Datasets
Models
Downloads: 1
1273 lines (1273 with data), 209.4 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": 13,
"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": 14,
"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": "a02711b6-e71b-42c3-a5b5-df7b12f254c8",
"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",
" TNLayer(),\n",
" TNLayer(),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 15,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_1\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_2 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_3 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_4 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_5 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_3 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 19457 (76.00 KB)\n",
"Trainable params: 19457 (76.00 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": [
"# Generate points forming concentric circles\n",
"num_points = 240 # Number of points for each circle\n",
"\n",
"# Inner circle\n",
"r1 = np.random.rand(num_points)\n",
"theta1 = np.random.rand(num_points) * 2 * np.pi\n",
"x1 = r1 * np.cos(theta1)\n",
"y1 = r1 * np.sin(theta1)\n",
"\n",
"# Outer circle\n",
"r2 = np.random.rand(num_points) + 1\n",
"theta2 = np.random.rand(num_points) * 2 * np.pi\n",
"x2 = r2 * np.cos(theta2)\n",
"y2 = r2 * np.sin(theta2)\n",
"\n",
"# Concatenate the points and labels\n",
"X = np.concatenate([np.column_stack((x1, y1)), np.column_stack((x2, y2))])\n",
"Y = np.concatenate([np.ones(num_points), -np.ones(num_points)])\n",
"\n",
"# Shuffle the data\n",
"shuffle_index = np.random.permutation(len(X))\n",
"X_shuffled = X[shuffle_index]\n",
"Y_shuffled = Y[shuffle_index]"
],
"execution_count": 16,
"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": "33222845-f2b6-4af2-e4ed-06200bc49a88"
},
"execution_count": 17,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712716567.3322396\n",
"Wed Apr 10 02:36:07 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "17636771-f243-44cb-aa00-26a8c5bd30c8",
"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": 18,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 1.0020 - 1s/epoch - 93ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 1.0001 - 73ms/epoch - 5ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 1.0001 - 69ms/epoch - 5ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.9859 - 71ms/epoch - 5ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.6123 - 66ms/epoch - 4ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.1755 - 67ms/epoch - 4ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.1300 - 69ms/epoch - 5ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0891 - 65ms/epoch - 4ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0545 - 65ms/epoch - 4ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0403 - 62ms/epoch - 4ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0571 - 62ms/epoch - 4ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0454 - 63ms/epoch - 4ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0230 - 60ms/epoch - 4ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0144 - 63ms/epoch - 4ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0127 - 64ms/epoch - 4ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0046 - 65ms/epoch - 4ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0318 - 62ms/epoch - 4ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0448 - 62ms/epoch - 4ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0293 - 62ms/epoch - 4ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0698 - 61ms/epoch - 4ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 0.0366 - 62ms/epoch - 4ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 0.0088 - 64ms/epoch - 4ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 0.0093 - 63ms/epoch - 4ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 0.0031 - 61ms/epoch - 4ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 0.0251 - 59ms/epoch - 4ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 0.0152 - 62ms/epoch - 4ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 0.0117 - 62ms/epoch - 4ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 0.0030 - 62ms/epoch - 4ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 0.0036 - 62ms/epoch - 4ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 0.0285 - 62ms/epoch - 4ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 0.0172 - 63ms/epoch - 4ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 0.0076 - 61ms/epoch - 4ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 0.0243 - 59ms/epoch - 4ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 0.0516 - 66ms/epoch - 4ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 0.0503 - 61ms/epoch - 4ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 0.0563 - 62ms/epoch - 4ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 0.0496 - 64ms/epoch - 4ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 0.0280 - 62ms/epoch - 4ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 0.0103 - 61ms/epoch - 4ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 0.0142 - 61ms/epoch - 4ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 0.0049 - 60ms/epoch - 4ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 0.0022 - 62ms/epoch - 4ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 0.0019 - 63ms/epoch - 4ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 0.0016 - 61ms/epoch - 4ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 0.0021 - 61ms/epoch - 4ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 9.6352e-04 - 67ms/epoch - 4ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 0.0032 - 66ms/epoch - 4ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 0.0030 - 64ms/epoch - 4ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 0.0077 - 63ms/epoch - 4ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 0.0176 - 64ms/epoch - 4ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 0.0272 - 64ms/epoch - 4ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 0.0140 - 66ms/epoch - 4ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 9.1025e-04 - 66ms/epoch - 4ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 3.5181e-04 - 62ms/epoch - 4ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 2.9596e-04 - 64ms/epoch - 4ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 5.7676e-04 - 64ms/epoch - 4ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 0.0017 - 63ms/epoch - 4ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 0.0223 - 65ms/epoch - 4ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 0.0139 - 70ms/epoch - 5ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 0.0107 - 64ms/epoch - 4ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 0.0049 - 64ms/epoch - 4ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 0.0041 - 62ms/epoch - 4ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 5.6507e-04 - 61ms/epoch - 4ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 3.3021e-05 - 62ms/epoch - 4ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 2.5001e-05 - 64ms/epoch - 4ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 9.2927e-06 - 63ms/epoch - 4ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 8.3121e-06 - 62ms/epoch - 4ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 7.3248e-06 - 62ms/epoch - 4ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 6.8689e-06 - 64ms/epoch - 4ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 6.1659e-06 - 64ms/epoch - 4ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 6.3707e-06 - 61ms/epoch - 4ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 6.7043e-06 - 63ms/epoch - 4ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 7.0160e-06 - 63ms/epoch - 4ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 1.6381e-05 - 65ms/epoch - 4ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 3.5327e-05 - 62ms/epoch - 4ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 1.2444e-05 - 60ms/epoch - 4ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 3.8970e-05 - 60ms/epoch - 4ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 1.6786e-05 - 62ms/epoch - 4ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 7.4567e-06 - 61ms/epoch - 4ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 4.5950e-06 - 61ms/epoch - 4ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 3.7222e-06 - 60ms/epoch - 4ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 4.1815e-06 - 65ms/epoch - 4ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 3.5488e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 4.9459e-06 - 67ms/epoch - 4ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 4.1310e-05 - 59ms/epoch - 4ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 6.6234e-05 - 59ms/epoch - 4ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 2.6201e-04 - 61ms/epoch - 4ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 8.6702e-05 - 61ms/epoch - 4ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 6.5770e-05 - 59ms/epoch - 4ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 1.5363e-04 - 60ms/epoch - 4ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 6.2001e-04 - 61ms/epoch - 4ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 1.2238e-04 - 61ms/epoch - 4ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 6.2949e-05 - 56ms/epoch - 4ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 3.9266e-05 - 57ms/epoch - 4ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 1.4139e-05 - 58ms/epoch - 4ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 5.1852e-05 - 60ms/epoch - 4ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 4.3538e-04 - 56ms/epoch - 4ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 0.0011 - 63ms/epoch - 4ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 5.7030e-04 - 57ms/epoch - 4ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 1.7217e-04 - 60ms/epoch - 4ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 1.9581e-04 - 60ms/epoch - 4ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 2.1176e-04 - 57ms/epoch - 4ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 9.3841e-05 - 58ms/epoch - 4ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 7.4221e-05 - 59ms/epoch - 4ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 7.4860e-05 - 60ms/epoch - 4ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 1.1438e-05 - 58ms/epoch - 4ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 9.3763e-06 - 61ms/epoch - 4ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 6.7289e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 4.4462e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 5.5895e-06 - 61ms/epoch - 4ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 4.4527e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 3.3966e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 3.9234e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 5.1331e-06 - 60ms/epoch - 4ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 2.5952e-06 - 56ms/epoch - 4ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 7.2392e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 8.9844e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 4.6455e-06 - 62ms/epoch - 4ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 2.7713e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 2.1972e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 1.9717e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 2.0014e-06 - 61ms/epoch - 4ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 3.2962e-06 - 60ms/epoch - 4ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 4.9576e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 4.1290e-06 - 56ms/epoch - 4ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 2.8701e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 2.1037e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 1.3764e-06 - 56ms/epoch - 4ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 1.6044e-06 - 55ms/epoch - 4ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 1.3200e-06 - 56ms/epoch - 4ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 1.7474e-06 - 62ms/epoch - 4ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 3.2121e-06 - 62ms/epoch - 4ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 3.3384e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 1.6330e-06 - 56ms/epoch - 4ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 1.7302e-06 - 61ms/epoch - 4ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 1.3628e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 1.9833e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 1.7483e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 2.1749e-06 - 55ms/epoch - 4ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 1.4342e-06 - 65ms/epoch - 4ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 1.0627e-06 - 63ms/epoch - 4ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 3.9627e-06 - 63ms/epoch - 4ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 8.8668e-06 - 61ms/epoch - 4ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 8.4250e-05 - 60ms/epoch - 4ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 5.8676e-05 - 62ms/epoch - 4ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 3.5250e-05 - 62ms/epoch - 4ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 4.3214e-04 - 60ms/epoch - 4ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 2.4251e-04 - 61ms/epoch - 4ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 2.0778e-04 - 61ms/epoch - 4ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 9.8481e-04 - 60ms/epoch - 4ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 0.0012 - 62ms/epoch - 4ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 0.0036 - 62ms/epoch - 4ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 0.0201 - 62ms/epoch - 4ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 0.0965 - 60ms/epoch - 4ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 0.1713 - 59ms/epoch - 4ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 0.1076 - 60ms/epoch - 4ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 0.0670 - 61ms/epoch - 4ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 0.0261 - 59ms/epoch - 4ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 0.0374 - 58ms/epoch - 4ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 0.0271 - 55ms/epoch - 4ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 0.0166 - 54ms/epoch - 4ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 0.0241 - 57ms/epoch - 4ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 0.0058 - 61ms/epoch - 4ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 0.0029 - 56ms/epoch - 4ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 0.0095 - 58ms/epoch - 4ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 0.0071 - 58ms/epoch - 4ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 0.0032 - 56ms/epoch - 4ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 0.0211 - 58ms/epoch - 4ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 0.0387 - 58ms/epoch - 4ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 0.0388 - 58ms/epoch - 4ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 0.0273 - 58ms/epoch - 4ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 0.0056 - 57ms/epoch - 4ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 0.0018 - 57ms/epoch - 4ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 0.0035 - 56ms/epoch - 4ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 0.0078 - 55ms/epoch - 4ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 0.0073 - 58ms/epoch - 4ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 0.0114 - 55ms/epoch - 4ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 0.0106 - 56ms/epoch - 4ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 0.0471 - 55ms/epoch - 4ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 0.0274 - 56ms/epoch - 4ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 0.0735 - 56ms/epoch - 4ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 0.0902 - 57ms/epoch - 4ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 0.0307 - 55ms/epoch - 4ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 0.0173 - 55ms/epoch - 4ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 0.0117 - 55ms/epoch - 4ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 0.0036 - 55ms/epoch - 4ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 0.0020 - 55ms/epoch - 4ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 0.0017 - 55ms/epoch - 4ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 8.1168e-04 - 55ms/epoch - 4ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 6.1157e-04 - 58ms/epoch - 4ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 3.6213e-04 - 57ms/epoch - 4ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 4.6052e-05 - 56ms/epoch - 4ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 4.5173e-05 - 56ms/epoch - 4ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 2.4787e-05 - 58ms/epoch - 4ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 1.5432e-05 - 58ms/epoch - 4ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 1.3391e-05 - 56ms/epoch - 4ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 1.2296e-05 - 55ms/epoch - 4ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 9.1417e-06 - 56ms/epoch - 4ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 8.1251e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 7.0672e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 5.8134e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 5.2286e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 4.9304e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 4.5814e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 4.1609e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 4.0069e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 3.9654e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 3.4443e-06 - 56ms/epoch - 4ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 3.6692e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 3.7334e-06 - 56ms/epoch - 4ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 4.3913e-06 - 55ms/epoch - 4ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 3.8205e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 2.7151e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 2.3159e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 2.3168e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 3.4111e-06 - 56ms/epoch - 4ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 3.3034e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 2.1755e-06 - 60ms/epoch - 4ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 2.0316e-06 - 62ms/epoch - 4ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 1.8873e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 1.8478e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 1.6226e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 1.5378e-06 - 60ms/epoch - 4ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 1.7001e-06 - 60ms/epoch - 4ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.6512e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 1.6189e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 1.5912e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 1.5548e-06 - 60ms/epoch - 4ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 2.0701e-06 - 61ms/epoch - 4ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 1.5425e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 1.4968e-06 - 61ms/epoch - 4ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 1.6313e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 2.0655e-06 - 56ms/epoch - 4ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 1.1052e-06 - 60ms/epoch - 4ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 1.9129e-06 - 60ms/epoch - 4ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 2.0871e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 1.3979e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 1.6935e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 4.2097e-06 - 55ms/epoch - 4ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 4.0676e-06 - 56ms/epoch - 4ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 1.0932e-06 - 54ms/epoch - 4ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 9.9956e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 2.5620e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 1.3255e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 1.6808e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 