Datasets
Models
Downloads: 1
1250 lines (1250 with data), 217.3 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": 79,
"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": 80,
"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": "d452f96d-1c30-4efb-b35d-d18e26113200",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
}
},
"source": [
"Dense = tf.keras.layers.Dense\n",
"tn_model = tf.keras.Sequential(\n",
" [\n",
" tf.keras.Input(shape=(2,)),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Start Modified Layers\n",
" TNLayer(),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 81,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_6\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_18 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_18 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_19 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 9217 (36.00 KB)\n",
"Trainable params: 9217 (36.00 KB)\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": 82,
"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": "6e9ccae0-e165-44bd-f9f0-224d34498754"
},
"execution_count": 83,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712550362.5466504\n",
"Mon Apr 8 04:26:02 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "4291fa30-d4d4-48ac-94cf-7a9122f66c0d",
"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": 84,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 0.8922 - 771ms/epoch - 51ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.5309 - 52ms/epoch - 3ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.1134 - 48ms/epoch - 3ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0740 - 43ms/epoch - 3ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0540 - 43ms/epoch - 3ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0482 - 43ms/epoch - 3ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0429 - 43ms/epoch - 3ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0377 - 40ms/epoch - 3ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0340 - 40ms/epoch - 3ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0300 - 38ms/epoch - 3ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0243 - 38ms/epoch - 3ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0200 - 38ms/epoch - 3ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0162 - 38ms/epoch - 3ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0128 - 39ms/epoch - 3ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0094 - 39ms/epoch - 3ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0074 - 40ms/epoch - 3ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0056 - 39ms/epoch - 3ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0047 - 38ms/epoch - 3ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0044 - 40ms/epoch - 3ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0036 - 41ms/epoch - 3ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 0.0031 - 38ms/epoch - 3ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 0.0031 - 39ms/epoch - 3ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 0.0026 - 38ms/epoch - 3ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 0.0023 - 39ms/epoch - 3ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 0.0020 - 39ms/epoch - 3ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 0.0017 - 38ms/epoch - 3ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 0.0016 - 40ms/epoch - 3ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 0.0011 - 39ms/epoch - 3ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 0.0011 - 39ms/epoch - 3ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 8.8891e-04 - 38ms/epoch - 3ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 9.6109e-04 - 37ms/epoch - 2ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 6.8459e-04 - 37ms/epoch - 2ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 6.4592e-04 - 36ms/epoch - 2ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 5.2315e-04 - 37ms/epoch - 2ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 5.0593e-04 - 38ms/epoch - 3ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 4.7202e-04 - 37ms/epoch - 2ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 5.5910e-04 - 38ms/epoch - 3ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 3.3655e-04 - 37ms/epoch - 2ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 3.3490e-04 - 39ms/epoch - 3ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 3.5281e-04 - 38ms/epoch - 3ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 3.0240e-04 - 38ms/epoch - 3ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 2.0281e-04 - 38ms/epoch - 3ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 2.1079e-04 - 39ms/epoch - 3ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 1.6996e-04 - 38ms/epoch - 3ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 1.6042e-04 - 39ms/epoch - 3ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 1.7519e-04 - 39ms/epoch - 3ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 1.2046e-04 - 37ms/epoch - 2ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 1.1263e-04 - 37ms/epoch - 2ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 1.1378e-04 - 38ms/epoch - 3ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 1.0423e-04 - 37ms/epoch - 2ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 9.3733e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 9.0095e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 9.7267e-05 - 37ms/epoch - 2ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 8.6930e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 7.4910e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 7.0346e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 7.0709e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 5.3301e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 5.9042e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 4.7067e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 4.6211e-05 - 37ms/epoch - 2ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 3.8769e-05 - 36ms/epoch - 2ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 3.6004e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 3.2332e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 2.8019e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 2.8953e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 3.7322e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 3.6969e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 3.3841e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 3.0364e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 3.1020e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 2.1751e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 2.0380e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 2.0801e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 2.1752e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 2.2411e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 2.1611e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 1.6325e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 1.4591e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 1.1911e-05 - 37ms/epoch - 2ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 1.2496e-05 - 37ms/epoch - 2ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 1.1834e-05 - 37ms/epoch - 2ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 1.2842e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 1.4694e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 9.3507e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 8.4809e-06 - 37ms/epoch - 2ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 9.6937e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 1.4287e-05 - 36ms/epoch - 2ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 1.3179e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 1.2656e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 1.1713e-05 - 40ms/epoch - 3ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 7.3984e-06 - 37ms/epoch - 2ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 1.5266e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 3.8359e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 6.8103e-05 - 40ms/epoch - 3ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 1.0904e-04 - 38ms/epoch - 3ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 4.6647e-05 - 40ms/epoch - 3ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 3.7262e-05 - 40ms/epoch - 3ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 1.3572e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 1.3869e-05 - 37ms/epoch - 2ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 2.8845e-05 - 37ms/epoch - 2ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 6.7455e-05 - 37ms/epoch - 2ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 6.0054e-05 - 37ms/epoch - 2ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 4.3575e-05 - 37ms/epoch - 2ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 3.6426e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 4.2577e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 4.9615e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 4.2535e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 5.6188e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 3.4839e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 1.6564e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 1.2964e-05 - 37ms/epoch - 2ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 7.7063e-06 - 37ms/epoch - 2ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 7.7956e-06 - 37ms/epoch - 2ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 5.4062e-06 - 37ms/epoch - 2ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 4.4474e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 6.3726e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 8.0969e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 6.3891e-06 - 37ms/epoch - 2ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 7.2830e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 1.7694e-05 - 40ms/epoch - 3ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 8.2109e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 1.0397e-05 - 36ms/epoch - 2ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 3.9748e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 5.7396e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 5.4312e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 1.7561e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 8.6495e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 7.3376e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 9.3166e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 3.2763e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 1.9355e-05 - 40ms/epoch - 3ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 2.7664e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 2.8498e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 1.2453e-05 - 40ms/epoch - 3ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 1.1500e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 7.4750e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 7.8097e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 4.3972e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 1.3851e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 2.5306e-05 - 37ms/epoch - 2ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 2.1066e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 2.0831e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 5.6145e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 8.2460e-05 - 41ms/epoch - 3ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 7.7230e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 5.0279e-05 - 40ms/epoch - 3ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 4.0906e-05 - 41ms/epoch - 3ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 3.4046e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 3.0892e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 3.0622e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 1.7820e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 9.5128e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 1.3108e-05 - 40ms/epoch - 3ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 2.4937e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 3.3904e-05 - 40ms/epoch - 3ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 2.9244e-05 - 40ms/epoch - 3ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 9.9121e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 1.8353e-04 - 37ms/epoch - 2ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 2.6400e-04 - 38ms/epoch - 3ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 7.3892e-04 - 39ms/epoch - 3ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 0.0021 - 40ms/epoch - 3ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 0.0015 - 39ms/epoch - 3ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 0.0013 - 39ms/epoch - 3ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 6.2809e-04 - 41ms/epoch - 3ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 0.0017 - 41ms/epoch - 3ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 0.0019 - 40ms/epoch - 3ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 0.0015 - 39ms/epoch - 3ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 3.4971e-04 - 40ms/epoch - 3ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 8.8422e-05 - 42ms/epoch - 3ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 6.0285e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 2.2824e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 2.0782e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 1.3162e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 8.6383e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 6.4070e-06 - 41ms/epoch - 3ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 6.9794e-06 - 42ms/epoch - 3ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 7.8777e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 5.9584e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 6.0509e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 5.1524e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 4.5614e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 4.6326e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 3.8963e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 3.6031e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 3.6904e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 2.4980e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 4.5033e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 2.7958e-06 - 37ms/epoch - 2ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 3.2597e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 4.0499e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 2.5184e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 3.4945e-06 - 41ms/epoch - 3ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 7.5009e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 1.2818e-05 - 40ms/epoch - 3ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 4.8513e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 2.4429e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 1.7302e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 1.2396e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 2.0364e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 4.1169e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 4.1949e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 5.4549e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 3.1480e-06 - 37ms/epoch - 2ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 4.3702e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 3.9709e-06 - 41ms/epoch - 3ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 3.6117e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 2.2495e-06 - 42ms/epoch - 3ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 1.9697e-06 - 41ms/epoch - 3ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 1.4727e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 1.8428e-06 - 37ms/epoch - 2ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 1.8180e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 1.2489e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 8.0971e-07 - 39ms/epoch - 3ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 1.0594e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 8.1333e-07 - 39ms/epoch - 3ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 5.7732e-07 - 39ms/epoch - 3ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 7.2286e-07 - 38ms/epoch - 3ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 1.0505e-06 - 