Datasets
Models
Downloads: 1
1271 lines (1271 with data), 218.4 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": 34,
"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": 35,
"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": "d7583e0c-519a-4fff-96fc-76711ac89429",
"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",
" TNLayer(),\n",
" TNLayer(),\n",
" TNLayer(),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 36,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_3\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_10 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_11 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_12 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_13 (Dense) (None, 1024) 1049600 \n",
" \n",
" tn_layer_9 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_10 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_11 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_14 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 3168257 (12.09 MB)\n",
"Trainable params: 3168257 (12.09 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": 37,
"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": "06dac289-a7e0-4e3e-9013-647728be6ed1"
},
"execution_count": 38,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712630230.7699065\n",
"Tue Apr 9 02:37:10 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "88bf3270-a31a-41aa-b1c3-eed523a458da",
"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": 39,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 2s - loss: 1.0021 - 2s/epoch - 135ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.9782 - 240ms/epoch - 16ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.2250 - 240ms/epoch - 16ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0515 - 235ms/epoch - 16ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0332 - 246ms/epoch - 16ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0229 - 240ms/epoch - 16ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0169 - 243ms/epoch - 16ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0138 - 233ms/epoch - 16ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0106 - 225ms/epoch - 15ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0093 - 225ms/epoch - 15ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0140 - 240ms/epoch - 16ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0058 - 228ms/epoch - 15ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0031 - 232ms/epoch - 15ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0019 - 228ms/epoch - 15ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0011 - 232ms/epoch - 15ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 6.8535e-04 - 226ms/epoch - 15ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 4.1511e-04 - 227ms/epoch - 15ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 2.1287e-04 - 222ms/epoch - 15ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 8.6161e-05 - 216ms/epoch - 14ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 3.5066e-05 - 228ms/epoch - 15ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 1.9260e-05 - 223ms/epoch - 15ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 1.2056e-05 - 231ms/epoch - 15ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 9.1563e-06 - 232ms/epoch - 15ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 7.8496e-06 - 214ms/epoch - 14ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 6.0445e-06 - 228ms/epoch - 15ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 5.0573e-06 - 224ms/epoch - 15ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 4.8231e-06 - 231ms/epoch - 15ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 3.6535e-06 - 226ms/epoch - 15ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 3.5497e-06 - 228ms/epoch - 15ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 3.4731e-06 - 226ms/epoch - 15ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 2.8123e-06 - 227ms/epoch - 15ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 2.8230e-06 - 229ms/epoch - 15ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 2.6197e-06 - 236ms/epoch - 16ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 2.2368e-06 - 234ms/epoch - 16ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 2.3085e-06 - 235ms/epoch - 16ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 2.2436e-06 - 223ms/epoch - 15ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 2.0750e-06 - 236ms/epoch - 16ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 2.0037e-06 - 231ms/epoch - 15ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 1.6620e-06 - 228ms/epoch - 15ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 1.9247e-06 - 232ms/epoch - 15ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 1.6047e-06 - 225ms/epoch - 15ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 1.6424e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 2.0375e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 1.9738e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 1.4739e-06 - 225ms/epoch - 15ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 1.4346e-06 - 224ms/epoch - 15ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 1.2279e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 1.5187e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 1.6870e-06 - 229ms/epoch - 15ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 1.5497e-06 - 223ms/epoch - 15ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 1.5124e-06 - 230ms/epoch - 15ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 1.8742e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 1.4984e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 1.2579e-06 - 237ms/epoch - 16ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 9.3107e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 8.6468e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 8.5909e-07 - 223ms/epoch - 15ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 8.4545e-07 - 226ms/epoch - 15ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 6.3071e-07 - 226ms/epoch - 15ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 6.7028e-07 - 233ms/epoch - 16ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 6.6049e-07 - 229ms/epoch - 15ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 9.1953e-07 - 235ms/epoch - 16ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 1.1641e-06 - 229ms/epoch - 15ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 7.1967e-07 - 218ms/epoch - 15ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 6.5827e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 6.1791e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 4.9626e-07 - 229ms/epoch - 15ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 4.5524e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 5.0329e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 4.7793e-07 - 226ms/epoch - 15ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 4.3502e-07 - 233ms/epoch - 16ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 4.7740e-07 - 230ms/epoch - 15ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 4.2559e-07 - 224ms/epoch - 15ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 4.1873e-07 - 218ms/epoch - 15ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 7.5071e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 6.1421e-07 - 229ms/epoch - 15ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 6.1946e-07 - 229ms/epoch - 15ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 3.6378e-07 - 216ms/epoch - 14ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 2.6986e-07 - 221ms/epoch - 15ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 3.9456e-07 - 233ms/epoch - 16ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 4.1445e-07 - 227ms/epoch - 15ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 3.1626e-07 - 232ms/epoch - 15ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 4.4256e-07 - 233ms/epoch - 16ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 4.2354e-07 - 227ms/epoch - 15ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 4.5663e-07 - 233ms/epoch - 16ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 2.9720e-07 - 239ms/epoch - 16ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 3.3106e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 1.9928e-07 - 224ms/epoch - 15ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 4.2023e-07 - 218ms/epoch - 15ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 5.4734e-07 - 228ms/epoch - 15ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 4.9559e-07 - 215ms/epoch - 14ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 4.0145e-07 - 223ms/epoch - 15ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 2.7853e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 1.5738e-07 - 222ms/epoch - 15ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 1.3848e-07 - 219ms/epoch - 15ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 2.6055e-07 - 222ms/epoch - 15ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 2.1036e-07 - 221ms/epoch - 15ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 1.1972e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 2.2472e-07 - 233ms/epoch - 16ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 1.5616e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 2.4254e-07 - 223ms/epoch - 15ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 4.5082e-07 - 216ms/epoch - 14ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 2.8596e-07 - 228ms/epoch - 15ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 2.2696e-07 - 226ms/epoch - 15ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 3.1346e-07 - 232ms/epoch - 15ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 1.3620e-07 - 227ms/epoch - 15ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 1.2038e-07 - 227ms/epoch - 15ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 1.0196e-07 - 236ms/epoch - 16ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 1.7133e-07 - 231ms/epoch - 15ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 1.7665e-07 - 234ms/epoch - 16ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 4.2016e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 7.1458e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 2.5674e-07 - 228ms/epoch - 15ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 1.3550e-07 - 221ms/epoch - 15ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 9.3404e-08 - 224ms/epoch - 15ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 9.6276e-08 - 237ms/epoch - 16ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 1.6335e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 1.3702e-07 - 234ms/epoch - 16ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 3.3801e-07 - 230ms/epoch - 15ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 6.1405e-07 - 223ms/epoch - 15ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 9.1836e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 1.9760e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 1.7123e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 2.8557e-06 - 225ms/epoch - 15ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 6.7009e-06 - 230ms/epoch - 15ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 1.0459e-05 - 222ms/epoch - 15ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 1.1726e-04 - 233ms/epoch - 16ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 2.2496e-04 - 237ms/epoch - 16ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 5.0590e-05 - 240ms/epoch - 16ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 1.8238e-05 - 230ms/epoch - 15ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 4.1103e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 2.5151e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 7.4446e-07 - 238ms/epoch - 16ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 1.0482e-06 - 224ms/epoch - 15ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 3.4123e-07 - 218ms/epoch - 15ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 2.8008e-07 - 227ms/epoch - 15ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 3.1427e-07 - 227ms/epoch - 15ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 3.1730e-07 - 222ms/epoch - 15ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 5.0125e-07 - 228ms/epoch - 15ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 1.8739e-06 - 226ms/epoch - 15ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 1.4904e-06 - 221ms/epoch - 15ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 1.8321e-06 - 223ms/epoch - 15ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 1.4117e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 1.3626e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 1.0856e-06 - 227ms/epoch - 15ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 1.5722e-06 - 225ms/epoch - 15ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 1.1345e-05 - 241ms/epoch - 16ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 2.1479e-05 - 229ms/epoch - 15ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 1.0639e-05 - 219ms/epoch - 15ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 8.2834e-06 - 228ms/epoch - 15ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 2.8168e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 8.2788e-07 - 234ms/epoch - 16ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 9.3748e-07 - 228ms/epoch - 15ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 3.4147e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 5.1821e-07 - 235ms/epoch - 16ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 1.4594e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 9.0278e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 6.0766e-07 - 218ms/epoch - 15ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 1.0663e-05 - 220ms/epoch - 15ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 3.1789e-05 - 226ms/epoch - 15ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 1.4866e-05 - 233ms/epoch - 16ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 2.0370e-05 - 232ms/epoch - 15ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 1.5614e-05 - 232ms/epoch - 15ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 1.0005e-05 - 227ms/epoch - 15ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 1.0035e-05 - 225ms/epoch - 15ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 4.7968e-06 - 227ms/epoch - 15ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 3.7850e-06 - 225ms/epoch - 15ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 5.0898e-06 - 230ms/epoch - 15ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 7.1516e-06 - 219ms/epoch - 15ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 1.1868e-06 - 233ms/epoch - 16ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 1.2939e-06 - 225ms/epoch - 15ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 6.3154e-07 - 237ms/epoch - 16ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 1.0560e-07 - 231ms/epoch - 15ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 4.1908e-07 - 246ms/epoch - 16ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 3.3817e-07 - 229ms/epoch - 15ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 5.3641e-07 - 239ms/epoch - 16ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 6.8340e-07 - 234ms/epoch - 16ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 4.2745e-07 - 236ms/epoch - 16ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 4.0081e-07 - 235ms/epoch - 16ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 6.8553e-07 - 226ms/epoch - 15ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 2.0027e-06 - 225ms/epoch - 15ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 8.0469e-07 - 236ms/epoch - 16ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 5.3155e-07 - 234ms/epoch - 16ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 6.2495e-07 - 235ms/epoch - 16ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 6.3543e-07 - 232ms/epoch - 15ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 2.5458e-06 - 218ms/epoch - 15ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 2.2451e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 1.5534e-05 - 226ms/epoch - 15ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 2.5841e-05 - 221ms/epoch - 15ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 5.1853e-05 - 225ms/epoch - 15ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 2.4748e-05 - 222ms/epoch - 15ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 2.2384e-05 - 228ms/epoch - 15ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 6.2447e-05 - 222ms/epoch - 15ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 5.1642e-05 - 226ms/epoch - 15ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 1.5347e-04 - 221ms/epoch - 15ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 1.4377e-04 - 223ms/epoch - 15ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 1.1889e-04 - 229ms/epoch - 15ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 6.0517e-05 - 231ms/epoch - 15ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 1.5623e-05 - 226ms/epoch - 15ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 3.1723e-06 - 236ms/epoch - 16ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 1.2698e-06 - 230ms/epoch - 15ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 6.7105e-06 - 236ms/epoch - 16ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 1.8511e-05 - 231ms/epoch - 15ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 3.1429e-06 - 232ms/epoch - 15ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 1.1749e-06 - 226ms/epoch - 15ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 4.1703e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 3.5164e-07 - 239ms/epoch - 16ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 2.5251e-07 - 227ms/epoch - 15ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 1.3698e-07 - 236ms/epoch - 16ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 9.2618e-08 - 215ms/epoch - 14ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 8.6535e-08 - 217ms/epoch - 14ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 1.3732e-07 - 224ms/epoch - 15ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 3.4113e-07 - 223ms/epoch - 15ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 1.1493e-07 - 234ms/epoch - 16ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 5.0553e-07 - 219ms/epoch - 15ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 1.4288e-06 - 223ms/epoch - 15ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 9.5950e-07 - 226ms/epoch - 15ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 3.4609e-07 - 228ms/epoch - 15ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 9.9875e-08 - 212ms/epoch - 14ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 1.1411e-07 - 216ms/epoch - 14ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 1.1009e-07 - 223ms/epoch - 15ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 4.9944e-08 - 225ms/epoch - 15ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 7.4368e-08 - 221ms/epoch - 15ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 1.0203e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.0192e-07 - 233ms/epoch - 16ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 3.5590e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 1.3797e-07 - 228ms/epoch - 15ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 9.5441e-07 - 230ms/epoch - 15ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 2.7173e-07 - 233ms/epoch - 16ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 1.7664e-07 - 242ms/epoch - 16ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 8.7350e-08 - 230ms/epoch - 15ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 3.3889e-07 - 238ms/epoch - 16ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 2.4895e-07 - 226ms/epoch - 15ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 9.0826e-08 - 235ms/epoch - 16ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 3.2138e-08 - 220ms/epoch - 15ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 2.3144e-08 - 226ms/epoch - 15ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 1.8279e-08 - 222ms/epoch - 15ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 5.9132e-08 - 226ms/epoch - 15ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 1.4624e-08 - 230ms/epoch - 15ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 2.1395e-08 - 217ms/epoch - 14ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 2.8792e-08 - 232ms/epoch - 15ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 2.3669e-07 - 226ms/epoch - 15ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 2.5480e-07 - 238ms/epoch - 16ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 8.4692e-08 - 222ms/epoch - 15ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 3.6256e-07 - 224ms/epoch - 15ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 7.0146e-06 - 223ms/epoch - 15ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 