Datasets
Models
Downloads: 1
1262 lines (1262 with data), 218.7 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": 89,
"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": 90,
"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": "4320b8ed-2ff6-4bae-bc01-66f3e86768a4",
"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",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 91,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_8\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_30 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_31 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_32 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_33 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 2103297 (8.02 MB)\n",
"Trainable params: 2103297 (8.02 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": 92,
"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": "7de1d188-0302-4ae2-e4f0-b632ce6dfea0"
},
"execution_count": 93,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712632843.1813152\n",
"Tue Apr 9 03:20:43 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "6822f266-797c-4aaf-dc33-3accb8be9466",
"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": 94,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 0.2829 - 759ms/epoch - 51ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.0940 - 140ms/epoch - 9ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.0780 - 134ms/epoch - 9ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0713 - 133ms/epoch - 9ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0566 - 139ms/epoch - 9ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0534 - 142ms/epoch - 9ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0505 - 135ms/epoch - 9ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0530 - 126ms/epoch - 8ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0443 - 129ms/epoch - 9ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0358 - 126ms/epoch - 8ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0276 - 123ms/epoch - 8ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0230 - 124ms/epoch - 8ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0155 - 122ms/epoch - 8ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0091 - 130ms/epoch - 9ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0068 - 127ms/epoch - 8ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0070 - 128ms/epoch - 9ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0045 - 129ms/epoch - 9ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0022 - 130ms/epoch - 9ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0015 - 131ms/epoch - 9ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0021 - 129ms/epoch - 9ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 0.0024 - 132ms/epoch - 9ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 0.0022 - 128ms/epoch - 9ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 0.0015 - 127ms/epoch - 8ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 8.3940e-04 - 132ms/epoch - 9ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 8.7838e-04 - 136ms/epoch - 9ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 6.5470e-04 - 125ms/epoch - 8ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 6.4894e-04 - 126ms/epoch - 8ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 2.1371e-04 - 130ms/epoch - 9ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 9.2961e-04 - 128ms/epoch - 9ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 6.5380e-04 - 123ms/epoch - 8ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 6.2486e-04 - 122ms/epoch - 8ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 4.1306e-04 - 131ms/epoch - 9ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 3.2661e-04 - 134ms/epoch - 9ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 3.8003e-04 - 124ms/epoch - 8ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 3.5678e-04 - 133ms/epoch - 9ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 1.3640e-04 - 127ms/epoch - 8ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 7.6688e-05 - 133ms/epoch - 9ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 1.4136e-04 - 129ms/epoch - 9ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 7.7330e-05 - 131ms/epoch - 9ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 6.1713e-05 - 138ms/epoch - 9ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 7.7502e-05 - 134ms/epoch - 9ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 1.0115e-04 - 135ms/epoch - 9ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 1.1663e-04 - 134ms/epoch - 9ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 1.3107e-04 - 126ms/epoch - 8ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 6.9424e-05 - 126ms/epoch - 8ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 1.1424e-04 - 130ms/epoch - 9ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 1.1259e-04 - 124ms/epoch - 8ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 5.8978e-05 - 128ms/epoch - 9ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 3.7899e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 4.2666e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 9.3850e-05 - 127ms/epoch - 8ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 0.0050 - 125ms/epoch - 8ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 0.0059 - 124ms/epoch - 8ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 0.0030 - 125ms/epoch - 8ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 0.0012 - 128ms/epoch - 9ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 0.0012 - 125ms/epoch - 8ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 7.6256e-04 - 125ms/epoch - 8ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 0.0010 - 129ms/epoch - 9ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 5.2127e-04 - 124ms/epoch - 8ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 3.2788e-04 - 123ms/epoch - 8ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 5.0415e-04 - 125ms/epoch - 8ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 3.4989e-04 - 125ms/epoch - 8ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 2.1421e-04 - 127ms/epoch - 8ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 1.5728e-04 - 129ms/epoch - 9ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 1.4793e-04 - 122ms/epoch - 8ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 1.4780e-04 - 129ms/epoch - 9ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 7.0317e-05 - 122ms/epoch - 8ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 6.2669e-05 - 129ms/epoch - 9ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 