Datasets
Models
Downloads: 1
1264 lines (1264 with data), 218.1 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": "765dd5e1-5d71-4384-cbf5-6777cdc954f0",
"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",
" 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_3 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_4 (Dense) (None, 1024) 1049600 \n",
" \n",
" tn_layer_1 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_5 (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": [
"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": 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": "308d0778-ce34-43df-943a-da72e9a70991"
},
"execution_count": 17,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712556768.284152\n",
"Mon Apr 8 06:12:48 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "61712461-0798-4d29-b9b2-ab53b1fee9b4",
"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: 0.5768 - 972ms/epoch - 65ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.0897 - 113ms/epoch - 8ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.0525 - 111ms/epoch - 7ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0440 - 113ms/epoch - 8ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0367 - 119ms/epoch - 8ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0317 - 108ms/epoch - 7ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0270 - 117ms/epoch - 8ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0213 - 107ms/epoch - 7ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0170 - 104ms/epoch - 7ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0142 - 108ms/epoch - 7ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0126 - 104ms/epoch - 7ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0065 - 107ms/epoch - 7ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0049 - 98ms/epoch - 7ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0028 - 103ms/epoch - 7ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0025 - 109ms/epoch - 7ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0013 - 109ms/epoch - 7ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0015 - 109ms/epoch - 7ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 7.4001e-04 - 106ms/epoch - 7ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 7.1302e-04 - 107ms/epoch - 7ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0010 - 96ms/epoch - 6ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 3.1903e-04 - 101ms/epoch - 7ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 2.8681e-04 - 98ms/epoch - 7ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 2.1966e-04 - 101ms/epoch - 7ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 3.5209e-04 - 104ms/epoch - 7ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 4.8028e-04 - 103ms/epoch - 7ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 7.9215e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 1.8736e-04 - 102ms/epoch - 7ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 4.4789e-05 - 103ms/epoch - 7ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 1.0101e-04 - 100ms/epoch - 7ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 2.8759e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 2.2645e-05 - 104ms/epoch - 7ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 2.2230e-05 - 103ms/epoch - 7ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 1.9798e-05 - 108ms/epoch - 7ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 1.4623e-05 - 106ms/epoch - 7ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 1.1927e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 1.1513e-05 - 106ms/epoch - 7ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 9.9803e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 1.1864e-05 - 105ms/epoch - 7ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 1.4987e-05 - 111ms/epoch - 7ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 1.0233e-05 - 105ms/epoch - 7ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 9.9277e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 8.4149e-06 - 107ms/epoch - 7ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 7.7489e-06 - 108ms/epoch - 7ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 5.6767e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 7.1790e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 7.6164e-06 - 109ms/epoch - 7ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 5.1597e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 3.8625e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 5.0299e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 5.3005e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 4.9382e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 8.1102e-06 - 108ms/epoch - 7ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 7.5871e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 5.2119e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 3.8493e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 3.2312e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 5.0469e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 2.8043e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 2.3464e-06 - 110ms/epoch - 7ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 3.6425e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 1.1411e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 6.9267e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 3.4783e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 3.3943e-06 - 110ms/epoch - 7ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 2.2379e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 6.4605e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 6.8113e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 3.0268e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 2.8140e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 1.0629e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 1.0782e-05 - 103ms/epoch - 7ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 1.1545e-05 - 106ms/epoch - 7ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 6.9880e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 1.8312e-05 - 112ms/epoch - 7ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 8.8581e-05 - 111ms/epoch - 7ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 2.9592e-05 - 102ms/epoch - 7ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 7.1285e-06 - 108ms/epoch - 7ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 6.5636e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 1.6209e-05 - 106ms/epoch - 7ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 2.8291e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 1.9570e-05 - 99ms/epoch - 7ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 1.0194e-05 - 96ms/epoch - 6ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 4.5113e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 2.2731e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 9.8990e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 1.4177e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 1.0482e-05 - 108ms/epoch - 7ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 1.3974e-05 - 107ms/epoch - 7ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 2.2665e-05 - 108ms/epoch - 7ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 1.6112e-04 - 109ms/epoch - 7ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 8.1165e-04 - 121ms/epoch - 8ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 0.0012 - 107ms/epoch - 7ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 4.0551e-04 - 111ms/epoch - 7ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 2.5142e-04 - 99ms/epoch - 7ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 5.8555e-04 - 102ms/epoch - 7ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 0.0012 - 95ms/epoch - 6ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 9.5763e-04 - 106ms/epoch - 7ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 4.4011e-04 - 102ms/epoch - 7ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 1.9701e-04 - 100ms/epoch - 7ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 1.8176e-04 - 110ms/epoch - 7ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 1.0552e-04 - 106ms/epoch - 7ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 5.9895e-05 - 99ms/epoch - 7ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 3.3913e-05 - 102ms/epoch - 7ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 2.0421e-05 - 108ms/epoch - 7ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 2.1085e-05 - 114ms/epoch - 8ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 3.1767e-05 - 109ms/epoch - 7ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 4.1958e-05 - 111ms/epoch - 7ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 5.8087e-05 - 104ms/epoch - 7ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 2.4446e-05 - 105ms/epoch - 7ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 2.2006e-05 - 105ms/epoch - 7ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 1.8002e-05 - 105ms/epoch - 7ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 1.2918e-05 - 108ms/epoch - 7ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 3.4512e-06 - 107ms/epoch - 7ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 1.5960e-06 - 111ms/epoch - 7ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 1.1652e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 1.0431e-06 - 109ms/epoch - 7ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 1.6844e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 8.7245e-07 - 102ms/epoch - 7ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 9.7709e-07 - 112ms/epoch - 7ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 1.0434e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 7.8144e-07 - 110ms/epoch - 7ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 8.2817e-07 - 102ms/epoch - 7ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 1.6779e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 1.3019e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 2.0063e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 9.6331e-07 - 104ms/epoch - 7ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 8.5592e-07 - 101ms/epoch - 7ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 1.3351e-06 - 108ms/epoch - 7ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 6.1410e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 7.5512e-07 - 109ms/epoch - 7ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 3.9772e-07 - 117ms/epoch - 8ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 1.4006e-06 - 113ms/epoch - 8ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 3.8386e-06 - 107ms/epoch - 7ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 1.4319e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 2.7567e-06 - 104ms/epoch - 7ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 2.8255e-06 - 109ms/epoch - 7ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 2.5333e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 1.2469e-06 - 112ms/epoch - 7ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 9.0346e-07 - 104ms/epoch - 7ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 3.7474e-06 - 107ms/epoch - 7ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 1.5324e-06 - 114ms/epoch - 8ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 1.2888e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 1.9745e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 4.9535e-06 - 109ms/epoch - 7ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 7.6945e-06 - 107ms/epoch - 7ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 8.1329e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 8.0353e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 6.0328e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 1.5835e-05 - 106ms/epoch - 7ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 1.1629e-05 - 106ms/epoch - 7ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 1.5759e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 1.9688e-05 - 102ms/epoch - 7ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 1.4013e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 5.9814e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 4.1950e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 1.7140e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 2.3561e-06 - 107ms/epoch - 7ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 7.3407e-06 - 107ms/epoch - 7ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 1.9797e-04 - 107ms/epoch - 7ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 6.5568e-05 - 103ms/epoch - 7ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 5.5049e-05 - 104ms/epoch - 7ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 1.3915e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 2.9339e-05 - 95ms/epoch - 6ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 2.8798e-05 - 107ms/epoch - 7ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 2.3978e-05 - 95ms/epoch - 6ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 5.3942e-05 - 102ms/epoch - 7ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 3.1403e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 2.8822e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 1.5534e-05 - 105ms/epoch - 7ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 5.8125e-05 - 103ms/epoch - 7ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 2.5567e-04 - 101ms/epoch - 7ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 4.0897e-04 - 101ms/epoch - 7ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 2.4730e-04 - 100ms/epoch - 7ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 7.3195e-04 - 103ms/epoch - 7ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 0.0256 - 98ms/epoch - 7ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 0.0291 - 99ms/epoch - 7ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 0.0178 - 96ms/epoch - 6ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 0.0261 - 102ms/epoch - 7ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 0.0287 - 97ms/epoch - 6ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 0.0126 - 104ms/epoch - 7ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 0.0040 - 97ms/epoch - 6ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 8.2234e-04 - 106ms/epoch - 7ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 3.1626e-04 - 98ms/epoch - 7ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 1.5093e-04 - 93ms/epoch - 6ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 9.3893e-05 - 97ms/epoch - 6ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 6.4938e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 3.5772e-05 - 102ms/epoch - 7ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 2.8266e-05 - 106ms/epoch - 7ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 2.5965e-05 - 104ms/epoch - 7ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 2.6680e-05 - 97ms/epoch - 6ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 1.8422e-05 - 113ms/epoch - 8ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 1.3594e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 1.4601e-05 - 105ms/epoch - 7ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 1.3708e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 2.2479e-05 - 106ms/epoch - 7ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 1.5139e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 8.0104e-06 - 112ms/epoch - 7ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 7.1709e-06 - 104ms/epoch - 7ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 6.5134e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 5.9587e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 5.8836e-06 - 110ms/epoch - 7ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 6.5369e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 7.1378e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 4.8332e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 4.4411e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 3.7970e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 4.3591e-06 - 104ms/epoch - 7ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 3.6152e-06 - 108ms/epoch - 7ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 3.1613e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 3.9176e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 1.8327e-05 - 106ms/epoch - 7ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 2.7426e-05 - 106ms/epoch - 7ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 2.9395e-05 - 102ms/epoch - 7ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 2.6642e-05 - 115ms/epoch - 8ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 1.8032e-04 - 102ms/epoch - 7ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 1.7577e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 1.4087e-05 - 97ms/epoch - 6ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 