Datasets
Models
Downloads: 1
1267 lines (1267 with data), 217.7 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": 133,
"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": 134,
"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": "02fbb131-4cf8-4797-f4a0-c19df644015d",
"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",
" 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": 135,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_12\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_52 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_53 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_54 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_55 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_56 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_57 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_58 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_59 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 6301697 (24.04 MB)\n",
"Trainable params: 6301697 (24.04 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": 136,
"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": "68671b5e-3db1-409e-c7a2-41cd2c242025"
},
"execution_count": 137,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712634282.0041528\n",
"Tue Apr 9 03:44:42 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "cd9dd705-754c-49ce-eaa2-31e3d79c15d1",
"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": 138,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 0.4480 - 1s/epoch - 94ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.0789 - 294ms/epoch - 20ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.0580 - 299ms/epoch - 20ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0469 - 298ms/epoch - 20ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0313 - 302ms/epoch - 20ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0269 - 303ms/epoch - 20ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0192 - 300ms/epoch - 20ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0122 - 298ms/epoch - 20ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0110 - 297ms/epoch - 20ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0033 - 292ms/epoch - 19ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0126 - 299ms/epoch - 20ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0351 - 292ms/epoch - 19ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0145 - 306ms/epoch - 20ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0140 - 310ms/epoch - 21ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0267 - 306ms/epoch - 20ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0083 - 301ms/epoch - 20ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0047 - 312ms/epoch - 21ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0340 - 307ms/epoch - 20ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0345 - 302ms/epoch - 20ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0215 - 305ms/epoch - 20ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 0.0122 - 300ms/epoch - 20ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 0.0034 - 292ms/epoch - 19ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 9.9358e-04 - 300ms/epoch - 20ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 3.6904e-04 - 304ms/epoch - 20ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 1.3925e-04 - 306ms/epoch - 20ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 6.5512e-05 - 302ms/epoch - 20ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 3.1689e-05 - 300ms/epoch - 20ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 1.1701e-05 - 314ms/epoch - 21ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 1.1839e-05 - 298ms/epoch - 20ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 8.8202e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 4.9803e-06 - 300ms/epoch - 20ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 3.3808e-06 - 295ms/epoch - 20ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 3.2015e-06 - 298ms/epoch - 20ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 3.1161e-06 - 297ms/epoch - 20ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 2.4299e-06 - 301ms/epoch - 20ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 2.5823e-06 - 297ms/epoch - 20ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 1.8835e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 1.6573e-06 - 293ms/epoch - 20ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 1.6236e-06 - 292ms/epoch - 19ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 1.4272e-06 - 297ms/epoch - 20ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 3.4031e-06 - 304ms/epoch - 20ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 6.3225e-06 - 293ms/epoch - 20ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 8.7410e-06 - 293ms/epoch - 20ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 1.1836e-05 - 297ms/epoch - 20ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 2.6947e-05 - 299ms/epoch - 20ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 3.5388e-06 - 304ms/epoch - 20ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 3.1930e-06 - 290ms/epoch - 19ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 1.8171e-06 - 287ms/epoch - 19ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 1.8050e-06 - 292ms/epoch - 19ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 2.2624e-06 - 292ms/epoch - 19ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 1.2906e-06 - 294ms/epoch - 20ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 1.0485e-06 - 287ms/epoch - 19ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 1.0125e-06 - 290ms/epoch - 19ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 6.0817e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 5.3554e-07 - 293ms/epoch - 20ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 8.0339e-07 - 293ms/epoch - 20ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 1.0357e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 4.4214e-07 - 290ms/epoch - 19ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 2.8740e-07 - 292ms/epoch - 19ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 4.2884e-07 - 290ms/epoch - 19ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 5.5033e-07 - 295ms/epoch - 20ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 4.7173e-07 - 295ms/epoch - 20ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 6.8461e-07 - 306ms/epoch - 20ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 3.4644e-07 - 301ms/epoch - 20ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 6.2962e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 3.9205e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 3.0164e-07 - 299ms/epoch - 20ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 4.0654e-07 - 306ms/epoch - 20ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 6.7634e-07 - 299ms/epoch - 20ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 5.3570e-07 - 293ms/epoch - 20ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 4.4140e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 