/epoch - 13ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0014 - 185ms/epoch - 12ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 2.7102e-04 - 185ms/epoch - 12ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 1.5033e-04 - 194ms/epoch - 13ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 6.1648e-05 - 193ms/epoch - 13ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 4.4335e-05 - 211ms/epoch - 14ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 2.6247e-05 - 189ms/epoch - 13ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 1.8451e-05 - 186ms/epoch - 12ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 1.4223e-05 - 193ms/epoch - 13ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 1.3243e-05 - 196ms/epoch - 13ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 1.2376e-05 - 192ms/epoch - 13ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 1.1365e-05 - 190ms/epoch - 13ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 1.4715e-05 - 189ms/epoch - 13ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 1.4610e-05 - 184ms/epoch - 12ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 9.2261e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 6.7453e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 4.8199e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 6.1287e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 4.4722e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 4.0875e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 3.8011e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 4.6474e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 3.3371e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 3.9395e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 3.9991e-06 - 201ms/epoch - 13ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 6.5775e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 6.7802e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 3.9398e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 3.1795e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 4.6821e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 4.0848e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 2.7282e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 1.9325e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 2.2299e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 3.1006e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 3.2220e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 1.8218e-06 - 204ms/epoch - 14ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 2.0165e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 2.5309e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 3.9885e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 4.3209e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 1.8049e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 1.6497e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 2.9088e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 2.6278e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 1.2238e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 1.0153e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 1.2164e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 9.1862e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 1.2848e-06 - 198ms/epoch - 13ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 1.1818e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 1.4579e-06 - 199ms/epoch - 13ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 2.6078e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 9.2720e-06 - 200ms/epoch - 13ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 3.5895e-06 - 202ms/epoch - 13ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 4.9880e-06 - 203ms/epoch - 14ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 3.0791e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 4.8907e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 9.2067e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 2.6209e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 1.4545e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 8.5117e-07 - 189ms/epoch - 13ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 3.6923e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 3.9750e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 2.7295e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 1.6709e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 3.5965e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 1.6080e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 3.1602e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 9.7868e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 4.6979e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 2.2685e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 2.9447e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 1.6739e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 2.4514e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 1.0381e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 1.1332e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 2.1230e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 1.6328e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 2.7224e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 1.3329e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 1.9609e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 6.0171e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 1.1765e-05 - 184ms/epoch - 12ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 1.9297e-05 - 190ms/epoch - 13ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 1.0131e-04 - 189ms/epoch - 13ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 3.2907e-05 - 191ms/epoch - 13ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 1.3758e-05 - 197ms/epoch - 13ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 1.5656e-05 - 190ms/epoch - 13ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 1.0039e-05 - 188ms/epoch - 13ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 3.0259e-05 - 186ms/epoch - 12ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 7.8586e-05 - 193ms/epoch - 13ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 8.2518e-05 - 197ms/epoch - 13ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 5.4721e-05 - 187ms/epoch - 12ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 5.7466e-05 - 189ms/epoch - 13ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 7.7604e-05 - 194ms/epoch - 13ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 2.3065e-04 - 191ms/epoch - 13ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 2.3807e-04 - 196ms/epoch - 13ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 7.3289e-05 - 190ms/epoch - 13ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 4.0741e-05 - 191ms/epoch - 13ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 3.8039e-05 - 192ms/epoch - 13ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 2.5900e-05 - 194ms/epoch - 13ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 5.3405e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 1.0237e-05 - 199ms/epoch - 13ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 5.8805e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 9.2035e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 4.9441e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 3.0909e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 1.3015e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 1.2851e-06 - 201ms/epoch - 13ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 4.8530e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 7.1625e-06 - 200ms/epoch - 13ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 6.9255e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 1.1201e-05 - 191ms/epoch - 13ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 6.8125e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 7.8351e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 8.1700e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 1.8187e-05 - 192ms/epoch - 13ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 1.0143e-05 - 196ms/epoch - 13ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 4.5677e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 1.4865e-05 - 192ms/epoch - 13ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 1.1751e-05 - 195ms/epoch - 13ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 7.0899e-06 - 203ms/epoch - 14ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 2.0140e-05 - 194ms/epoch - 13ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 2.4632e-05 - 189ms/epoch - 13ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 1.1951e-05 - 190ms/epoch - 13ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 2.3231e-05 - 196ms/epoch - 13ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 2.5968e-05 - 186ms/epoch - 12ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 5.0784e-05 - 194ms/epoch - 13ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 6.8826e-05 - 187ms/epoch - 12ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 5.3629e-05 - 195ms/epoch - 13ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 3.0255e-04 - 190ms/epoch - 13ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 7.0893e-04 - 198ms/epoch - 13ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 2.3946e-04 - 196ms/epoch - 13ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 3.9364e-04 - 187ms/epoch - 12ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 2.8381e-04 - 192ms/epoch - 13ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 3.2278e-04 - 187ms/epoch - 12ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 1.0901e-04 - 194ms/epoch - 13ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 8.2966e-05 - 193ms/epoch - 13ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 1.3149e-04 - 188ms/epoch - 13ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 7.9062e-05 - 205ms/epoch - 14ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 2.0771e-05 - 188ms/epoch - 13ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 2.7077e-05 - 203ms/epoch - 14ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 1.1881e-05 - 183ms/epoch - 12ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 3.6373e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 1.6395e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 2.4027e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 1.6911e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 7.9147e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 8.1906e-07 - 193ms/epoch - 13ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 6.7746e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 5.0695e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 5.2376e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 4.7035e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 6.8512e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 1.1127e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 7.5596e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 2.0156e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 4.4137e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 3.5395e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 2.3816e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 1.3771e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 1.0181e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 1.4872e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 1.1157e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 9.2607e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 1.0599e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 1.1511e-06 - 198ms/epoch - 13ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 1.3371e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 9.8376e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 1.3434e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 6.4092e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 6.7846e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 7.2655e-07 - 189ms/epoch - 13ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 3.2400e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 2.7961e-07 - 186ms/epoch - 12ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 6.2526e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 2.4514e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 5.2628e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 8.5572e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 5.7536e-05 - 187ms/epoch - 12ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 4.9806e-04 - 200ms/epoch - 13ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 0.0011 - 195ms/epoch - 13ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 0.0021 - 195ms/epoch - 13ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 4.1072e-04 - 189ms/epoch - 13ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 0.0524 - 198ms/epoch - 13ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 0.0335 - 191ms/epoch - 13ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 0.0269 - 199ms/epoch - 13ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 0.0291 - 188ms/epoch - 13ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 0.0181 - 193ms/epoch - 13ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 0.0053 - 197ms/epoch - 13ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 0.0057 - 193ms/epoch - 13ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 6.9766e-04 - 192ms/epoch - 13ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 4.7614e-04 - 196ms/epoch - 13ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 3.8999e-04 - 190ms/epoch - 13ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 3.7305e-04 - 195ms/epoch - 13ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 1.3468e-04 - 190ms/epoch - 13ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 4.8477e-05 - 195ms/epoch - 13ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 2.3540e-05 - 192ms/epoch - 13ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 1.3096e-05 - 189ms/epoch - 13ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 1.0967e-05 - 194ms/epoch - 13ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 9.1126e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 1.1345e-05 - 196ms/epoch - 13ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 9.9650e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 7.1240e-06 - 192ms/epoch - 13ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 6.1795e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 4.5006e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 4.2508e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 5.4038e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 5.5203e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 3.3948e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 2.9957e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 2.6392e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 2.7181e-06 - 198ms/epoch - 13ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 2.4576e-06 - 189ms/epoch - 13ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 3.6335e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 3.7561e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 6.5126e-06 - 198ms/epoch - 13ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 