Datasets
Models
Downloads: 1
1282 lines (1282 with data), 212.9 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": 24,
"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": 25,
"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": "0eb41024-47ee-4fda-c064-032fc90be6bf",
"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",
" Dense(1024, activation=tf.nn.relu),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 26,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_2\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_6 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_2 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_7 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_8 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 1058817 (4.04 MB)\n",
"Trainable params: 1058817 (4.04 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": [
"# 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": 27,
"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": "4f8982df-926a-4f1f-977b-7931c6ad3b38"
},
"execution_count": 28,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712721758.8235977\n",
"Wed Apr 10 04:02:38 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "846e2d52-d48b-482f-c341-cd601301851b",
"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": 29,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 0.8774 - 972ms/epoch - 65ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.3833 - 110ms/epoch - 7ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.2184 - 102ms/epoch - 7ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.2060 - 105ms/epoch - 7ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.1789 - 109ms/epoch - 7ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.1656 - 102ms/epoch - 7ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.1742 - 106ms/epoch - 7ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.1447 - 95ms/epoch - 6ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.1307 - 107ms/epoch - 7ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0991 - 94ms/epoch - 6ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0926 - 98ms/epoch - 7ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0717 - 96ms/epoch - 6ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0477 - 97ms/epoch - 6ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0502 - 106ms/epoch - 7ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0489 - 98ms/epoch - 7ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0361 - 95ms/epoch - 6ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0349 - 104ms/epoch - 7ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0215 - 104ms/epoch - 7ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0216 - 105ms/epoch - 7ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0291 - 100ms/epoch - 7ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 0.0372 - 95ms/epoch - 6ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 0.0258 - 98ms/epoch - 7ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 0.0227 - 94ms/epoch - 6ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 0.0222 - 99ms/epoch - 7ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 0.0309 - 96ms/epoch - 6ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 0.0473 - 96ms/epoch - 6ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 0.0315 - 94ms/epoch - 6ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 0.0134 - 94ms/epoch - 6ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 0.0170 - 93ms/epoch - 6ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 0.0128 - 96ms/epoch - 6ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 0.0132 - 94ms/epoch - 6ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 0.0154 - 97ms/epoch - 6ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 0.0315 - 96ms/epoch - 6ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 0.0250 - 99ms/epoch - 7ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 0.0319 - 97ms/epoch - 6ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 0.0213 - 102ms/epoch - 7ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 0.0238 - 92ms/epoch - 6ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 0.0081 - 101ms/epoch - 7ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 0.0033 - 94ms/epoch - 6ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 0.0107 - 98ms/epoch - 7ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 0.0195 - 94ms/epoch - 6ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 0.0390 - 95ms/epoch - 6ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 0.0211 - 101ms/epoch - 7ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 0.0148 - 100ms/epoch - 7ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 0.0450 - 97ms/epoch - 6ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 0.0386 - 98ms/epoch - 7ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 0.0302 - 97ms/epoch - 6ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 0.0114 - 94ms/epoch - 6ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 0.0096 - 99ms/epoch - 7ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 0.0115 - 96ms/epoch - 6ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 0.0116 - 95ms/epoch - 6ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 0.0089 - 93ms/epoch - 6ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 0.0090 - 92ms/epoch - 6ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 0.0086 - 89ms/epoch - 6ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 0.0068 - 95ms/epoch - 6ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 0.0074 - 103ms/epoch - 7ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 0.0145 - 93ms/epoch - 6ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 0.0239 - 93ms/epoch - 6ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 0.0222 - 101ms/epoch - 7ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 0.0103 - 93ms/epoch - 6ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 0.0196 - 93ms/epoch - 6ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 0.0200 - 97ms/epoch - 6ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 0.0385 - 94ms/epoch - 6ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 0.0136 - 96ms/epoch - 6ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 0.0105 - 103ms/epoch - 7ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 0.0039 - 97ms/epoch - 6ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 0.0017 - 101ms/epoch - 7ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 0.0149 - 97ms/epoch - 6ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 0.0409 - 92ms/epoch - 6ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 0.0387 - 98ms/epoch - 7ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 0.0151 - 101ms/epoch - 7ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 0.0054 - 94ms/epoch - 6ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 0.0061 - 105ms/epoch - 7ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 0.0182 - 90ms/epoch - 6ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 0.0485 - 95ms/epoch - 6ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 0.1520 - 96ms/epoch - 6ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 0.0595 - 103ms/epoch - 7ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 0.0147 - 98ms/epoch - 7ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 0.0091 - 95ms/epoch - 6ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 0.0082 - 93ms/epoch - 6ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 0.0103 - 97ms/epoch - 6ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 0.0077 - 88ms/epoch - 6ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 0.0112 - 98ms/epoch - 7ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 0.0058 - 98ms/epoch - 7ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 0.0076 - 92ms/epoch - 6ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 0.0071 - 97ms/epoch - 6ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 0.0044 - 97ms/epoch - 6ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 0.0074 - 110ms/epoch - 7ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 0.0157 - 106ms/epoch - 7ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 0.0590 - 105ms/epoch - 7ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 0.0183 - 93ms/epoch - 6ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 0.0199 - 98ms/epoch - 7ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 0.0157 - 99ms/epoch - 7ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 0.0029 - 100ms/epoch - 7ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 0.0021 - 102ms/epoch - 7ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 0.0070 - 102ms/epoch - 7ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 0.0037 - 106ms/epoch - 7ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 0.0023 - 97ms/epoch - 6ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 0.0015 - 99ms/epoch - 7ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 0.0019 - 105ms/epoch - 7ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 0.0026 - 100ms/epoch - 7ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 0.0021 - 105ms/epoch - 7ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 0.0124 - 90ms/epoch - 6ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 0.0190 - 94ms/epoch - 6ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 0.0076 - 96ms/epoch - 6ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 0.0115 - 98ms/epoch - 7ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 0.0197 - 92ms/epoch - 6ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 0.0823 - 93ms/epoch - 6ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 0.0526 - 96ms/epoch - 6ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 0.0548 - 97ms/epoch - 6ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 0.1114 - 97ms/epoch - 6ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 0.0994 - 99ms/epoch - 7ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 0.0240 - 97ms/epoch - 6ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 0.0179 - 96ms/epoch - 6ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 0.0096 - 99ms/epoch - 7ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 0.0092 - 98ms/epoch - 7ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 0.0055 - 91ms/epoch - 6ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 0.0050 - 91ms/epoch - 6ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 0.0052 - 93ms/epoch - 6ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 0.0068 - 98ms/epoch - 7ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 0.0038 - 94ms/epoch - 6ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 0.0188 - 91ms/epoch - 6ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 0.0264 - 92ms/epoch - 6ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 0.0168 - 98ms/epoch - 7ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 0.0032 - 90ms/epoch - 6ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 0.0019 - 91ms/epoch - 6ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 0.0027 - 92ms/epoch - 6ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 0.0011 - 90ms/epoch - 6ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 0.0011 - 95ms/epoch - 6ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 0.0033 - 94ms/epoch - 6ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 0.0042 - 95ms/epoch - 6ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 0.0050 - 96ms/epoch - 6ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 0.0070 - 97ms/epoch - 6ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 0.0028 - 92ms/epoch - 6ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 0.0079 - 93ms/epoch - 6ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 0.0041 - 89ms/epoch - 6ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 0.0067 - 91ms/epoch - 6ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 0.0157 - 91ms/epoch - 6ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 0.0455 - 100ms/epoch - 7ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 0.0148 - 96ms/epoch - 6ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 0.0086 - 93ms/epoch - 6ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 0.0015 - 91ms/epoch - 6ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 0.0019 - 94ms/epoch - 6ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 0.0047 - 92ms/epoch - 6ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 0.0043 - 87ms/epoch - 6ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 0.0057 - 91ms/epoch - 6ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 0.0038 - 91ms/epoch - 6ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 0.0031 - 91ms/epoch - 6ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 0.0106 - 94ms/epoch - 6ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 0.0024 - 96ms/epoch - 6ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 0.0034 - 93ms/epoch - 6ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 0.0018 - 91ms/epoch - 6ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 0.0021 - 91ms/epoch - 6ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 0.0042 - 95ms/epoch - 6ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 0.0117 - 94ms/epoch - 6ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 0.0228 - 96ms/epoch - 6ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 0.0317 - 96ms/epoch - 6ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 0.0143 - 93ms/epoch - 6ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 0.0082 - 90ms/epoch - 6ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 0.0109 - 98ms/epoch - 7ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 0.0302 - 94ms/epoch - 6ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 0.0274 - 90ms/epoch - 6ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 0.0138 - 94ms/epoch - 6ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 0.0059 - 97ms/epoch - 6ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 0.0065 - 96ms/epoch - 6ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 0.0083 - 92ms/epoch - 6ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 0.0036 - 92ms/epoch - 6ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 0.0080 - 101ms/epoch - 7ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 0.0161 - 94ms/epoch - 6ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 0.0044 - 94ms/epoch - 6ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 0.0093 - 98ms/epoch - 7ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 0.0732 - 89ms/epoch - 6ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 0.0514 - 102ms/epoch - 7ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 0.0145 - 95ms/epoch - 6ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 0.0123 - 97ms/epoch - 6ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 0.0023 - 90ms/epoch - 6ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 0.0017 - 104ms/epoch - 7ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 4.9983e-04 - 93ms/epoch - 6ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 9.9217e-04 - 89ms/epoch - 6ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 0.0016 - 98ms/epoch - 7ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 0.0010 - 90ms/epoch - 6ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 1.7434e-04 - 92ms/epoch - 6ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 3.4239e-05 - 90ms/epoch - 6ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 3.8306e-05 - 94ms/epoch - 6ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 2.7351e-05 - 99ms/epoch - 7ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 2.0522e-05 - 96ms/epoch - 6ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 2.3894e-05 - 92ms/epoch - 6ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 2.2861e-05 - 92ms/epoch - 6ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 1.6642e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 1.4370e-05 - 90ms/epoch - 6ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 1.2435e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 1.1948e-05 - 90ms/epoch - 6ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 1.3802e-05 - 91ms/epoch - 6ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 1.6557e-05 - 95ms/epoch - 6ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 1.4158e-05 - 106ms/epoch - 7ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 1.0168e-05 - 108ms/epoch - 7ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 8.9395e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 8.2306e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 7.3362e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 8.0760e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 6.3712e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 7.1727e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 6.3498e-06 - 104ms/epoch - 7ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 5.5644e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 8.5286e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 5.4775e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 4.9405e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 4.5293e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 6.8065e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 7.4408e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 4.5623e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 5.4564e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 4.8691e-06 - 89ms/epoch - 6ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 4.8483e-06 - 87ms/epoch - 6ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 4.2429e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 6.1750e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 5.9399e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 3.3361e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 3.2168e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 4.1033e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 3.7542e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 3.0054e-06 - 90ms/epoch - 6ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 3.1027e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 3.2402e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 4.5417e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 4.2137e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 5.4875e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 6.8992e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 5.8787e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 2.8729e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 3.1542e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 3.2672e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 6.4589e-06 - 90ms/epoch - 6ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 9.0889e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 1.2474e-05 - 91ms/epoch - 6ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 5.6601e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 6.9260e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 9.2978e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 5.1490e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 6.0482e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 5.9111e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 3.1073e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 2.5574e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 4.3076e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 3.5631e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 2.1238e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 1.9795e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 2.2912e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 2.3550e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 