9.1116e-07 - 296ms/epoch - 20ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 5.6861e-07 - 306ms/epoch - 20ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 6.9099e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 3.0197e-06 - 295ms/epoch - 20ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 4.7801e-07 - 293ms/epoch - 20ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 5.0733e-07 - 299ms/epoch - 20ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 7.5699e-07 - 308ms/epoch - 21ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 1.9291e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 2.4754e-06 - 290ms/epoch - 19ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 1.9972e-06 - 313ms/epoch - 21ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 1.1884e-05 - 298ms/epoch - 20ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 1.1392e-05 - 302ms/epoch - 20ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 2.3493e-05 - 303ms/epoch - 20ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 2.0708e-05 - 305ms/epoch - 20ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 1.5418e-05 - 305ms/epoch - 20ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 5.8229e-06 - 303ms/epoch - 20ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 2.0400e-06 - 302ms/epoch - 20ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 3.0211e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 1.2300e-06 - 300ms/epoch - 20ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 9.1464e-07 - 305ms/epoch - 20ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 3.8370e-07 - 308ms/epoch - 21ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 2.1384e-07 - 307ms/epoch - 20ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 4.6664e-07 - 306ms/epoch - 20ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 7.3502e-07 - 310ms/epoch - 21ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 2.6311e-07 - 301ms/epoch - 20ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 2.8676e-07 - 297ms/epoch - 20ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 1.0054e-06 - 295ms/epoch - 20ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 1.1548e-06 - 303ms/epoch - 20ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 1.7654e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 1.8135e-06 - 290ms/epoch - 19ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 2.5219e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 6.5184e-07 - 306ms/epoch - 20ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 4.8963e-07 - 309ms/epoch - 21ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 4.1926e-07 - 304ms/epoch - 20ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 9.4544e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 1.0789e-06 - 292ms/epoch - 19ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 5.8213e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 2.9991e-07 - 304ms/epoch - 20ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 1.8511e-07 - 295ms/epoch - 20ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 1.5226e-07 - 300ms/epoch - 20ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 8.3316e-07 - 304ms/epoch - 20ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 8.2862e-07 - 295ms/epoch - 20ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 5.1102e-07 - 312ms/epoch - 21ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 2.4679e-07 - 294ms/epoch - 20ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 9.1850e-07 - 300ms/epoch - 20ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 5.8150e-07 - 299ms/epoch - 20ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 1.4431e-06 - 307ms/epoch - 20ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 5.4743e-07 - 300ms/epoch - 20ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 5.0619e-07 - 294ms/epoch - 20ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 1.7437e-06 - 300ms/epoch - 20ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 3.6614e-06 - 296ms/epoch - 20ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 3.8236e-06 - 303ms/epoch - 20ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 2.3968e-06 - 289ms/epoch - 19ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 2.4118e-06 - 294ms/epoch - 20ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 2.7306e-06 - 293ms/epoch - 20ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 6.2714e-06 - 295ms/epoch - 20ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 7.5372e-05 - 290ms/epoch - 19ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 3.3687e-05 - 298ms/epoch - 20ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 3.7735e-05 - 284ms/epoch - 19ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 1.1813e-05 - 299ms/epoch - 20ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 6.8643e-06 - 294ms/epoch - 20ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 7.4785e-06 - 293ms/epoch - 20ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 7.7142e-06 - 295ms/epoch - 20ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 5.0125e-06 - 292ms/epoch - 19ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 5.0414e-06 - 300ms/epoch - 20ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 2.8095e-06 - 293ms/epoch - 20ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 8.2049e-07 - 292ms/epoch - 19ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 4.4472e-07 - 294ms/epoch - 20ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 5.2021e-07 - 300ms/epoch - 20ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 6.0290e-07 - 304ms/epoch - 20ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 2.6592e-06 - 294ms/epoch - 20ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 5.4951e-06 - 296ms/epoch - 20ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 1.1008e-05 - 296ms/epoch - 20ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 1.9100e-05 - 295ms/epoch - 20ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 3.3876e-05 - 292ms/epoch - 19ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 7.7080e-05 - 292ms/epoch - 19ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 1.2854e-05 - 298ms/epoch - 20ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 3.6963e-06 - 295ms/epoch - 20ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 1.3556e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 1.1447e-06 - 296ms/epoch - 20ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 3.7141e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 2.9981e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 2.8302e-06 - 292ms/epoch - 19ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 2.4226e-06 - 293ms/epoch - 20ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 6.4080e-06 - 298ms/epoch - 20ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 4.9435e-06 - 294ms/epoch - 20ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 5.9009e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 1.3369e-06 - 300ms/epoch - 20ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 4.9752e-06 - 297ms/epoch - 20ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 1.8742e-05 - 297ms/epoch - 20ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 1.5789e-04 - 293ms/epoch - 20ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 3.5041e-05 - 306ms/epoch - 20ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 1.4339e-05 - 295ms/epoch - 20ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 5.6745e-06 - 300ms/epoch - 20ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 4.0749e-06 - 294ms/epoch - 20ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 2.0525e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 2.6820e-06 - 289ms/epoch - 19ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 2.7595e-06 - 294ms/epoch - 20ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 1.5204e-06 - 301ms/epoch - 20ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 1.8017e-05 - 301ms/epoch - 20ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 1.2027e-05 - 307ms/epoch - 20ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 9.1439e-06 - 299ms/epoch - 20ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 1.5206e-06 - 297ms/epoch - 20ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 1.5324e-06 - 307ms/epoch - 20ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 4.9973e-07 - 307ms/epoch - 20ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 1.0836e-06 - 294ms/epoch - 20ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 3.0056e-06 - 306ms/epoch - 20ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 6.7202e-06 - 304ms/epoch - 20ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 6.5208e-06 - 312ms/epoch - 21ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 6.6537e-06 - 311ms/epoch - 21ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 2.1726e-06 - 297ms/epoch - 20ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 2.0450e-06 - 304ms/epoch - 20ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 1.6453e-06 - 307ms/epoch - 20ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 3.3057e-06 - 300ms/epoch - 20ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 7.2005e-06 - 306ms/epoch - 20ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 2.3571e-05 - 295ms/epoch - 20ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 7.8683e-05 - 306ms/epoch - 20ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 7.6047e-05 - 295ms/epoch - 20ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 8.3311e-05 - 295ms/epoch - 20ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 1.3098e-05 - 289ms/epoch - 19ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 5.8108e-06 - 290ms/epoch - 19ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 4.9290e-06 - 296ms/epoch - 20ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 2.1793e-06 - 289ms/epoch - 19ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 9.2731e-07 - 289ms/epoch - 19ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 3.7267e-07 - 287ms/epoch - 19ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 3.5408e-07 - 295ms/epoch - 20ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 2.0738e-07 - 300ms/epoch - 20ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 1.8493e-07 - 293ms/epoch - 20ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 1.0021e-07 - 291ms/epoch - 19ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 8.7537e-08 - 290ms/epoch - 19ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 2.6470e-07 - 309ms/epoch - 21ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 9.9417e-07 - 289ms/epoch - 19ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 1.9933e-06 - 301ms/epoch - 20ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 4.1001e-06 - 303ms/epoch - 20ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 3.0956e-06 - 298ms/epoch - 20ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 8.2789e-07 - 297ms/epoch - 20ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 6.2351e-06 - 301ms/epoch - 20ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 4.2929e-06 - 293ms/epoch - 20ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 1.3045e-05 - 298ms/epoch - 20ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 1.0927e-04 - 305ms/epoch - 20ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 1.0284e-04 - 296ms/epoch - 20ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 7.7237e-05 - 303ms/epoch - 20ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 5.8834e-05 - 294ms/epoch - 20ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 4.5498e-05 - 301ms/epoch - 20ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 8.8680e-06 - 305ms/epoch - 20ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 1.0065e-05 - 298ms/epoch - 20ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 8.0247e-06 - 313ms/epoch - 21ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 4.1017e-06 - 301ms/epoch - 20ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 1.1392e-06 - 300ms/epoch - 20ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 9.4530e-07 - 292ms/epoch - 19ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 4.0268e-07 - 296ms/epoch - 20ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 3.3730e-07 - 293ms/epoch - 20ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 1.7759e-07 - 300ms/epoch - 20ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 5.6321e-07 - 303ms/epoch - 20ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 3.7351e-07 - 288ms/epoch - 19ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 1.2196e-07 - 285ms/epoch - 19ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 2.3325e-07 - 295ms/epoch - 20ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 3.4197e-07 - 299ms/epoch - 20ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 2.4147e-07 - 296ms/epoch - 20ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 2.5055e-07 - 296ms/epoch - 20ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 2.9382e-07 - 299ms/epoch - 20ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 2.2010e-07 - 300ms/epoch - 20ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 2.4778e-07 - 302ms/epoch - 20ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 2.0133e-07 - 307ms/epoch - 20ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 2.1558e-07 - 300ms/epoch - 20ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 1.3917e-07 - 299ms/epoch - 20ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 7.0637e-08 - 304ms/epoch - 20ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 2.8932e-07 - 296ms/epoch - 20ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 4.1481e-07 - 311ms/epoch - 21ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 4.7940e-07 - 300ms/epoch - 20ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 9.6691e-07 - 289ms/epoch - 19ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 1.1589e-06 - 296ms/epoch - 20ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 5.5345e-07 - 303ms/epoch - 20ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 2.3406e-07 - 304ms/epoch - 20ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 