3.7408e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 3.1839e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 2.6279e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 2.9620e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 1.9269e-06 - 182ms/epoch - 12ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 2.2063e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 1.0373e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 1.5863e-06 - 188ms/epoch - 13ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 1.0715e-06 - 186ms/epoch - 12ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 1.7203e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 1.8744e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 1.2501e-06 - 191ms/epoch - 13ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 2.0699e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 1.1242e-06 - 183ms/epoch - 12ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 8.9338e-07 - 195ms/epoch - 13ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 6.5814e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 7.5146e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 7.4007e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 7.0143e-07 - 186ms/epoch - 12ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 8.5311e-07 - 197ms/epoch - 13ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 5.7629e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 9.3737e-07 - 190ms/epoch - 13ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 8.1168e-07 - 193ms/epoch - 13ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 1.0050e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 8.0461e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 5.1918e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 5.4603e-07 - 193ms/epoch - 13ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 9.1676e-07 - 195ms/epoch - 13ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 9.4585e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 1.0165e-06 - 185ms/epoch - 12ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 1.9075e-06 - 187ms/epoch - 12ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 1.4057e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 1.1767e-06 - 193ms/epoch - 13ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 1.3460e-06 - 194ms/epoch - 13ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 5.6627e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 7.1422e-07 - 197ms/epoch - 13ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 1.8139e-06 - 184ms/epoch - 12ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 1.0811e-06 - 190ms/epoch - 13ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 5.6713e-07 - 208ms/epoch - 14ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 5.1670e-07 - 204ms/epoch - 14ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 4.8577e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 4.6334e-07 - 190ms/epoch - 13ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 6.8964e-07 - 198ms/epoch - 13ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 6.3844e-07 - 191ms/epoch - 13ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 3.1782e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 2.2926e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 2.9913e-07 - 196ms/epoch - 13ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 6.2950e-07 - 192ms/epoch - 13ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 5.2784e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 6.5575e-07 - 198ms/epoch - 13ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 5.1862e-07 - 197ms/epoch - 13ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 6.4273e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 6.3952e-07 - 188ms/epoch - 13ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 8.8995e-07 - 198ms/epoch - 13ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 6.5779e-07 - 189ms/epoch - 13ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 2.1581e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 1.1341e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 3.3974e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 5.8249e-07 - 194ms/epoch - 13ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 9.1725e-07 - 200ms/epoch - 13ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 3.6017e-07 - 196ms/epoch - 13ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 1.2420e-06 - 197ms/epoch - 13ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 9.9730e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 2.4886e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 5.0001e-07 - 205ms/epoch - 14ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 4.5109e-07 - 200ms/epoch - 13ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 2.2460e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 1.4255e-06 - 195ms/epoch - 13ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 2.2532e-06 - 196ms/epoch - 13ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 7.1462e-07 - 205ms/epoch - 14ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x791974336890>"
]
},
"metadata": {},
"execution_count": 139
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "985ff8c8-89b4-421a-baf8-d39a4b4970d6",
"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": 140,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 5ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x791a7c298ac0>"
]
},
"metadata": {},
"execution_count": 140
},
{
"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": "60d2d118-bd7d-4184-f0d2-e3b6996452c6"
},
"execution_count": 141,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712561531.4977987\n",
"Mon Apr 8 07:32:11 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": "c1c528fe-2df0-4897-83e5-5dcbe32418f9"
},
"execution_count": 142,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712561531.5032427\n",
"Mon Apr 8 07:32:11 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": "199ee53a-089a-476e-beca-f4b4f61c42db"
},
"execution_count": 143,
"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",
"327 0.334242\n",
"377 0.192773\n",
"287 0.165684\n",
"307 0.138510\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 0.006895\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.001813\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.001046\n",
"1 0.001075\n",
"2 0.001423\n",
"Normalized Saliency Sum: Saliency 3.309649\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.049878\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 17.361063\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 333.871277\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.002488\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 723.385315\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.001970\n",
"1 0.004252\n",
"2 0.004787\n",
"3 0.009548\n",
"4 0.010252\n",
".. ...\n",
"475 3.304781\n",
"476 3.305652\n",
"477 3.305798\n",
"478 3.307041\n",
"479 3.309650\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000004\n",
"1 0.000009\n",
"2 0.000010\n",
"3 0.000020\n",
"4 0.000021\n",
".. ...\n",
"475 0.006885\n",
"476 0.006887\n",
"477 0.006887\n",
"478 0.006890\n",
"479 0.006895\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.05030099\n",
"Normalized Saliency 25th Percentile: Saliency 0.001146\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.003042\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.001896\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": "f072f960-1662-4fd5-8716-fa7db2f9d5e1"
},
"execution_count": 144,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712561533.4322658\n",
"Mon Apr 8 07:32:13 2024\n"
]
}
]
}
]
}