3.7262e-06 - 219ms/epoch - 15ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 2.2273e-06 - 230ms/epoch - 15ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 1.2544e-05 - 231ms/epoch - 15ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 2.8590e-04 - 229ms/epoch - 15ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 0.0059 - 232ms/epoch - 15ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 0.0540 - 230ms/epoch - 15ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 0.0336 - 226ms/epoch - 15ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 0.0933 - 226ms/epoch - 15ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 0.0098 - 220ms/epoch - 15ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 0.0068 - 233ms/epoch - 16ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 0.0162 - 223ms/epoch - 15ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 0.0156 - 225ms/epoch - 15ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 0.0015 - 234ms/epoch - 16ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 2.2518e-04 - 225ms/epoch - 15ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 5.1927e-05 - 217ms/epoch - 14ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 9.7206e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 5.2753e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 4.3394e-06 - 224ms/epoch - 15ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 3.3445e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 2.8683e-06 - 223ms/epoch - 15ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 1.9917e-06 - 221ms/epoch - 15ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 1.7798e-06 - 226ms/epoch - 15ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 1.7421e-06 - 221ms/epoch - 15ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 1.9916e-06 - 227ms/epoch - 15ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 1.5642e-06 - 229ms/epoch - 15ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 1.3961e-06 - 225ms/epoch - 15ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 1.0693e-06 - 231ms/epoch - 15ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 1.0093e-06 - 218ms/epoch - 15ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 8.3988e-07 - 219ms/epoch - 15ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 7.5933e-07 - 248ms/epoch - 17ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 7.4310e-07 - 221ms/epoch - 15ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 6.3554e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 6.1666e-07 - 224ms/epoch - 15ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 5.9289e-07 - 221ms/epoch - 15ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 5.3107e-07 - 228ms/epoch - 15ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 5.5663e-07 - 219ms/epoch - 15ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 4.8481e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 4.5875e-07 - 228ms/epoch - 15ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 4.0242e-07 - 223ms/epoch - 15ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 4.4616e-07 - 221ms/epoch - 15ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 4.3970e-07 - 228ms/epoch - 15ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 4.4119e-07 - 233ms/epoch - 16ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 5.1351e-07 - 223ms/epoch - 15ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 3.6918e-07 - 230ms/epoch - 15ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 2.8036e-07 - 232ms/epoch - 15ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 2.9334e-07 - 232ms/epoch - 15ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 4.3580e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 3.7172e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 3.7023e-07 - 227ms/epoch - 15ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 2.7273e-07 - 239ms/epoch - 16ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 2.4306e-07 - 221ms/epoch - 15ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 2.1635e-07 - 224ms/epoch - 15ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 2.0641e-07 - 224ms/epoch - 15ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 2.0106e-07 - 222ms/epoch - 15ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7f3b905b1930>"
]
},
"metadata": {},
"execution_count": 39
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "a5178311-f327-4a8a-d5bb-572d83e56a15",
"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": 40,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 1s 7ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7f3a8031f1c0>"
]
},
"metadata": {},
"execution_count": 40
},
{
"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": "0c6c17e0-932c-4c24-cb0f-aa974bb6d175"
},
"execution_count": 41,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712630302.1515276\n",
"Tue Apr 9 02:38:22 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": "18c83f1c-1385-478b-e6b8-803a1bf67eca"
},
"execution_count": 42,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712630302.1575177\n",
"Tue Apr 9 02:38:22 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": 1996
},
"id": "95xed6YyDClf",
"outputId": "bbf7663b-6991-466f-9708-1c81e252c1d6"
},
"execution_count": 43,
"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",
"161 1.000000\n",
"377 0.804166\n",
"37 0.526937\n",
"239 0.358587\n",
"327 0.311096\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 0.010721\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.000827\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.000364\n",
"1 0.000515\n",
"2 0.000528\n",
"3 0.001357\n",
"4 0.001847\n",
"5 0.002580\n",
"6 0.002660\n",
"Normalized Saliency Sum: Saliency 5.146019\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.068292\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 11.133526\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 138.015198\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.004664\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 637.001099\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000273\n",
"1 0.001079\n",
"2 0.001293\n",
"3 0.001850\n",
"4 0.002191\n",
".. ...\n",
"475 5.119881\n",
"476 5.136941\n",
"477 5.144647\n",
"478 5.145474\n",
"479 5.146018\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 5.693324e-07\n",
"1 2.248826e-06\n",
"2 2.693775e-06\n",
"3 3.854469e-06\n",
"4 4.565455e-06\n",
".. ...\n",
"475 1.066642e-02\n",
"476 1.070196e-02\n",
"477 1.071802e-02\n",
"478 1.071974e-02\n",
"479 1.072087e-02\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.06905815\n",
"Normalized Saliency 25th Percentile: Saliency 0.000461\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.00282\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.002359\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": "069c40c7-9e01-424d-e082-470c335a46b5"
},
"execution_count": 44,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712630304.2600067\n",
"Tue Apr 9 02:38:24 2024\n"
]
}
]
}
]
}