4.6254e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 8.0235e-08 - 297ms/epoch - 20ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 1.4363e-07 - 294ms/epoch - 20ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 4.7089e-07 - 293ms/epoch - 20ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 1.4577e-07 - 304ms/epoch - 20ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 1.6440e-07 - 303ms/epoch - 20ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 1.1456e-06 - 301ms/epoch - 20ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 6.4051e-07 - 304ms/epoch - 20ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 5.0261e-08 - 301ms/epoch - 20ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 2.4492e-08 - 299ms/epoch - 20ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 2.5216e-08 - 297ms/epoch - 20ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 2.6168e-08 - 301ms/epoch - 20ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 5.2311e-08 - 311ms/epoch - 21ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 1.0782e-07 - 307ms/epoch - 20ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 7.5493e-07 - 302ms/epoch - 20ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 1.9036e-06 - 297ms/epoch - 20ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 4.1965e-06 - 301ms/epoch - 20ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 6.0931e-06 - 301ms/epoch - 20ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 1.7416e-05 - 290ms/epoch - 19ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 1.2331e-05 - 297ms/epoch - 20ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 1.0743e-05 - 302ms/epoch - 20ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 5.8104e-06 - 303ms/epoch - 20ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 4.8280e-06 - 302ms/epoch - 20ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 4.5632e-07 - 298ms/epoch - 20ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 2.5230e-06 - 297ms/epoch - 20ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 9.0697e-06 - 295ms/epoch - 20ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 5.2746e-06 - 302ms/epoch - 20ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 2.2134e-06 - 303ms/epoch - 20ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 1.7779e-06 - 298ms/epoch - 20ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 6.2648e-06 - 297ms/epoch - 20ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 4.9407e-06 - 302ms/epoch - 20ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 3.8577e-06 - 300ms/epoch - 20ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 5.9212e-06 - 303ms/epoch - 20ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 5.9292e-06 - 308ms/epoch - 21ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 1.0653e-05 - 301ms/epoch - 20ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 3.2722e-05 - 294ms/epoch - 20ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 4.6717e-06 - 296ms/epoch - 20ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 5.0025e-06 - 295ms/epoch - 20ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 3.3890e-06 - 294ms/epoch - 20ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 2.7879e-06 - 298ms/epoch - 20ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 3.0786e-06 - 293ms/epoch - 20ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 1.0039e-06 - 292ms/epoch - 19ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 8.6577e-07 - 300ms/epoch - 20ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 1.2110e-06 - 288ms/epoch - 19ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 3.1428e-06 - 294ms/epoch - 20ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 6.4649e-06 - 295ms/epoch - 20ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 1.7615e-05 - 300ms/epoch - 20ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 1.3791e-05 - 306ms/epoch - 20ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 6.2846e-06 - 296ms/epoch - 20ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 1.2724e-05 - 292ms/epoch - 19ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 1.8771e-05 - 303ms/epoch - 20ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 3.6298e-05 - 302ms/epoch - 20ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 2.3531e-05 - 296ms/epoch - 20ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 6.2163e-05 - 289ms/epoch - 19ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 3.4196e-05 - 303ms/epoch - 20ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7f3b9c3b6380>"
]
},
"metadata": {},
"execution_count": 138
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "e54001de-bc9c-46dc-a1cc-fb351b365c8f",
"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": 139,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 5ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7f3a18143f10>"
]
},
"metadata": {},
"execution_count": 139
},
{
"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": "fe86049f-ba35-40ed-e6a7-866aa73f0af1"
},
"execution_count": 140,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712634373.8582394\n",
"Tue Apr 9 03:46:13 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": "2708195d-f75f-46a7-e8dc-4e53b304fb9a"
},
"execution_count": 141,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712634373.8642654\n",
"Tue Apr 9 03:46:13 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": "f3eddc88-0693-4b67-c22c-e7d08014d606"
},
"execution_count": 142,
"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",
"37 0.683016\n",
"370 0.294107\n",
"287 0.174463\n",
"193 0.106990\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 0.019095\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.012336\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.011696\n",
"1 0.012007\n",
"2 0.021401\n",
"Normalized Saliency Sum: Saliency 9.165418\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.057578\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 13.867396\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 213.661987\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.003315\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 301.5401\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.007970\n",
"1 0.016123\n",
"2 0.027405\n",
"3 0.034767\n",
"4 0.044555\n",
".. ...\n",
"475 9.064732\n",
"476 9.100277\n",
"477 9.118701\n",
"478 9.141863\n",
"479 9.165421\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000017\n",
"1 0.000034\n",
"2 0.000057\n",
"3 0.000072\n",
"4 0.000093\n",
".. ...\n",
"475 0.018885\n",
"476 0.018959\n",
"477 0.018997\n",
"478 0.019046\n",
"479 0.019095\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.06060459\n",
"Normalized Saliency 25th Percentile: Saliency 0.007178\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.01781\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.010632\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": "02be47f8-f919-48ff-ee65-47942db5e4ed"
},
"execution_count": 143,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712634375.9249177\n",
"Tue Apr 9 03:46:15 2024\n"
]
}
]
}
]
}