Datasets
Models
Downloads: 1
1259 lines (1259 with data), 216.4 kB
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"machine_shape": "hm",
"gpuType": "V28"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "TPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "8XnVMPBXmtRa"
},
"source": [
"# TensorNetworks in Neural Networks.\n",
"\n",
"Here, we have a small toy example of how to use a TN inside of a fully connected neural network.\n",
"\n",
"First off, let's install tensornetwork"
]
},
{
"cell_type": "code",
"metadata": {
"id": "7HGRsYNAFxME"
},
"source": [
"# !pip install tensornetwork\n",
"\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import tensorflow as tf\n",
"# Import tensornetwork\n",
"import tensornetwork as tn\n",
"import random\n",
"import time\n",
"import pandas as pd\n",
"# Set the backend to tesorflow\n",
"# (default is numpy)\n",
"tn.set_default_backend(\"tensorflow\")\n",
"np.random.seed(42)\n",
"random.seed(42)\n",
"tf.random.set_seed(42)\n",
"# Explainability code assistance aided by ChatGPT3.5\n",
"# 2021 Kelly, D. TensorFlow Explainable AI tutorial https://www.youtube.com/watch?v=6xePkn3-LME"
],
"execution_count": 57,
"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": 58,
"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": "35f6f89d-80e3-4403-86e0-89c549c14c65",
"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",
" Dense(1024, activation=tf.nn.relu),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 59,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_5\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_18 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_5 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_19 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_20 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_21 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 2108417 (8.04 MB)\n",
"Trainable params: 2108417 (8.04 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": 60,
"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": "31c8435b-b88b-4acf-fe52-cb7766662038"
},
"execution_count": 61,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712558711.404281\n",
"Mon Apr 8 06:45:11 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "3ae5a623-d1e2-4c72-f33d-bfdf74d213cd",
"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": 62,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 0.4341 - 1s/epoch - 78ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.0598 - 141ms/epoch - 9ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.0428 - 150ms/epoch - 10ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0267 - 143ms/epoch - 10ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0157 - 142ms/epoch - 9ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0121 - 150ms/epoch - 10ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0081 - 141ms/epoch - 9ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0067 - 131ms/epoch - 9ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0049 - 130ms/epoch - 9ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0041 - 135ms/epoch - 9ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0051 - 131ms/epoch - 9ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0039 - 138ms/epoch - 9ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0013 - 129ms/epoch - 9ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0031 - 128ms/epoch - 9ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0025 - 136ms/epoch - 9ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0047 - 137ms/epoch - 9ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0069 - 137ms/epoch - 9ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0053 - 136ms/epoch - 9ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 8.5502e-04 - 139ms/epoch - 9ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 5.2157e-04 - 135ms/epoch - 9ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 2.9916e-04 - 138ms/epoch - 9ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 1.8443e-04 - 135ms/epoch - 9ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 9.7762e-05 - 147ms/epoch - 10ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 7.0402e-05 - 135ms/epoch - 9ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 6.5882e-05 - 137ms/epoch - 9ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 5.1643e-05 - 134ms/epoch - 9ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 3.9335e-05 - 136ms/epoch - 9ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 4.0445e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 3.4312e-05 - 134ms/epoch - 9ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 3.0137e-05 - 134ms/epoch - 9ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 2.8201e-05 - 138ms/epoch - 9ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 2.5835e-05 - 136ms/epoch - 9ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 2.4152e-05 - 136ms/epoch - 9ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 2.3587e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 1.8760e-05 - 141ms/epoch - 9ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 1.6179e-05 - 139ms/epoch - 9ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 1.3036e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 1.3834e-05 - 131ms/epoch - 9ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 1.3475e-05 - 137ms/epoch - 9ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 1.2415e-05 - 144ms/epoch - 10ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 1.0092e-05 - 138ms/epoch - 9ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 9.8728e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 9.0427e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 8.2934e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 1.0262e-05 - 134ms/epoch - 9ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 8.3729e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 6.2051e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 6.3666e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 8.2038e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 7.8090e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 5.9705e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 8.3067e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 6.7796e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 5.1793e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 5.4928e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 8.0526e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 5.1311e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 4.1412e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 7.9785e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 1.2412e-05 - 145ms/epoch - 10ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 7.0907e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 7.7464e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 5.7921e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 6.5594e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 9.1554e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 7.2529e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 6.7783e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 4.8893e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 6.8252e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 4.0902e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 3.1475e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 2.0853e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 2.2735e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 2.1801e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 2.1774e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 2.5222e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 2.2297e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 2.3128e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 3.9452e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 2.9914e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 2.8753e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 2.2766e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 1.9921e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 1.7853e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 2.1123e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 2.2440e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 4.0718e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 3.2271e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 1.7786e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 2.6123e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 1.8853e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 2.4102e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 2.3949e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 1.8879e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 