6.3348e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 3.1882e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 2.0047e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 1.4751e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 1.8029e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 1.5422e-06 - 112ms/epoch - 7ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 3.8928e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 4.1193e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 2.4353e-06 - 107ms/epoch - 7ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 1.5802e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 2.2638e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 2.5614e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 2.5436e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 2.6088e-06 - 111ms/epoch - 7ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 2.2213e-06 - 107ms/epoch - 7ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 1.1857e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 1.9719e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 1.7408e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 1.7928e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 1.7243e-06 - 112ms/epoch - 7ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 9.8866e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 3.1510e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 2.6151e-05 - 99ms/epoch - 7ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 5.4812e-06 - 104ms/epoch - 7ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 1.4819e-05 - 107ms/epoch - 7ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 2.0456e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 9.9418e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 1.3371e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 1.3574e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 9.4729e-07 - 103ms/epoch - 7ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 1.7172e-06 - 104ms/epoch - 7ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 1.9401e-06 - 110ms/epoch - 7ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 8.5146e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 5.3811e-07 - 104ms/epoch - 7ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 6.3800e-07 - 98ms/epoch - 7ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 7.6454e-07 - 107ms/epoch - 7ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 7.2870e-07 - 104ms/epoch - 7ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 6.4843e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 6.1283e-07 - 103ms/epoch - 7ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 7.5136e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 1.9626e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 1.6930e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 1.1847e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 5.9066e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 1.6098e-05 - 112ms/epoch - 7ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 3.3566e-05 - 96ms/epoch - 6ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 1.5895e-05 - 99ms/epoch - 7ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 2.0440e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 1.7289e-04 - 104ms/epoch - 7ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 4.8372e-04 - 104ms/epoch - 7ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 3.8005e-04 - 99ms/epoch - 7ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 0.0026 - 109ms/epoch - 7ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 0.0012 - 103ms/epoch - 7ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 4.2163e-04 - 108ms/epoch - 7ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 1.1165e-04 - 101ms/epoch - 7ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 3.2245e-05 - 110ms/epoch - 7ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 1.0869e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 6.0355e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 4.6157e-06 - 108ms/epoch - 7ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 3.9959e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 3.1427e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 2.6211e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 2.3347e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 1.9459e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 1.8445e-06 - 113ms/epoch - 8ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 1.5342e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 1.3123e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 1.3513e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 1.4644e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 1.3205e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 1.5053e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 1.0100e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 8.6158e-07 - 114ms/epoch - 8ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 9.1570e-07 - 102ms/epoch - 7ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 7.8504e-07 - 102ms/epoch - 7ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 1.0700e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 7.9393e-07 - 101ms/epoch - 7ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 6.8926e-07 - 112ms/epoch - 7ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 5.7306e-07 - 105ms/epoch - 7ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 5.5632e-07 - 107ms/epoch - 7ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 8.1889e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 5.2196e-07 - 102ms/epoch - 7ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 4.4966e-07 - 98ms/epoch - 7ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x791a7c4b84f0>"
]
},
"metadata": {},
"execution_count": 18
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "1d50f4b6-dea4-4ae8-b144-23a0cc730ab3",
"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": [
"16/16 [==============================] - 0s 3ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x791a7c5dac50>"
]
},
"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": "7984f462-57ed-4c8e-ca4a-350c8c25f3e8"
},
"execution_count": 20,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712556801.5322602\n",
"Mon Apr 8 06:13:21 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": "3fb92c32-5614-4f71-aa9f-37ac0cb13feb"
},
"execution_count": 21,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712556801.538495\n",
"Mon Apr 8 06:13:21 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": 2061
},
"id": "95xed6YyDClf",
"outputId": "fb3ec3a5-ff3b-45f7-ef65-ad590c581279"
},
"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",
"37 1.000000\n",
"239 0.361803\n",
"370 0.340036\n",
"287 0.283799\n",
"327 0.250626\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 0.009647\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.002104\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.000562\n",
"1 0.000925\n",
"2 0.001290\n",
"3 0.001616\n",
"4 0.001713\n",
"5 0.001818\n",
"6 0.002452\n",
"7 0.002461\n",
"8 0.002534\n",
"9 0.002826\n",
"10 0.003701\n",
"11 0.011207\n",
"Normalized Saliency Sum: Saliency 4.630467\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.055647\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 13.413833\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 217.689819\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.003097\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 576.843018\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.002532\n",
"1 0.005990\n",
"2 0.007995\n",
"3 0.011371\n",
"4 0.011971\n",
".. ...\n",
"475 4.620595\n",
"476 4.628232\n",
"477 4.629124\n",
"478 4.630177\n",
"479 4.630468\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000005\n",
"1 0.000012\n",
"2 0.000017\n",
"3 0.000024\n",
"4 0.000025\n",
".. ...\n",
"475 0.009626\n",
"476 0.009642\n",
"477 0.009644\n",
"478 0.009646\n",
"479 0.009647\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.056419775\n",
"Normalized Saliency 25th Percentile: Saliency 0.001322\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.003794\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.002471\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": "425f71f4-f153-4585-87ad-c139575fc189"
},
"execution_count": 23,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712556802.825828\n",
"Mon Apr 8 06:13:22 2024\n"
]
}
]
}
]
}