Datasets
Models
Downloads: 1
1269 lines (1269 with data), 218.0 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": 100,
"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": 101,
"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": "b7077cda-ba6a-41b6-f4aa-c0d7b892c1db",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
}
},
"source": [
"Dense = tf.keras.layers.Dense\n",
"tn_model = tf.keras.Sequential(\n",
" [\n",
" tf.keras.Input(shape=(2,)),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Start Modified Layers\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 102,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_9\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_34 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_35 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_36 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_37 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_38 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 3152897 (12.03 MB)\n",
"Trainable params: 3152897 (12.03 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": 103,
"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": "99485d7a-a353-4ddb-a964-facc68382661"
},
"execution_count": 104,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712633174.7803848\n",
"Tue Apr 9 03:26:14 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "9446e419-53be-4f66-9ba9-3800726423b0",
"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": 105,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 0.3129 - 904ms/epoch - 60ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.0821 - 182ms/epoch - 12ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.0743 - 177ms/epoch - 12ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0664 - 180ms/epoch - 12ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0540 - 178ms/epoch - 12ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0513 - 182ms/epoch - 12ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0410 - 176ms/epoch - 12ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0437 - 173ms/epoch - 12ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0305 - 178ms/epoch - 12ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0245 - 174ms/epoch - 12ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0280 - 171ms/epoch - 11ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0205 - 167ms/epoch - 11ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0108 - 168ms/epoch - 11ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0056 - 166ms/epoch - 11ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0032 - 168ms/epoch - 11ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0019 - 167ms/epoch - 11ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0012 - 168ms/epoch - 11ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 3.9303e-04 - 172ms/epoch - 11ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 2.6649e-04 - 174ms/epoch - 12ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 1.4816e-04 - 180ms/epoch - 12ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 1.2451e-04 - 182ms/epoch - 12ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 6.0767e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 9.0989e-05 - 166ms/epoch - 11ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 8.5368e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 1.0623e-04 - 176ms/epoch - 12ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 1.2329e-04 - 172ms/epoch - 11ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 6.8007e-05 - 170ms/epoch - 11ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 2.5893e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 1.8737e-05 - 170ms/epoch - 11ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 1.6825e-05 - 165ms/epoch - 11ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 9.4271e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 1.1994e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 1.0492e-05 - 167ms/epoch - 11ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 1.3646e-05 - 164ms/epoch - 11ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 1.0874e-05 - 170ms/epoch - 11ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 5.7333e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 7.1466e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 1.0837e-05 - 172ms/epoch - 11ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 1.5098e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 1.5376e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 1.3336e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 1.0755e-05 - 167ms/epoch - 11ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 9.6123e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 3.0869e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 7.8780e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 3.6055e-05 - 173ms/epoch - 12ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 3.1711e-05 - 174ms/epoch - 12ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 8.9389e-06 - 171ms/epoch - 11ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 1.0313e-05 - 166ms/epoch - 11ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 1.2650e-05 - 167ms/epoch - 11ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 2.9976e-05 - 166ms/epoch - 11ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 9.0105e-04 - 164ms/epoch - 11ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 0.0015 - 163ms/epoch - 11ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 6.8964e-04 - 170ms/epoch - 11ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 4.8655e-04 - 166ms/epoch - 11ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 1.2103e-04 - 164ms/epoch - 11ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 2.6543e-04 - 165ms/epoch - 11ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 3.9405e-04 - 168ms/epoch - 11ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 2.9355e-04 - 166ms/epoch - 11ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 4.5794e-04 - 168ms/epoch - 11ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 2.1942e-04 - 167ms/epoch - 11ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 1.4274e-04 - 171ms/epoch - 11ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 8.6461e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 2.7214e-05 - 170ms/epoch - 11ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 3.5646e-05 - 171ms/epoch - 11ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 2.1074e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 1.3284e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 1.3007e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 1.4209e-05 - 170ms/epoch - 11ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 7.3360e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 9.1099e-06 - 171ms/epoch - 11ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 2.1326e-05 - 167ms/epoch - 11ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 8.9637e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 5.0583e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 5.7580e-06 - 164ms/epoch - 11ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 3.6805e-06 - 164ms/epoch - 11ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 2.7315e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 2.0124e-06 - 164ms/epoch - 11ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 1.6169e-05 - 164ms/epoch - 11ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 7.3213e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 6.4119e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 5.5034e-06 - 177ms/epoch - 12ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 2.2754e-06 - 180ms/epoch - 12ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 3.7296e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 4.1840e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 4.1317e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 3.6978e-06 - 177ms/epoch - 12ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 2.1903e-06 - 171ms/epoch - 11ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 7.5042e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 1.4010e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 1.8029e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 1.7865e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 4.3752e-06 - 181ms/epoch - 12ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 5.2027e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 6.0753e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 2.0583e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 1.2788e-05 - 167ms/epoch - 11ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 6.1865e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 4.7876e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 1.8908e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 1.4447e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 5.1088e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 5.7102e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 6.6118e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 9.4756e-06 - 164ms/epoch - 11ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 2.2284e-05 - 166ms/epoch - 11ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 3.1444e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 6.3151e-05 - 167ms/epoch - 11ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 4.1739e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 2.3663e-05 - 167ms/epoch - 11ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 1.4809e-05 - 163ms/epoch - 11ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 4.0588e-05 - 173ms/epoch - 12ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 4.9957e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 2.6121e-05 - 166ms/epoch - 11ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 2.5204e-05 - 168ms/epoch - 11ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 8.4306e-05 - 163ms/epoch - 11ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 7.3343e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 2.2788e-04 - 168ms/epoch - 11ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 2.5868e-04 - 167ms/epoch - 11ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 8.7751e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 1.4428e-04 - 169ms/epoch - 11ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 1.0677e-04 - 170ms/epoch - 11ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 2.9259e-04 - 172ms/epoch - 11ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 2.9114e-04 - 171ms/epoch - 11ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 8.9835e-05 - 170ms/epoch - 11ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 1.2822e-04 - 170ms/epoch - 11ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 1.7135e-04 - 171ms/epoch - 11ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 2.0094e-04 - 168ms/epoch - 11ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 9.9319e-05 - 170ms/epoch - 11ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 2.9646e-04 - 167ms/epoch - 11ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 2.0150e-04 - 169ms/epoch - 11ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 5.3238e-04 - 176ms/epoch - 12ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 4.2158e-04 - 171ms/epoch - 11ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 2.1316e-04 - 175ms/epoch - 12ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 2.5043e-04 - 174ms/epoch - 12ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 2.1416e-04 - 175ms/epoch - 12ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 1.6230e-04 - 173ms/epoch - 12ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 1.0854e-04 - 179ms/epoch - 12ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 6.9214e-05 - 169ms/epoch - 11ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 3.2587e-05 - 171ms/epoch - 11ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 9.0390e-06 - 163ms/epoch - 11ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 5.3025e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 5.6772e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 5.1560e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 7.4986e-06 - 164ms/epoch - 11ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 4.0080e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 3.6362e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 2.5868e-06 - 175ms/epoch - 12ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 2.1023e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 1.3896e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 