Datasets
Models
Downloads: 1
1262 lines (1262 with data), 217.4 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": 122,
"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": 123,
"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": "5e113b1f-0639-4f45-8e65-86b59787cbd0",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
}
},
"source": [
"Dense = tf.keras.layers.Dense\n",
"tn_model = tf.keras.Sequential(\n",
" [\n",
" tf.keras.Input(shape=(2,)),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Start Modified Layers\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 124,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_11\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_45 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_46 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_47 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_48 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_49 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_50 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_51 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 5252097 (20.04 MB)\n",
"Trainable params: 5252097 (20.04 MB)\n",
"Non-trainable params: 0 (0.00 Byte)\n",
"_________________________________________________________________\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "GWwoYp0WnsLA"
},
"source": [
"# Training a model\n",
"\n",
"You can train the TN model just as you would a normal neural network model! Here, we give an example of how to do it in Keras."
]
},
{
"cell_type": "code",
"metadata": {
"id": "qDFzOC7sDBJ-"
},
"source": [
"X = np.concatenate([np.random.randn(120, 2) + np.array([3, 3]),\n",
" np.random.randn(120, 2) + np.array([-3, -3]),\n",
" np.random.randn(120, 2) + np.array([-3, 3]),\n",
" np.random.randn(120, 2) + np.array([3, -3])])\n",
"\n",
"Y = np.concatenate([np.ones((240)), -np.ones((240))])"
],
"execution_count": 125,
"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": "bb485d46-9db3-4c00-aed1-5d50bcab68e6"
},
"execution_count": 126,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712633830.6954975\n",
"Tue Apr 9 03:37:10 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "36074dcb-6d3a-4c52-8c81-6ea481375293",
"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": 127,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 0.3778 - 1s/epoch - 85ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.0845 - 276ms/epoch - 18ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.0561 - 274ms/epoch - 18ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0425 - 278ms/epoch - 19ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0351 - 275ms/epoch - 18ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0394 - 268ms/epoch - 18ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0376 - 281ms/epoch - 19ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0191 - 277ms/epoch - 18ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0084 - 274ms/epoch - 18ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0024 - 260ms/epoch - 17ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 5.7345e-04 - 264ms/epoch - 18ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 1.4971e-04 - 264ms/epoch - 18ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 6.3904e-05 - 263ms/epoch - 18ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 3.8599e-05 - 261ms/epoch - 17ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 2.1102e-05 - 265ms/epoch - 18ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 6.9013e-06 - 275ms/epoch - 18ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 4.1483e-06 - 271ms/epoch - 18ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 6.8194e-06 - 266ms/epoch - 18ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 4.0209e-06 - 261ms/epoch - 17ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 2.0835e-06 - 267ms/epoch - 18ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 1.5335e-06 - 268ms/epoch - 18ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 1.4401e-06 - 269ms/epoch - 18ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 1.1926e-06 - 275ms/epoch - 18ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 1.6044e-06 - 261ms/epoch - 17ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 2.2010e-06 - 258ms/epoch - 17ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 1.9721e-06 - 263ms/epoch - 18ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 1.3903e-06 - 261ms/epoch - 17ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 1.0622e-06 - 261ms/epoch - 17ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 1.1001e-06 - 259ms/epoch - 17ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 6.1895e-07 - 269ms/epoch - 18ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 5.7111e-07 - 265ms/epoch - 18ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 6.3559e-07 - 267ms/epoch - 18ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 1.8102e-06 - 266ms/epoch - 18ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 1.3123e-06 - 267ms/epoch - 18ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 2.6287e-06 - 262ms/epoch - 17ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 5.0530e-06 - 265ms/epoch - 18ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 1.5731e-06 - 269ms/epoch - 18ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 1.5765e-06 - 264ms/epoch - 18ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 3.6753e-06 - 255ms/epoch - 17ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 3.3019e-06 - 252ms/epoch - 17ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 2.0198e-06 - 267ms/epoch - 18ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 3.5187e-06 - 256ms/epoch - 17ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 8.3254e-06 - 262ms/epoch - 17ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 7.9769e-06 - 260ms/epoch - 17ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 5.0490e-06 - 252ms/epoch - 17ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 3.8128e-06 - 258ms/epoch - 17ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 6.6786e-06 - 254ms/epoch - 17ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 6.2713e-06 - 259ms/epoch - 17ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 7.2969e-06 - 252ms/epoch - 17ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 2.2827e-06 - 261ms/epoch - 17ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 3.0834e-06 - 258ms/epoch - 17ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 5.8847e-05 - 263ms/epoch - 18ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 1.3397e-04 - 257ms/epoch - 17ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 4.6410e-05 - 254ms/epoch - 17ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 1.1695e-05 - 259ms/epoch - 17ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 9.3823e-06 - 258ms/epoch - 17ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 3.9504e-05 - 262ms/epoch - 17ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 2.1176e-05 - 253ms/epoch - 17ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 1.0686e-05 - 261ms/epoch - 17ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 1.2536e-05 - 256ms/epoch - 17ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 3.7984e-05 - 262ms/epoch - 17ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 1.4770e-04 - 260ms/epoch - 17ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 4.8935e-04 - 259ms/epoch - 17ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 8.1386e-04 - 258ms/epoch - 17ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 5.1625e-04 - 262ms/epoch - 17ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 3.4967e-04 - 262ms/epoch - 17ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 1.2151e-04 - 258ms/epoch - 17ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 2.7546e-05 - 257ms/epoch - 17ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 8.8761e-06 - 268ms/epoch - 18ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 3.4951e-06 - 257ms/epoch - 17ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 9.9405e-06 - 267ms/epoch - 18ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 4.0322e-06 - 259ms/epoch - 17ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 1.3966e-06 - 261ms/epoch - 17ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 1.7787e-06 - 257ms/epoch - 17ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 2.7146e-06 - 259ms/epoch - 17ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 2.2340e-06 - 263ms/epoch - 18ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 1.3221e-06 - 259ms/epoch - 17ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 5.1021e-07 - 268ms/epoch - 18ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 4.5609e-07 - 262ms/epoch - 17ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 2.9248e-07 - 263ms/epoch - 18ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 1.2318e-06 - 255ms/epoch - 17ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 1.0526e-06 - 256ms/epoch - 17ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 1.0655e-06 - 257ms/epoch - 17ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 3.3900e-07 - 264ms/epoch - 18ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 1.9783e-07 - 257ms/epoch - 17ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 2.3748e-07 - 257ms/epoch - 17ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 2.6380e-07 - 260ms/epoch - 17ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 1.4933e-07 - 264ms/epoch - 18ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 1.5187e-07 - 269ms/epoch - 18ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 1.9137e-07 - 264ms/epoch - 18ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 2.1250e-07 - 266ms/epoch - 18ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 1.9669e-07 - 259ms/epoch - 17ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 1.7929e-07 - 256ms/epoch - 17ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 1.6538e-07 - 252ms/epoch - 17ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 1.5746e-07 - 255ms/epoch - 17ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 5.3034e-07 - 249ms/epoch - 17ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 9.4150e-07 - 252ms/epoch - 17ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 3.5810e-07 - 259ms/epoch - 17ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 5.7005e-07 - 255ms/epoch - 17ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 5.2839e-07 - 254ms/epoch - 17ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 1.1431e-06 - 261ms/epoch - 17ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 2.8225e-06 - 258ms/epoch - 17ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 2.2271e-06 - 265ms/epoch - 18ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 3.2246e-06 - 249ms/epoch - 17ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 7.8872e-07 - 254ms/epoch - 17ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 5.6330e-07 - 260ms/epoch - 17ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 7.2915e-07 - 253ms/epoch - 17ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 1.1597e-06 - 248ms/epoch - 17ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 6.4688e-07 - 249ms/epoch - 17ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 2.2764e-07 - 259ms/epoch - 17ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 1.3075e-07 - 261ms/epoch - 17ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 1.3168e-07 - 251ms/epoch - 17ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 1.1794e-07 - 252ms/epoch - 17ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 1.1861e-07 - 259ms/epoch - 17ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 4.0190e-07 - 260ms/epoch - 17ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 2.2366e-06 - 259ms/epoch - 17ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 