Datasets
Models
Downloads: 1
1259 lines (1259 with data), 217.8 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": 112,
"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": 113,
"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": "d7edfe25-94de-4b43-dfc2-96dac24435d7",
"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",
" Dense(1024, activation=tf.nn.relu),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 114,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_10\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_39 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_13 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_14 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_40 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_41 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 1063937 (4.06 MB)\n",
"Trainable params: 1063937 (4.06 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": 115,
"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": "d3f76318-be78-4aac-ad98-bbdb26193057"
},
"execution_count": 116,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712560809.941222\n",
"Mon Apr 8 07:20:09 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "74559e76-1cdf-40e1-b2a3-1ebcc212fc54",
"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": 117,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 0.9981 - 1s/epoch - 88ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.7854 - 107ms/epoch - 7ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.1196 - 107ms/epoch - 7ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0292 - 103ms/epoch - 7ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0162 - 104ms/epoch - 7ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0074 - 107ms/epoch - 7ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0051 - 103ms/epoch - 7ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0031 - 110ms/epoch - 7ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0017 - 99ms/epoch - 7ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0013 - 98ms/epoch - 7ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0014 - 104ms/epoch - 7ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 2.2823e-04 - 108ms/epoch - 7ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 2.3679e-04 - 100ms/epoch - 7ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 3.8628e-04 - 107ms/epoch - 7ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 1.6042e-04 - 104ms/epoch - 7ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 5.9963e-05 - 107ms/epoch - 7ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 5.4335e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 6.5360e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 1.8081e-04 - 98ms/epoch - 7ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 2.0400e-04 - 104ms/epoch - 7ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 8.5998e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 3.6778e-05 - 102ms/epoch - 7ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 2.0093e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 1.3731e-05 - 105ms/epoch - 7ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 9.5729e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 1.1979e-05 - 99ms/epoch - 7ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 9.4215e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 7.7923e-06 - 104ms/epoch - 7ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 1.1421e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 9.6677e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 1.0479e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 1.4989e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 7.4478e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 4.9470e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 4.5059e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 3.7401e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 3.1885e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 3.0532e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 4.0557e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 4.2204e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 2.5690e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 3.0815e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 5.6616e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 2.5205e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 5.2319e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 2.8394e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 2.4260e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 1.2355e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 7.1651e-05 - 97ms/epoch - 6ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 1.2613e-04 - 97ms/epoch - 6ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 7.6260e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 3.7263e-04 - 112ms/epoch - 7ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 0.0020 - 102ms/epoch - 7ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 7.7175e-04 - 103ms/epoch - 7ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 3.2531e-04 - 103ms/epoch - 7ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 3.7101e-04 - 100ms/epoch - 7ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 0.0017 - 102ms/epoch - 7ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 0.0085 - 100ms/epoch - 7ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 0.0106 - 102ms/epoch - 7ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 0.0039 - 100ms/epoch - 7ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 0.0045 - 103ms/epoch - 7ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 0.0140 - 102ms/epoch - 7ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 0.0013 - 99ms/epoch - 7ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 9.8757e-04 - 102ms/epoch - 7ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 5.5831e-04 - 97ms/epoch - 6ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 3.5195e-04 - 103ms/epoch - 7ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 1.2511e-04 - 100ms/epoch - 7ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 2.8252e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 1.2011e-05 - 97ms/epoch - 6ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 9.8243e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 6.9242e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 6.8723e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 4.1112e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 3.7893e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 3.3699e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 2.7713e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 2.2500e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 3.1224e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 2.2941e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 1.7601e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 1.7427e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 1.6315e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 1.0141e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 9.5794e-07 - 94ms/epoch - 6ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 1.3484e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 1.7110e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 1.8087e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 1.1777e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 1.0702e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 1.5812e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 1.4244e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 7.7592e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 7.2113e-07 - 98ms/epoch - 7ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 8.5605e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 8.9351e-07 - 97ms/epoch - 6ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 1.1353e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 3.2494e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 1.5176e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 1.2694e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 2.4282e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 7.5461e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 1.5934e-05 - 97ms/epoch - 6ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 1.1836e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 7.2663e-07 - 95ms/epoch - 6ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 8.2543e-07 - 95ms/epoch - 6ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 7.7369e-07 - 95ms/epoch - 6ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 6.6547e-07 - 94ms/epoch - 6ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 1.4692e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 2.9790e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 1.8158e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 6.9528e-07 - 97ms/epoch - 6ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 4.6837e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 3.1972e-07 - 104ms/epoch - 7ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 7.7286e-07 - 97ms/epoch - 6ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 7.6531e-07 - 98ms/epoch - 7ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 1.7186e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 1.5732e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 2.7147e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 9.9598e-07 - 96ms/epoch - 6ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 5.9074e-07 - 96ms/epoch - 6ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 1.8800e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 2.1332e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 2.3201e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 2.4507e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 1.8938e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 2.7662e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 8.4238e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 2.5110e-05 - 97ms/epoch - 6ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 3.7519e-05 - 99ms/epoch - 7ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 1.3042e-04 - 96ms/epoch - 6ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 5.8369e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 1.7481e-04 - 103ms/epoch - 7ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 1.8313e-04 - 95ms/epoch - 6ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 5.5013e-05 - 96ms/epoch - 6ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 6.7195e-05 - 95ms/epoch - 6ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 3.4437e-05 - 95ms/epoch - 6ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 5.8318e-05 - 96ms/epoch - 6ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 1.5735e-05 - 97ms/epoch - 6ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 4.5840e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 3.5859e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 1.4195e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 1.4068e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 9.2178e-07 - 96ms/epoch - 6ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 1.1398e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 9.0105e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 7.5884e-07 - 98ms/epoch - 7ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 3.6398e-07 - 95ms/epoch - 6ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 3.8336e-07 - 98ms/epoch - 7ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 5.3854e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 2.6164e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 2.4653e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 3.4472e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 2.1910e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 6.3588e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 1.1020e-06 - 104ms/epoch - 7ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 5.7415e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 1.0010e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 6.2760e-07 - 97ms/epoch - 6ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 1.5417e-05 - 102ms/epoch - 7ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 1.7089e-05 - 96ms/epoch - 6ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 7.4098e-05 - 95ms/epoch - 6ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 6.2882e-04 - 102ms/epoch - 7ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 4.6326e-04 - 98ms/epoch - 7ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 2.0480e-04 - 101ms/epoch - 7ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 1.1013e-04 - 102ms/epoch - 7ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 9.2947e-05 - 99ms/epoch - 7ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 3.9371e-05 - 102ms/epoch - 7ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 4.5072e-05 - 104ms/epoch - 7ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 3.0252e-05 - 105ms/epoch - 7ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 1.0305e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 3.8551e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 2.0138e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 1.6685e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 4.7997e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 2.3851e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 1.5987e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 1.5632e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 1.9695e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 3.5622e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 1.7654e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 1.6317e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 9.8805e-07 - 103ms/epoch - 7ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 4.1594e-07 - 102ms/epoch - 7ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 3.1558e-07 - 105ms/epoch - 7ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 3.3401e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 6.8817e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 1.4762e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 9.2096e-07 - 103ms/epoch - 7ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 9.5016e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 2.0233e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 3.8331e-06 - 104ms/epoch - 7ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 5.0163e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 7.0824e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 1.4473e-05 - 104ms/epoch - 7ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 1.0229e-04 - 99ms/epoch - 7ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 2.6550e-04 - 100ms/epoch - 7ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 3.1494e-04 - 97ms/epoch - 6ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 2.6461e-04 - 98ms/epoch - 7ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 8.6388e-05 - 99ms/epoch - 7ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 7.9412e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 9.6867e-05 - 107ms/epoch - 7ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 1.2086e-04 - 102ms/epoch - 7ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 2.4405e-04 - 100ms/epoch - 7ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 1.3263e-04 - 99ms/epoch - 7ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 3.3218e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 5.4697e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 3.1831e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 1.9251e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 2.4523e-06 - 105ms/epoch - 7ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 3.9643e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 2.0958e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 5.7416e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 5.0327e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 2.5141e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 6.0604e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 3.9988e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 9.1960e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 5.9393e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 7.0597e-07 - 106ms/epoch - 7ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 8.1595e-07 - 103ms/epoch - 7ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 3.6341e-07 - 101ms/epoch - 7ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 2.5181e-07 - 97ms/epoch - 6ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 6.1567e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 1.4416e-06 - 104ms/epoch - 7ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.8310e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 2.4920e-05 - 102ms/epoch - 7ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 1.2229e-05 - 99ms/epoch - 7ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 2.4100e-05 - 97ms/epoch - 6ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 7.2942e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 9.0230e-07 - 98ms/epoch - 7ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 9.9615e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 1.1675e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 6.9643e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 3.6403e-07 - 104ms/epoch - 7ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 3.8681e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 3.2370e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 1.6524e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 2.2298e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 2.5067e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 2.2940e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 1.6942e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 2.1824e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 3.7157e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 2.1722e-04 - 97ms/epoch - 6ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 1.8931e-04 - 99ms/epoch - 7ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 1.3626e-04 - 102ms/epoch - 7ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 2.8126e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 7.1195e-06 - 106ms/epoch - 7ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 3.7282e-06 - 107ms/epoch - 7ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 2.4851e-05 - 109ms/epoch - 7ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 3.3398e-04 - 99ms/epoch - 7ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 5.3721e-04 - 102ms/epoch - 7ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 4.2037e-04 - 101ms/epoch - 7ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 1.6163e-04 - 98ms/epoch - 7ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 1.0242e-04 - 104ms/epoch - 7ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 4.7626e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 3.3566e-05 - 101ms/epoch - 7ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 5.4615e-05 - 103ms/epoch - 7ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 6.2280e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 1.7208e-04 - 103ms/epoch - 7ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 2.5269e-04 - 98ms/epoch - 7ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 2.1752e-04 - 99ms/epoch - 7ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 3.7994e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 5.8298e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 2.4553e-06 - 101ms/epoch - 7ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 2.3885e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 1.4453e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 7.6637e-07 - 105ms/epoch - 7ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 5.3003e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 5.2320e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 1.8890e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 7.1218e-07 - 98ms/epoch - 7ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 5.7362e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 1.0652e-06 - 104ms/epoch - 7ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 3.2986e-06 - 102ms/epoch - 7ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 3.0766e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 9.0719e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 9.1382e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 1.0529e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 5.5165e-07 - 97ms/epoch - 6ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 5.2218e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 5.0169e-07 - 95ms/epoch - 6ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 8.2268e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 1.0555e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 2.7541e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 1.2494e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 8.8759e-07 - 97ms/epoch - 6ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 4.6838e-07 - 98ms/epoch - 7ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 6.8124e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 7.9864e-07 - 98ms/epoch - 7ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 4.3703e-07 - 101ms/epoch - 7ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 2.8158e-07 - 98ms/epoch - 7ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 3.0925e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 7.3796e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 2.2085e-05 - 100ms/epoch - 7ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 9.6886e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 4.3204e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 1.2498e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 1.6373e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 1.8970e-06 - 98ms/epoch - 7ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x79196c6934f0>"
]
},
"metadata": {},
"execution_count": 117
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "ad8ef3d2-b7e6-4e97-ea94-763dbcc3bfc8",
"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": 118,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 4ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7918dc35ee60>"
]
},
"metadata": {},
"execution_count": 118
},
{
"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": "6269c6a6-14b6-4652-dc1e-25fca8bccb65"
},
"execution_count": 119,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712560842.5084324\n",
"Mon Apr 8 07:20:42 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": "879c7cb2-b44a-4a11-ffdb-9c8a8a347ba0"
},
"execution_count": 120,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712560842.5138009\n",
"Mon Apr 8 07:20:42 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": 1914
},
"id": "95xed6YyDClf",
"outputId": "39254ccf-62f4-4104-e28f-48edf895758e"
},
"execution_count": 121,
"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",
"239 1.000000\n",
"37 0.886851\n",
"377 0.425064\n",
"327 0.340778\n",
"370 0.338488\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 0.010727\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.002039\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.000868\n",
"1 0.000872\n",
"2 0.000995\n",
"3 0.004720\n",
"Normalized Saliency Sum: Saliency 5.149031\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.069399\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 11.355125\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 143.321335\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.004816\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 646.95105\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.003822\n",
"1 0.005930\n",
"2 0.007961\n",
"3 0.010681\n",
"4 0.011976\n",
".. ...\n",
"475 5.141833\n",
"476 5.143551\n",
"477 5.146358\n",
"478 5.148335\n",
"479 5.149033\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000008\n",
"1 0.000012\n",
"2 0.000017\n",
"3 0.000022\n",
"4 0.000025\n",
".. ...\n",
"475 0.010712\n",
"476 0.010716\n",
"477 0.010722\n",
"478 0.010726\n",
"479 0.010727\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.07015209\n",
"Normalized Saliency 25th Percentile: Saliency 0.001149\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.003385\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.002235\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": "496d2fa6-8822-41fd-f8b3-709a309705fc"
},
"execution_count": 122,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712560844.1154397\n",
"Mon Apr 8 07:20:44 2024\n"
]
}
]
}
]
}