2.3456e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 3.1856e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 1.6373e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 1.2294e-06 - 176ms/epoch - 12ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 6.3806e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 3.0773e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 3.9064e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 6.0712e-07 - 167ms/epoch - 11ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 3.0016e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 6.4882e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 1.0030e-05 - 167ms/epoch - 11ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 5.4283e-05 - 166ms/epoch - 11ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 2.7639e-04 - 165ms/epoch - 11ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 4.2993e-04 - 167ms/epoch - 11ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 0.0407 - 170ms/epoch - 11ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 0.0642 - 177ms/epoch - 12ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 0.0384 - 169ms/epoch - 11ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 0.0129 - 177ms/epoch - 12ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 0.0024 - 172ms/epoch - 11ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 7.8259e-04 - 174ms/epoch - 12ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 2.3529e-04 - 171ms/epoch - 11ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 8.9532e-05 - 175ms/epoch - 12ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 3.5139e-05 - 175ms/epoch - 12ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 1.9162e-05 - 167ms/epoch - 11ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 1.2984e-05 - 173ms/epoch - 12ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 8.3575e-06 - 178ms/epoch - 12ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 6.1381e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 5.8063e-06 - 168ms/epoch - 11ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 5.0477e-06 - 169ms/epoch - 11ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 3.8143e-06 - 164ms/epoch - 11ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 3.0845e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 2.8440e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 3.6724e-06 - 174ms/epoch - 12ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 3.4034e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 1.7791e-06 - 167ms/epoch - 11ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 1.5948e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 1.3475e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 1.3793e-06 - 170ms/epoch - 11ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 1.2948e-06 - 171ms/epoch - 11ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 9.8064e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 8.5661e-07 - 166ms/epoch - 11ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 9.4081e-07 - 162ms/epoch - 11ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 8.6118e-07 - 162ms/epoch - 11ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 7.0163e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 9.9287e-07 - 166ms/epoch - 11ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 1.2152e-06 - 166ms/epoch - 11ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 6.8423e-07 - 168ms/epoch - 11ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 5.1636e-07 - 169ms/epoch - 11ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 5.8150e-07 - 166ms/epoch - 11ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 5.7625e-07 - 168ms/epoch - 11ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 5.6905e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 4.9822e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 6.3110e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 7.1131e-07 - 162ms/epoch - 11ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 1.2635e-06 - 172ms/epoch - 11ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 1.2899e-06 - 173ms/epoch - 12ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 8.6655e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 8.8316e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 6.4372e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 3.4622e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 3.3552e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 5.7489e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 5.5515e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 4.4923e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 6.6234e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 3.4913e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 2.1660e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 2.1719e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 1.9163e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 2.0763e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 2.0229e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 2.8579e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 2.5031e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 2.3156e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.6779e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 1.8278e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 3.2601e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 3.0056e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 2.5066e-07 - 185ms/epoch - 12ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 1.7889e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 1.7295e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 1.9398e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 3.0888e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 6.7689e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 2.6117e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 2.0628e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 1.9240e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 1.9141e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 1.6457e-07 - 180ms/epoch - 12ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 1.8261e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 1.5342e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 