37ms/epoch - 2ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 1.1564e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 1.3202e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 8.5789e-07 - 37ms/epoch - 2ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 1.0976e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 2.7599e-06 - 37ms/epoch - 2ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 9.0777e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 1.5181e-05 - 37ms/epoch - 2ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 7.8139e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 5.8952e-06 - 37ms/epoch - 2ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 7.0791e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 6.5321e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 3.8499e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 2.2766e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 2.9889e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 2.4292e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 9.5284e-07 - 39ms/epoch - 3ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 8.7267e-07 - 38ms/epoch - 3ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 7.7259e-07 - 39ms/epoch - 3ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 2.3065e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 3.1300e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 2.4601e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 1.2145e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 8.9349e-07 - 39ms/epoch - 3ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 6.1982e-07 - 39ms/epoch - 3ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 7.0576e-07 - 38ms/epoch - 3ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 5.4875e-07 - 41ms/epoch - 3ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 1.7074e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 2.5632e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 1.0719e-05 - 37ms/epoch - 2ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 1.0188e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 4.7548e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 2.4687e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 2.3670e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 1.5229e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 1.1294e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 1.5999e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 1.1438e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 1.9845e-06 - 37ms/epoch - 2ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 5.4367e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 5.3108e-06 - 42ms/epoch - 3ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 4.7876e-06 - 41ms/epoch - 3ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 1.9156e-05 - 42ms/epoch - 3ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 9.6716e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 7.0152e-06 - 42ms/epoch - 3ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 5.2249e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 4.3205e-06 - 41ms/epoch - 3ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 8.1226e-06 - 41ms/epoch - 3ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 4.8447e-05 - 41ms/epoch - 3ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 2.2224e-04 - 40ms/epoch - 3ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 2.0431e-04 - 40ms/epoch - 3ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 5.8484e-04 - 40ms/epoch - 3ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 7.2587e-04 - 41ms/epoch - 3ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 6.5821e-04 - 41ms/epoch - 3ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 6.4781e-04 - 40ms/epoch - 3ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 0.0045 - 41ms/epoch - 3ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 0.0045 - 40ms/epoch - 3ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 0.0065 - 40ms/epoch - 3ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 0.0042 - 39ms/epoch - 3ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 0.0011 - 39ms/epoch - 3ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 4.5927e-04 - 39ms/epoch - 3ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 1.6168e-04 - 39ms/epoch - 3ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 5.8020e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 2.8500e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 2.3686e-05 - 39ms/epoch - 3ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 1.5198e-05 - 38ms/epoch - 3ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 1.0874e-05 - 40ms/epoch - 3ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 7.8480e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 5.4056e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 4.8383e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 3.8485e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 4.6917e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 3.8390e-06 - 40ms/epoch - 3ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 4.0659e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 3.7175e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 2.7258e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 2.7772e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 2.4019e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 3.9302e-06 - 39ms/epoch - 3ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 2.5659e-06 - 38ms/epoch - 3ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 1.7756e-06 - 37ms/epoch - 2ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 1.8881e-06 - 37ms/epoch - 2ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7ce24c411780>"
]
},
"metadata": {},
"execution_count": 84
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "ef623a78-3ea6-4e92-d9c2-93b3c0fe987f",
"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": 85,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 2ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7ce2446bc4c0>"
]
},
"metadata": {},
"execution_count": 85
},
{
"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": "c3f1b71b-27dc-4944-bf46-671ec3f38924"
},
"execution_count": 86,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712550375.9200459\n",
"Mon Apr 8 04:26:15 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": "409bc1a5-8ec8-401b-ed72-8ab25c80a0f6"
},
"execution_count": 87,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712550375.9258373\n",
"Mon Apr 8 04:26:15 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": 1886
},
"id": "95xed6YyDClf",
"outputId": "2c27641c-99d4-4bcd-eb46-d37788888bd3"
},
"execution_count": 88,
"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",
"287 0.593953\n",
"377 0.489469\n",
"327 0.427926\n",
"37 0.415776\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 0.018003\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.005896\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.001611\n",
"Normalized Saliency Sum: Saliency 8.641273\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.070065\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 9.077344\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 100.118958\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.004909\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 389.194275\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.001312\n",
"1 0.010477\n",
"2 0.015087\n",
"3 0.020735\n",
"4 0.023634\n",
".. ...\n",
"475 8.600565\n",
"476 8.617616\n",
"477 8.624347\n",
"478 8.631016\n",
"479 8.641277\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000003\n",
"1 0.000022\n",
"2 0.000031\n",
"3 0.000043\n",
"4 0.000049\n",
".. ...\n",
"475 0.017918\n",
"476 0.017953\n",
"477 0.017967\n",
"478 0.017981\n",
"479 0.018003\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.072270416\n",
"Normalized Saliency 25th Percentile: Saliency 0.003561\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.009749\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.006188\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": "5bbef96e-c568-4ea3-fd8a-2a993b3b7ee4"
},
"execution_count": 89,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712550376.9526744\n",
"Mon Apr 8 04:26:16 2024\n"
]
}
]
}
]
}