5.4717e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 1.8826e-05 - 93ms/epoch - 6ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 4.6128e-05 - 97ms/epoch - 6ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 4.8377e-05 - 96ms/epoch - 6ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 8.8111e-05 - 95ms/epoch - 6ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 2.9968e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 4.5866e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 3.1578e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 4.9342e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 4.3420e-06 - 114ms/epoch - 8ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 7.8838e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 4.4944e-05 - 97ms/epoch - 6ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 1.3759e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 4.2708e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 1.8975e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 2.6575e-05 - 92ms/epoch - 6ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 5.7443e-05 - 97ms/epoch - 6ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 1.4584e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 1.0276e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 3.9842e-05 - 91ms/epoch - 6ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 4.1634e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 2.4939e-05 - 96ms/epoch - 6ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 5.2533e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 4.1620e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 1.9912e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 1.7925e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 2.1435e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 3.4568e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 7.4832e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 6.8348e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 2.3315e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 2.2069e-06 - 90ms/epoch - 6ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 1.5072e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 1.9541e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 2.8685e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 6.9633e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 1.9565e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 1.9912e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 6.7160e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 4.6234e-04 - 93ms/epoch - 6ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 4.9817e-04 - 97ms/epoch - 6ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 5.2083e-04 - 105ms/epoch - 7ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 0.0022 - 98ms/epoch - 7ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 0.0023 - 97ms/epoch - 6ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 0.0011 - 94ms/epoch - 6ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 0.0085 - 95ms/epoch - 6ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 0.0528 - 97ms/epoch - 6ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 0.1431 - 94ms/epoch - 6ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 0.0723 - 89ms/epoch - 6ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 0.0469 - 88ms/epoch - 6ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 0.0158 - 97ms/epoch - 6ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7fab0473a080>"
]
},
"metadata": {},
"execution_count": 29
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "50ef6c12-938f-4e03-dbc8-a0dca5449d20",
"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": 30,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"7/7 [==============================] - 0s 4ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7fab8c065990>"
]
},
"metadata": {},
"execution_count": 30
},
{
"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": "4e740f87-56b4-445b-aa45-7d80d886236f"
},
"execution_count": 31,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712721790.0157607\n",
"Wed Apr 10 04:03:10 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": "1165f18c-8dea-4706-83f3-d65b250754be"
},
"execution_count": 32,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712721790.0220468\n",
"Wed Apr 10 04:03:10 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": 1979
},
"id": "95xed6YyDClf",
"outputId": "9a858221-4d7f-47db-d9df-aa636e57efed"
},
"execution_count": 33,
"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",
"192 1.000000\n",
"370 0.943248\n",
"400 0.937998\n",
"288 0.891574\n",
"376 0.885339\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 0.03702\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.003621\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.000007\n",
"1 0.000135\n",
"2 0.000148\n",
"3 0.000191\n",
"Normalized Saliency Sum: Saliency 17.769506\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.133391\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 5.314736\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 29.507771\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.017793\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 360.323029\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.007039\n",
"1 0.086339\n",
"2 0.090659\n",
"3 0.093983\n",
"4 0.094396\n",
".. ...\n",
"475 17.736307\n",
"476 17.741402\n",
"477 17.747232\n",
"478 17.764242\n",
"479 17.769505\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000015\n",
"1 0.000180\n",
"2 0.000189\n",
"3 0.000196\n",
"4 0.000197\n",
".. ...\n",
"475 0.036951\n",
"476 0.036961\n",
"477 0.036973\n",
"478 0.037009\n",
"479 0.037020\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: Saliency 0.138299\n",
"dtype: float32\n",
"Normalized Saliency 25th Percentile: Saliency 0.001838\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.006174\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.004336\n",
"dtype: float64\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.10/dist-packages/numpy/core/fromnumeric.py:3502: FutureWarning: In a future version, DataFrame.mean(axis=None) will return a scalar mean over the entire DataFrame. To retain the old behavior, use 'frame.mean(axis=0)' or just 'frame.mean()'\n",
" return mean(axis=axis, dtype=dtype, out=out, **kwargs)\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": "a0bbe29f-165b-491b-adc8-7808b0c9e3fe"
},
"execution_count": 34,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712721791.300542\n",
"Wed Apr 10 04:03:11 2024\n"
]
}
]
}
]
}