6.9664e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 1.2377e-05 - 57ms/epoch - 4ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 7.7628e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 9.1102e-06 - 56ms/epoch - 4ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 2.4488e-05 - 59ms/epoch - 4ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 3.4085e-05 - 60ms/epoch - 4ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 7.8207e-05 - 59ms/epoch - 4ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 4.2830e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 6.2197e-06 - 55ms/epoch - 4ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 1.3699e-06 - 55ms/epoch - 4ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 8.6856e-07 - 53ms/epoch - 4ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 3.5474e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 6.9940e-06 - 56ms/epoch - 4ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 1.2018e-05 - 56ms/epoch - 4ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 8.9503e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 1.9238e-05 - 57ms/epoch - 4ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 4.3505e-05 - 54ms/epoch - 4ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 2.6366e-05 - 57ms/epoch - 4ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 2.8519e-05 - 56ms/epoch - 4ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 3.2493e-05 - 56ms/epoch - 4ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 3.3674e-05 - 56ms/epoch - 4ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 3.9570e-05 - 57ms/epoch - 4ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 1.4406e-04 - 57ms/epoch - 4ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 0.0018 - 58ms/epoch - 4ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 8.4657e-04 - 59ms/epoch - 4ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 4.8473e-04 - 56ms/epoch - 4ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 0.0054 - 56ms/epoch - 4ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 0.0308 - 55ms/epoch - 4ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 0.0239 - 57ms/epoch - 4ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 0.0143 - 56ms/epoch - 4ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 0.0257 - 57ms/epoch - 4ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 0.0376 - 56ms/epoch - 4ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 0.0163 - 56ms/epoch - 4ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 0.0040 - 59ms/epoch - 4ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 0.0080 - 56ms/epoch - 4ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 0.0077 - 56ms/epoch - 4ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 0.0248 - 57ms/epoch - 4ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 0.1453 - 56ms/epoch - 4ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 0.1600 - 57ms/epoch - 4ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 0.1050 - 60ms/epoch - 4ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 0.0217 - 58ms/epoch - 4ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 0.0091 - 57ms/epoch - 4ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 0.0064 - 55ms/epoch - 4ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 0.0048 - 57ms/epoch - 4ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 0.0035 - 55ms/epoch - 4ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 0.0042 - 57ms/epoch - 4ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 0.0018 - 60ms/epoch - 4ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 0.0033 - 60ms/epoch - 4ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 5.8991e-04 - 58ms/epoch - 4ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 0.0012 - 59ms/epoch - 4ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 0.0043 - 60ms/epoch - 4ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 0.0121 - 58ms/epoch - 4ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 7.1038e-04 - 58ms/epoch - 4ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 0.0083 - 60ms/epoch - 4ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 0.0050 - 59ms/epoch - 4ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7867141b8a30>"
]
},
"metadata": {},
"execution_count": 18
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "c709addc-097e-44c5-e79c-f57b8102805f",
"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": 19,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"7/7 [==============================] - 0s 3ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x78672c283d60>"
]
},
"metadata": {},
"execution_count": 19
},
{
"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": "3e4f6453-9a90-440a-e8a3-9801d0bc4712"
},
"execution_count": 20,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712716587.853165\n",
"Wed Apr 10 02:36:27 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": "26bd301c-2bfd-490e-efd0-2a83542d8bbb"
},
"execution_count": 21,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712716587.859266\n",
"Wed Apr 10 02:36:27 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": 1849
},
"id": "95xed6YyDClf",
"outputId": "034ae914-3b51-4fc0-944b-94f96c08e50f"
},
"execution_count": 22,
"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",
"50 1.000000\n",
"1 0.954330\n",
"191 0.945628\n",
"134 0.907147\n",
"154 0.885093\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 0.015005\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.000211\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.0\n",
"Normalized Saliency Sum: Saliency 7.202397\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.110564\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 7.867597\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 61.21925\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.012224\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 736.846069\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000307\n",
"1 0.954637\n",
"2 0.955035\n",
"3 0.955484\n",
"4 0.955484\n",
".. ...\n",
"475 7.201847\n",
"476 7.201897\n",
"477 7.201949\n",
"478 7.202342\n",
"479 7.202398\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 6.405893e-07\n",
"1 1.988828e-03\n",
"2 1.989657e-03\n",
"3 1.990592e-03\n",
"4 1.990592e-03\n",
".. ...\n",
"475 1.500385e-02\n",
"476 1.500395e-02\n",
"477 1.500406e-02\n",
"478 1.500488e-02\n",
"479 1.500500e-02\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.11146307\n",
"Normalized Saliency 25th Percentile: Saliency 0.000065\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.000425\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.000361\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": "3017e5f4-191b-4c9d-d9f4-32d5b5aa8134"
},
"execution_count": 23,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712716589.2574239\n",
"Wed Apr 10 02:36:29 2024\n"
]
}
]
}
]
}