7.3668e-05 - 127ms/epoch - 8ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 6.7812e-05 - 125ms/epoch - 8ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 2.1254e-04 - 127ms/epoch - 8ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 7.3498e-04 - 127ms/epoch - 8ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 7.8145e-04 - 130ms/epoch - 9ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 6.0264e-04 - 125ms/epoch - 8ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 2.2849e-04 - 127ms/epoch - 8ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 9.3824e-05 - 126ms/epoch - 8ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 5.5533e-05 - 125ms/epoch - 8ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 6.8029e-05 - 126ms/epoch - 8ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 1.8204e-04 - 124ms/epoch - 8ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 2.2560e-04 - 125ms/epoch - 8ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 5.5585e-04 - 127ms/epoch - 8ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 5.7191e-04 - 127ms/epoch - 8ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 4.8719e-04 - 139ms/epoch - 9ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 4.0313e-04 - 124ms/epoch - 8ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 3.0554e-04 - 126ms/epoch - 8ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 1.9380e-04 - 129ms/epoch - 9ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 1.8286e-04 - 126ms/epoch - 8ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 6.7514e-05 - 124ms/epoch - 8ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 4.2449e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 1.5833e-05 - 135ms/epoch - 9ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 1.9624e-05 - 128ms/epoch - 9ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 2.0044e-05 - 125ms/epoch - 8ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 1.0961e-05 - 129ms/epoch - 9ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 1.1290e-05 - 131ms/epoch - 9ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 1.3426e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 3.4066e-05 - 129ms/epoch - 9ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 5.0107e-05 - 138ms/epoch - 9ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 2.2838e-04 - 132ms/epoch - 9ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 1.5954e-04 - 128ms/epoch - 9ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 8.5557e-05 - 125ms/epoch - 8ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 8.5937e-05 - 134ms/epoch - 9ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 3.6214e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 3.7107e-05 - 131ms/epoch - 9ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 1.5352e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 2.0853e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 5.0621e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 1.5559e-04 - 126ms/epoch - 8ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 3.4460e-04 - 129ms/epoch - 9ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 3.5168e-04 - 132ms/epoch - 9ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 2.1258e-04 - 126ms/epoch - 8ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 2.0765e-04 - 127ms/epoch - 8ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 1.4349e-04 - 127ms/epoch - 8ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 5.7519e-05 - 127ms/epoch - 8ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 2.2365e-05 - 126ms/epoch - 8ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 2.1894e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 2.8731e-05 - 129ms/epoch - 9ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 3.0204e-05 - 134ms/epoch - 9ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 5.0886e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 4.1195e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 3.2968e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 7.7000e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 6.7136e-05 - 141ms/epoch - 9ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 6.6494e-05 - 127ms/epoch - 8ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 4.0356e-05 - 135ms/epoch - 9ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 2.0807e-05 - 127ms/epoch - 8ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 3.1830e-05 - 131ms/epoch - 9ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 5.5906e-05 - 129ms/epoch - 9ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 2.3733e-04 - 136ms/epoch - 9ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 2.7603e-04 - 130ms/epoch - 9ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 3.3173e-04 - 129ms/epoch - 9ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 4.9548e-04 - 137ms/epoch - 9ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 2.9916e-04 - 138ms/epoch - 9ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 1.3882e-04 - 129ms/epoch - 9ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 5.1795e-05 - 141ms/epoch - 9ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 5.7875e-05 - 129ms/epoch - 9ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 5.8166e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 1.0009e-04 - 130ms/epoch - 9ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 1.5181e-04 - 127ms/epoch - 8ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 1.4415e-04 - 129ms/epoch - 9ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 7.7581e-04 - 128ms/epoch - 9ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 9.7395e-04 - 129ms/epoch - 9ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 0.0034 - 127ms/epoch - 8ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 0.0013 - 131ms/epoch - 9ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 0.0031 - 138ms/epoch - 9ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 0.0022 - 126ms/epoch - 8ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 0.0054 - 133ms/epoch - 9ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 0.0059 - 129ms/epoch - 9ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 0.0089 - 125ms/epoch - 8ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 0.0062 - 126ms/epoch - 8ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 0.0072 - 133ms/epoch - 9ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 0.0041 - 124ms/epoch - 8ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 0.0041 - 126ms/epoch - 8ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 0.0025 - 128ms/epoch - 9ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 7.6607e-04 - 128ms/epoch - 9ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 2.4125e-04 - 131ms/epoch - 9ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 4.7703e-05 - 139ms/epoch - 9ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 2.8073e-05 - 131ms/epoch - 9ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 3.1006e-05 - 129ms/epoch - 9ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 1.7029e-05 - 128ms/epoch - 9ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 1.4961e-05 - 127ms/epoch - 8ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 1.1397e-05 - 129ms/epoch - 9ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 1.1586e-05 - 131ms/epoch - 9ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 8.9648e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 7.7993e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 9.8689e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 1.7011e-05 - 128ms/epoch - 9ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 1.8319e-05 - 126ms/epoch - 8ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 1.9694e-05 - 125ms/epoch - 8ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 8.9233e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 1.0330e-05 - 126ms/epoch - 8ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 1.1187e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 5.6703e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 4.8738e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 3.5798e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 3.4138e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 3.8643e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 5.3703e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 7.9582e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 5.6515e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 4.2214e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 3.7597e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 4.0993e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 2.4873e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 2.4365e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 5.3453e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 6.8843e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 8.7901e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 1.5173e-05 - 137ms/epoch - 9ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 3.3909e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 7.7898e-05 - 135ms/epoch - 9ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 1.0917e-04 - 143ms/epoch - 10ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 6.9996e-05 - 134ms/epoch - 9ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 2.9510e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 3.7459e-05 - 131ms/epoch - 9ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 8.6234e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 3.4861e-05 - 125ms/epoch - 8ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 7.6800e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 3.2227e-05 - 126ms/epoch - 8ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 2.4965e-05 - 127ms/epoch - 8ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 1.8032e-05 - 133ms/epoch - 9ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 1.2136e-05 - 136ms/epoch - 9ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 1.3499e-05 - 136ms/epoch - 9ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 2.3603e-05 - 136ms/epoch - 9ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 1.5429e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 7.6976e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 3.2033e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 3.0818e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 3.9776e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 3.5464e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 3.7780e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 7.5352e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 9.1575e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 6.7839e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 6.1467e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 4.3274e-05 - 137ms/epoch - 9ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 2.8858e-05 - 137ms/epoch - 9ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 9.7495e-05 - 133ms/epoch - 9ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 1.5002e-04 - 137ms/epoch - 9ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 5.3333e-05 - 129ms/epoch - 9ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 3.3117e-05 - 129ms/epoch - 9ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 1.9616e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 3.3612e-05 - 133ms/epoch - 9ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 3.4182e-05 - 129ms/epoch - 9ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 1.3727e-05 - 126ms/epoch - 8ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.6736e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 1.9198e-05 - 131ms/epoch - 9ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 5.4586e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 2.0665e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 3.1634e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 8.9788e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 7.8601e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 2.8978e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 3.6678e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 7.0834e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 6.9925e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 2.8946e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 4.3475e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 5.9393e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 1.6333e-05 - 126ms/epoch - 8ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 3.5899e-05 - 131ms/epoch - 9ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 2.0380e-05 - 126ms/epoch - 8ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 1.5969e-05 - 131ms/epoch - 9ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 1.4147e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 1.3357e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 4.4924e-05 - 136ms/epoch - 9ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 2.8351e-04 - 144ms/epoch - 10ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 2.9519e-04 - 130ms/epoch - 9ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 8.5721e-04 - 138ms/epoch - 9ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 7.9441e-04 - 128ms/epoch - 9ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 3.8521e-04 - 132ms/epoch - 9ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 0.0013 - 126ms/epoch - 8ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 9.9580e-04 - 125ms/epoch - 8ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 8.9007e-04 - 131ms/epoch - 9ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 0.0015 - 129ms/epoch - 9ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 0.0015 - 128ms/epoch - 9ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 4.0784e-04 - 129ms/epoch - 9ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 2.0562e-04 - 127ms/epoch - 8ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 2.9919e-04 - 127ms/epoch - 8ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 4.9389e-04 - 129ms/epoch - 9ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 5.7257e-04 - 126ms/epoch - 8ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 1.5807e-04 - 133ms/epoch - 9ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 5.5241e-05 - 127ms/epoch - 8ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 1.5566e-05 - 129ms/epoch - 9ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 1.1046e-05 - 124ms/epoch - 8ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 9.5385e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 8.1947e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 1.3426e-05 - 122ms/epoch - 8ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 9.8981e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 7.0411e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 3.6702e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 2.5619e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 1.9194e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 1.4740e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 1.3054e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 1.1528e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 1.8554e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 2.4634e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 1.4110e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 5.8235e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 3.8517e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 2.7172e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 2.1526e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 2.8425e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 4.2609e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 2.3753e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 1.7127e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 1.5265e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 3.8935e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 3.5794e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 3.6830e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 2.1362e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 1.6306e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 1.6727e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 1.2036e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 1.1323e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 2.4774e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 2.2155e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 1.8635e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 9.6997e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 3.9618e-06 - 127ms/epoch - 8ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7f3a5831e020>"
]
},
"metadata": {},
"execution_count": 94
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "926f264a-4aa0-45dc-c88b-31cfa14c4a0c",
"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": 95,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 3ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7f3a58249cc0>"
]
},
"metadata": {},
"execution_count": 95
},
{
"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": "02ea3b7a-50dd-4c89-90d9-c9df0a385cdd"
},
"execution_count": 96,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712632883.7613978\n",
"Tue Apr 9 03:21:23 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": "54074fbc-7c98-4b39-86c7-600897e57a9b"
},
"execution_count": 97,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712632883.7675738\n",
"Tue Apr 9 03:21:23 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": 2024
},
"id": "95xed6YyDClf",
"outputId": "0d8cb98a-0b04-4ecf-881e-aab5bb78b1e0"
},
"execution_count": 98,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Saliency values saved to saliency_values.csv\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Normalized saliency values saved to normalized_saliency_values.csv\n",
"Normalized Saliency Top-k:\n",
" Saliency\n",
"37 1.000000\n",
"239 0.912613\n",
"377 0.658046\n",
"287 0.278763\n",
"327 0.252680\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 0.022191\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.00941\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.001499\n",
"1 0.002879\n",
"2 0.003678\n",
"3 0.005003\n",
"4 0.006896\n",
"5 0.008125\n",
"6 0.008156\n",
"7 0.008568\n",
"8 0.010545\n",
"9 0.013772\n",
"Normalized Saliency Sum: Saliency 10.651455\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.0732\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 10.427355\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 123.392311\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.005358\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 329.872498\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.003012\n",
"1 0.012208\n",
"2 0.018691\n",
"3 0.024637\n",
"4 0.040916\n",
".. ...\n",
"475 10.524874\n",
"476 10.617480\n",
"477 10.623999\n",
"478 10.632812\n",
"479 10.651456\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000006\n",
"1 0.000025\n",
"2 0.000039\n",
"3 0.000051\n",
"4 0.000085\n",
".. ...\n",
"475 0.021927\n",
"476 0.022120\n",
"477 0.022133\n",
"478 0.022152\n",
"479 0.022191\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.07641704\n",
"Normalized Saliency 25th Percentile: Saliency 0.005104\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.015523\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.010419\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": "2b052841-68dd-4509-d3c3-61f65007eab8"
},
"execution_count": 99,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712632885.0067606\n",
"Tue Apr 9 03:21:25 2024\n"
]
}
]
}
]
}