2.0140e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 1.5765e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 1.7748e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 1.4614e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 9.2049e-08 - 174ms/epoch - 12ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 1.0276e-07 - 182ms/epoch - 12ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 1.4615e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 1.6329e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 2.3018e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 2.5334e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 1.6156e-07 - 187ms/epoch - 12ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 1.4386e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 1.5762e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 1.4624e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 1.0395e-07 - 184ms/epoch - 12ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 9.0840e-08 - 170ms/epoch - 11ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 9.3985e-08 - 170ms/epoch - 11ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 2.0403e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 3.6892e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 1.9164e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 1.4067e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 1.3199e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 1.0312e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 1.1358e-07 - 167ms/epoch - 11ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 2.1280e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 2.5142e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 2.4965e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 5.9151e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 4.1257e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 1.6031e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 1.0259e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 1.2326e-07 - 173ms/epoch - 12ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 1.4645e-07 - 165ms/epoch - 11ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 1.4304e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 3.0798e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 3.8023e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 2.5953e-07 - 179ms/epoch - 12ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 2.9112e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 3.1493e-07 - 172ms/epoch - 11ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 2.3892e-07 - 168ms/epoch - 11ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 1.3574e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 9.7516e-08 - 170ms/epoch - 11ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 8.6057e-08 - 174ms/epoch - 12ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 1.0093e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 1.9721e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 9.5594e-08 - 167ms/epoch - 11ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 1.1838e-07 - 170ms/epoch - 11ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 2.5045e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 3.1204e-07 - 171ms/epoch - 11ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 1.4525e-07 - 176ms/epoch - 12ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 2.2537e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 3.0503e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 1.9329e-07 - 181ms/epoch - 12ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 5.7129e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 5.0296e-07 - 177ms/epoch - 12ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 2.6444e-07 - 178ms/epoch - 12ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 2.8194e-07 - 174ms/epoch - 12ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 2.0979e-07 - 175ms/epoch - 12ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 2.6676e-06 - 166ms/epoch - 11ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7f3a187cead0>"
]
},
"metadata": {},
"execution_count": 105
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "b22ad39b-bf51-45bf-b601-efea059e1eca",
"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": 106,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 3ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7f3a184eaef0>"
]
},
"metadata": {},
"execution_count": 106
},
{
"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": "d4a81c81-def0-479f-8605-c0c3f55545da"
},
"execution_count": 107,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712633228.124665\n",
"Tue Apr 9 03:27:08 2024\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"seconds = time.time()\n",
"print(\"Time in seconds since beginning of run:\", seconds)\n",
"local_time = time.ctime(seconds)\n",
"print(local_time)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"id": "o8HTyvcHchzQ",
"outputId": "2f933bb9-7219-4909-c4c3-06d05353cd01"
},
"execution_count": 108,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712633228.1315792\n",
"Tue Apr 9 03:27:08 2024\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Function to compute saliency map\n",
"@tf.function\n",
"def compute_saliency(input_image):\n",
" with tf.GradientTape() as tape:\n",
" tape.watch(input_image)\n",
" predictions = tn_model(input_image)\n",
" grads = tape.gradient(predictions, input_image)\n",
" saliency_map = tf.reduce_max(tf.abs(grads), axis=-1)\n",
" return saliency_map\n",
"\n",
"# Function to compute saliency map using Gradient\n",
"@tf.function\n",
"def compute_gradient_saliency(input_image):\n",
" with tf.GradientTape() as tape:\n",
" tape.watch(input_image)\n",
" predictions = tn_model(input_image)\n",
" grads = tape.gradient(predictions, input_image)\n",
" saliency_map = tf.reduce_max(tf.abs(grads), axis=-1)\n",
" return saliency_map\n",
"\n",
"# Compute saliency map for the entire grid\n",
"def compute_saliency_map_grid():\n",
" xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))\n",
" input_image = np.c_[xx.ravel(), yy.ravel()]\n",
" saliency_map = compute_saliency(tf.constant(input_image, dtype=tf.float32)).numpy()\n",
" saliency_map = saliency_map.reshape(xx.shape)\n",
" return xx, yy, saliency_map\n",