1.7412e-06 - 250ms/epoch - 17ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 2.4537e-06 - 264ms/epoch - 18ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 1.2177e-06 - 257ms/epoch - 17ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 1.1247e-06 - 257ms/epoch - 17ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 1.4269e-06 - 251ms/epoch - 17ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 4.6098e-06 - 253ms/epoch - 17ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 1.5626e-05 - 258ms/epoch - 17ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 8.3913e-06 - 255ms/epoch - 17ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 5.9126e-06 - 258ms/epoch - 17ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 3.0704e-05 - 266ms/epoch - 18ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 1.8747e-04 - 253ms/epoch - 17ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 2.0282e-04 - 253ms/epoch - 17ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 8.0088e-05 - 254ms/epoch - 17ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 1.1141e-04 - 252ms/epoch - 17ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 6.8919e-05 - 253ms/epoch - 17ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 8.3276e-05 - 261ms/epoch - 17ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 2.5737e-04 - 265ms/epoch - 18ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 2.0717e-04 - 263ms/epoch - 18ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 1.8990e-04 - 255ms/epoch - 17ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 8.8504e-05 - 261ms/epoch - 17ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 2.7130e-05 - 258ms/epoch - 17ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 1.7335e-05 - 257ms/epoch - 17ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 5.3387e-06 - 262ms/epoch - 17ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 3.7392e-06 - 263ms/epoch - 18ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 1.4878e-06 - 268ms/epoch - 18ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 4.1386e-06 - 263ms/epoch - 18ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 2.8284e-06 - 260ms/epoch - 17ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 3.3013e-06 - 263ms/epoch - 18ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 2.5025e-06 - 271ms/epoch - 18ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 1.0864e-06 - 267ms/epoch - 18ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 7.9415e-07 - 267ms/epoch - 18ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 8.7661e-07 - 256ms/epoch - 17ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 1.7812e-06 - 257ms/epoch - 17ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 2.3489e-06 - 261ms/epoch - 17ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 9.4262e-07 - 253ms/epoch - 17ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 1.0916e-06 - 258ms/epoch - 17ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 6.4473e-07 - 266ms/epoch - 18ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 1.8620e-07 - 253ms/epoch - 17ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 3.9467e-07 - 267ms/epoch - 18ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 3.0973e-07 - 269ms/epoch - 18ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 3.0907e-07 - 261ms/epoch - 17ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 1.5748e-07 - 259ms/epoch - 17ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 4.0201e-07 - 254ms/epoch - 17ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 9.4387e-07 - 263ms/epoch - 18ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 4.9554e-07 - 263ms/epoch - 18ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 1.6688e-06 - 263ms/epoch - 18ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 4.3077e-06 - 254ms/epoch - 17ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 2.1229e-06 - 250ms/epoch - 17ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 1.5251e-06 - 256ms/epoch - 17ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 1.2186e-06 - 252ms/epoch - 17ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 5.4912e-07 - 253ms/epoch - 17ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 2.6410e-07 - 249ms/epoch - 17ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 1.8500e-07 - 253ms/epoch - 17ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 2.6426e-07 - 253ms/epoch - 17ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 8.8755e-07 - 256ms/epoch - 17ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 6.4556e-07 - 251ms/epoch - 17ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 4.5370e-07 - 256ms/epoch - 17ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 2.1330e-07 - 258ms/epoch - 17ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 2.5614e-07 - 252ms/epoch - 17ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 8.9647e-07 - 257ms/epoch - 17ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 6.8496e-07 - 255ms/epoch - 17ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 1.8894e-07 - 260ms/epoch - 17ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 1.6284e-07 - 253ms/epoch - 17ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 1.4168e-07 - 254ms/epoch - 17ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 8.3923e-08 - 259ms/epoch - 17ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 1.2021e-07 - 256ms/epoch - 17ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 1.1806e-07 - 260ms/epoch - 17ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 1.1181e-07 - 256ms/epoch - 17ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 1.6228e-07 - 255ms/epoch - 17ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 9.5482e-07 - 256ms/epoch - 17ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 2.4422e-06 - 251ms/epoch - 17ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 2.1351e-06 - 251ms/epoch - 17ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 8.1382e-07 - 258ms/epoch - 17ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 2.8060e-06 - 248ms/epoch - 17ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 1.5649e-05 - 247ms/epoch - 16ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 1.0993e-05 - 246ms/epoch - 16ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 1.5759e-04 - 249ms/epoch - 17ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 6.3792e-04 - 263ms/epoch - 18ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 0.0011 - 259ms/epoch - 17ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 0.0040 - 249ms/epoch - 17ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 0.2047 - 255ms/epoch - 17ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 0.0821 - 254ms/epoch - 17ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 0.0569 - 256ms/epoch - 17ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 0.0183 - 257ms/epoch - 17ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 0.0333 - 253ms/epoch - 17ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 0.0136 - 251ms/epoch - 17ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 0.0027 - 268ms/epoch - 18ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 0.0010 - 253ms/epoch - 17ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 5.2454e-04 - 251ms/epoch - 17ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 1.5321e-04 - 260ms/epoch - 17ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 6.7280e-05 - 257ms/epoch - 17ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 4.4212e-05 - 258ms/epoch - 17ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 2.3646e-05 - 257ms/epoch - 17ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 1.4981e-05 - 259ms/epoch - 17ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 1.1119e-05 - 256ms/epoch - 17ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 7.4597e-06 - 260ms/epoch - 17ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 6.0949e-06 - 259ms/epoch - 17ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 4.5891e-06 - 255ms/epoch - 17ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 3.8256e-06 - 257ms/epoch - 17ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 3.4138e-06 - 266ms/epoch - 18ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 2.7108e-06 - 255ms/epoch - 17ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 2.3913e-06 - 256ms/epoch - 17ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 2.1950e-06 - 258ms/epoch - 17ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 1.9130e-06 - 268ms/epoch - 18ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 1.9039e-06 - 267ms/epoch - 18ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 1.3358e-06 - 262ms/epoch - 17ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 1.3457e-06 - 267ms/epoch - 18ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 1.1638e-06 - 269ms/epoch - 18ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.1425e-06 - 264ms/epoch - 18ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 1.2959e-06 - 264ms/epoch - 18ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 1.3811e-06 - 263ms/epoch - 18ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 8.6700e-07 - 273ms/epoch - 18ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 6.9032e-07 - 257ms/epoch - 17ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 6.5129e-07 - 261ms/epoch - 17ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 6.7010e-07 - 252ms/epoch - 17ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 5.6940e-07 - 258ms/epoch - 17ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 4.4536e-07 - 257ms/epoch - 17ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 4.5153e-07 - 255ms/epoch - 17ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 3.7663e-07 - 260ms/epoch - 17ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 3.8209e-07 - 256ms/epoch - 17ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 3.7210e-07 - 252ms/epoch - 17ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 4.0504e-07 - 267ms/epoch - 18ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 3.9925e-07 - 252ms/epoch - 17ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 3.3417e-07 - 255ms/epoch - 17ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 3.1564e-07 - 263ms/epoch - 18ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 2.6226e-07 - 255ms/epoch - 17ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 3.1767e-07 - 260ms/epoch - 17ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 2.4356e-07 - 261ms/epoch - 17ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 2.3545e-07 - 255ms/epoch - 17ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 2.9424e-07 - 264ms/epoch - 18ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 2.5610e-07 - 267ms/epoch - 18ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 3.1529e-07 - 256ms/epoch - 17ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 4.0959e-07 - 255ms/epoch - 17ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 3.7208e-07 - 264ms/epoch - 18ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 2.0490e-07 - 255ms/epoch - 17ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 2.0291e-07 - 254ms/epoch - 17ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 2.1863e-07 - 261ms/epoch - 17ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 2.1423e-07 - 252ms/epoch - 17ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 4.6572e-07 - 256ms/epoch - 17ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 3.9148e-07 - 258ms/epoch - 17ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 3.4822e-07 - 259ms/epoch - 17ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 3.3698e-07 - 259ms/epoch - 17ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 1.7296e-07 - 263ms/epoch - 18ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 1.4464e-07 - 262ms/epoch - 17ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 1.2297e-07 - 276ms/epoch - 18ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 1.4718e-07 - 260ms/epoch - 17ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 1.1964e-07 - 256ms/epoch - 17ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 1.8089e-07 - 268ms/epoch - 18ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 1.7324e-07 - 260ms/epoch - 17ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 1.7356e-07 - 258ms/epoch - 17ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 1.1058e-07 - 263ms/epoch - 18ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 1.3033e-07 - 254ms/epoch - 17ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 2.2592e-07 - 262ms/epoch - 17ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 1.9894e-07 - 262ms/epoch - 17ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 1.9528e-07 - 260ms/epoch - 17ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 1.5507e-07 - 266ms/epoch - 18ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 1.0684e-07 - 264ms/epoch - 18ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 1.1442e-07 - 255ms/epoch - 17ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 8.8264e-08 - 268ms/epoch - 18ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 7.9688e-08 - 265ms/epoch - 18ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 8.0020e-08 - 262ms/epoch - 17ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 9.3920e-08 - 255ms/epoch - 17ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 1.1001e-07 - 255ms/epoch - 17ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 1.4456e-07 - 260ms/epoch - 17ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 8.3111e-08 - 260ms/epoch - 17ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 1.1554e-07 - 264ms/epoch - 18ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 8.4918e-08 - 263ms/epoch - 18ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 9.9200e-08 - 257ms/epoch - 17ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 8.5386e-08 - 269ms/epoch - 18ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 1.2268e-07 - 259ms/epoch - 17ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 1.4155e-07 - 262ms/epoch - 17ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 2.4688e-07 - 263ms/epoch - 18ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 3.3057e-07 - 257ms/epoch - 17ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 1.4866e-07 - 264ms/epoch - 18ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 8.3178e-08 - 270ms/epoch - 18ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 8.2846e-08 - 258ms/epoch - 17ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 9.3065e-08 - 266ms/epoch - 18ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 5.7005e-08 - 261ms/epoch - 17ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 7.0167e-08 - 269ms/epoch - 18ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 5.4782e-08 - 268ms/epoch - 18ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 6.8455e-08 - 265ms/epoch - 18ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 5.5980e-08 - 264ms/epoch - 18ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 4.8600e-08 - 273ms/epoch - 18ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 6.0228e-08 - 264ms/epoch - 18ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7f3a807b7580>"
]
},
"metadata": {},
"execution_count": 127
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "a1050e1a-dda7-4ab5-cecf-fb12d6819d08",
"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": 128,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 5ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7f3a187cfe20>"
]
},
"metadata": {},
"execution_count": 128
},
{
"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": "539b25c4-261d-4cae-e2ad-4c73d2f7fbfc"
},
"execution_count": 129,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712633910.8257244\n",
"Tue Apr 9 03:38:30 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": "265d6088-044d-4d2a-b7df-3d33ae2751a6"
},
"execution_count": 130,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712633910.8321862\n",
"Tue Apr 9 03:38:30 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": 1859
},
"id": "95xed6YyDClf",
"outputId": "053018ba-7c23-4c5b-9daa-7bda317f8482"
},
"execution_count": 131,
"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",
"327 1.000000\n",
"377 0.585489\n",
"370 0.500220\n",
"423 0.464183\n",
"262 0.338702\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 0.016081\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.003992\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.002928\n",
"Normalized Saliency Sum: Saliency 7.719094\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.068719\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 9.331953\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 107.261612\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.004722\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 427.317871\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.002022\n",
"1 0.005217\n",
"2 0.006747\n",
"3 0.010829\n",
"4 0.011636\n",
".. ...\n",
"475 7.695082\n",
"476 7.710361\n",
"477 7.712762\n",
"478 7.716906\n",
"479 7.719093\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000004\n",
"1 0.000011\n",
"2 0.000014\n",
"3 0.000023\n",
"4 0.000024\n",
".. ...\n",
"475 0.016031\n",
"476 0.016063\n",
"477 0.016068\n",
"478 0.016077\n",
"479 0.016081\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.070505746\n",
"Normalized Saliency 25th Percentile: Saliency 0.002184\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.007364\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.00518\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": "e7fa8870-0486-4d55-bcd2-1d566799cac8"
},
"execution_count": 132,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712633912.5265467\n",
"Tue Apr 9 03:38:32 2024\n"
]
}
]
}
]
}