"\n",
"# Compute and plot saliency map for the entire grid\n",
"xx, yy, saliency_map = compute_saliency_map_grid()\n",
"\n",
"# Compute saliency maps for all data points\n",
"def compute_saliency_maps():\n",
" saliency_maps = []\n",
" for data_point in X:\n",
" saliency_map = compute_gradient_saliency(tf.constant(data_point[None, :], dtype=tf.float32)).numpy()\n",
" saliency_maps.append(saliency_map)\n",
" return saliency_maps\n",
"\n",
"# Find the indices of the data points with the highest saliency values\n",
"def find_top_indices(saliency_maps, top_k):\n",
" top_indices = np.argsort(np.max(saliency_maps, axis=1))[-top_k:]\n",
" return top_indices\n",
"\n",
"def plot_most_diagnostic(top_indices, top_k, normalized_saliency_values):\n",
" plt.figure(figsize=(8, 6))\n",
" plt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired)\n",
" plt.scatter(X[top_indices, 0], X[top_indices, 1], marker='o', s=200, facecolors='none', edgecolors='r', linewidths=2)\n",
" for i, index in enumerate(top_indices):\n",
" plt.annotate(f'{normalized_saliency_values.iloc[index][\"Saliency\"]:.4f}', (X[index, 0], X[index, 1]), xytext=(X[index, 0]+0.35, X[index, 1]+0.25), arrowprops=dict(facecolor='black', arrowstyle='->'))\n",
" plt.title(f'Saliency Most Diagnostic Data Points (Top {top_k})')\n",
" plt.xlabel('Feature 1')\n",
" plt.ylabel('Feature 2')\n",
" plt.grid(True)\n",
" plt.axis('equal')\n",
" plt.show()\n",
"\n",
"# Compute saliency maps for all data points\n",
"saliency_maps = compute_saliency_maps()\n",
"\n",
"# Find the indices of the data points with the highest saliency values\n",
"top_k = 5 # Number of top diagnostic data points to select\n",
"top_indices = find_top_indices(saliency_maps, top_k)\n",
"\n",
"# Create a DataFrame to store the saliency values\n",
"saliency_df = pd.DataFrame(data=saliency_maps, columns=[\"Saliency\"])\n",
"\n",
"# Save the saliency values to a CSV file\n",
"saliency_df.to_csv(\"saliency_values.csv\", index=False)\n",
"\n",
"print(\"Saliency values saved to saliency_values.csv\")\n",
"\n",
"# Normalizing the saliency values\n",
"normalized_saliency = (saliency_df - saliency_df.min()) / (saliency_df.max() - saliency_df.min())\n",
"\n",
"# Saving the normalized saliency values to a new CSV file\n",
"normalized_saliency.to_csv(\"normalized_saliency_values.csv\", index=False)\n",
"\n",
"# Plot the most diagnostic data points\n",
"plot_most_diagnostic(top_indices, top_k, normalized_saliency)\n",
"\n",
"print(\"Normalized saliency values saved to normalized_saliency_values.csv\")\n",
"print(\"Normalized Saliency Top-k:\")\n",
"print(normalized_saliency.nlargest(top_k, 'Saliency'))\n",
"print(\"Normalized Saliency Max:\", normalized_saliency.max())\n",
"print(\"Normalized Saliency Min:\", normalized_saliency.min())\n",
"print(\"Normalized Saliency Mean:\", normalized_saliency.mean())\n",
"print(\"Normalized Saliency Median:\", normalized_saliency.median())\n",
"print(\"Normalized Saliency Mode:\", normalized_saliency.mode())\n",
"sum_normalized_values = normalized_saliency.sum()\n",
"print(\"Normalized Saliency Sum:\", sum_normalized_values)\n",
"print(\"#\")\n",
"print(\"#\")\n",
"print(\"#\")\n",
"print(\"Normalized Saliency Standard Deviation:\", normalized_saliency.std())\n",
"print(\"Normalized Saliency Skewness:\", normalized_saliency.skew())\n",
"print(\"Normalized Saliency Kurtosis:\", normalized_saliency.kurtosis())\n",
"print(\"Normalized Saliency Variance:\", normalized_saliency.var())\n",
"coefficient_variation = (normalized_saliency.std() / normalized_saliency.mean()) * 100\n",
"print(\"Normalized Saliency Coefficient of Variation:\", coefficient_variation)\n",
"print(\"#\")\n",
"print(\"#\")\n",
"print(\"#\")\n",
"cumulative_sum = normalized_saliency.cumsum()\n",
"print(\"Cumulative Sum of Normalized Saliency Values:\", cumulative_sum)\n",
"mean_cumulative_sum = cumulative_sum / len(normalized_saliency)\n",
"print(\"Mean of Cumulative Sum of Normalized Saliency Values:\", mean_cumulative_sum)\n",
"rms = np.sqrt(np.mean(normalized_saliency**2))\n",
"print(\"Normalized Saliency Root Mean Square:\", rms)\n",
"q1 = normalized_saliency.quantile(0.25)\n",
"q2 = normalized_saliency.quantile(0.75)\n",
"iqr = q2 - q1\n",
"print(\"Normalized Saliency 25th Percentile:\", q1)\n",
"print(\"Normalized Saliency 75th Percentile:\", q2)\n",
"print(\"Normalized Saliency Interquartile Range:\", iqr)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 2098
},
"id": "95xed6YyDClf",
"outputId": "2f5a2f28-263a-4326-8d2d-4aeae97ea138"
},
"execution_count": 109,
"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 0.989049\n",
"287 0.371257\n",
"37 0.337966\n",
"423 0.330760\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 0.014254\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.004431\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.000775\n",
"1 0.001101\n",
"2 0.001757\n",
"3 0.001858\n",
"4 0.002013\n",
"5 0.002296\n",
"6 0.002296\n",
"7 0.002651\n",
"8 0.004055\n",
"9 0.005099\n",
"10 0.005134\n",
"11 0.006670\n",
"12 0.007637\n",
"13 0.019132\n",
"Normalized Saliency Sum: Saliency 6.842004\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.070809\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 11.87493\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 155.703568\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.005014\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 496.756317\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.001459\n",
"1 0.011952\n",
"2 0.013853\n",
"3 0.016568\n",
"4 0.022741\n",
".. ...\n",
"475 6.813513\n",
"476 6.822796\n",
"477 6.829741\n",
"478 6.835310\n",
"479 6.842001\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000003\n",
"1 0.000025\n",
"2 0.000029\n",
"3 0.000035\n",
"4 0.000047\n",
".. ...\n",
"475 0.014195\n",
"476 0.014214\n",
"477 0.014229\n",
"478 0.014240\n",
"479 0.014254\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.07215664\n",
"Normalized Saliency 25th Percentile: Saliency 0.002244\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.007908\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.005665\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": "121488b9-5feb-4213-af88-11c8e05b0029"
},
"execution_count": 110,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712633229.5371826\n",
"Tue Apr 9 03:27:09 2024\n"
]
}
]
}
]
}