1.3334e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 1.4847e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 1.4857e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 1.1412e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 3.6033e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 2.1893e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 1.8966e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 1.3893e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 3.0836e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 4.0907e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 2.2046e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 2.4159e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 1.8094e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 2.8122e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 1.8898e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 2.0315e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 2.0542e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 8.8017e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 9.4922e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 4.4264e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 3.0254e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 2.3152e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 4.1276e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 8.4078e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 8.5308e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 1.2286e-05 - 137ms/epoch - 9ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 4.2902e-05 - 131ms/epoch - 9ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 4.1574e-05 - 136ms/epoch - 9ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 3.4744e-04 - 130ms/epoch - 9ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 5.3331e-04 - 130ms/epoch - 9ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 5.3239e-04 - 131ms/epoch - 9ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 0.0091 - 131ms/epoch - 9ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 0.0252 - 134ms/epoch - 9ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 0.0863 - 132ms/epoch - 9ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 0.0160 - 131ms/epoch - 9ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 0.0101 - 131ms/epoch - 9ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 7.7037e-04 - 128ms/epoch - 9ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 9.7539e-04 - 132ms/epoch - 9ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 4.8052e-04 - 137ms/epoch - 9ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 1.8083e-04 - 135ms/epoch - 9ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 2.6229e-04 - 144ms/epoch - 10ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 9.1570e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 6.0071e-05 - 135ms/epoch - 9ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 2.9091e-05 - 133ms/epoch - 9ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 1.9986e-05 - 140ms/epoch - 9ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 1.4138e-05 - 133ms/epoch - 9ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 1.2680e-05 - 133ms/epoch - 9ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 1.0418e-05 - 133ms/epoch - 9ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 1.0360e-05 - 135ms/epoch - 9ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 1.1517e-05 - 145ms/epoch - 10ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 9.9932e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 8.4297e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 5.8404e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 5.0634e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 4.7437e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 4.5320e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 4.1316e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 3.6297e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 4.0133e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 3.1283e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 2.8436e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 3.4901e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 2.6955e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 2.4281e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 2.0497e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 1.9315e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 2.0575e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 2.6585e-06 - 146ms/epoch - 10ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 2.1489e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 1.8991e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 1.8234e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 1.3860e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 1.6176e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 1.6411e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 1.3879e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 1.4521e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 1.4938e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 1.2382e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 9.8727e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 9.8756e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 9.8459e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 9.6337e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 8.7772e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 8.6861e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 1.1481e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 9.3055e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 8.4499e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 1.1437e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 8.3833e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 7.6243e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 7.7472e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 8.1483e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 9.7039e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 8.9950e-07 - 133ms/epoch - 9ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 8.4074e-07 - 131ms/epoch - 9ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 8.1877e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 6.0425e-07 - 144ms/epoch - 10ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 6.1765e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 5.7162e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 7.3355e-07 - 131ms/epoch - 9ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 2.0292e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 1.3227e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 7.7752e-07 - 144ms/epoch - 10ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 5.7043e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 4.8449e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 4.7818e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 6.8165e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 5.5007e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 4.1812e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 4.9039e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 6.1332e-07 - 148ms/epoch - 10ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 4.6857e-07 - 143ms/epoch - 10ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 4.8843e-07 - 145ms/epoch - 10ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 5.7358e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 3.7813e-07 - 146ms/epoch - 10ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 5.4602e-07 - 147ms/epoch - 10ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 8.1889e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 6.9640e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 3.9721e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 4.2450e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 4.5236e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 5.3633e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 3.8577e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 4.0302e-07 - 130ms/epoch - 9ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 3.9632e-07 - 129ms/epoch - 9ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 4.4516e-07 - 131ms/epoch - 9ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 4.0613e-07 - 131ms/epoch - 9ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 3.4690e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 3.0875e-07 - 129ms/epoch - 9ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 2.8192e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 3.3041e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 6.1134e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 4.8068e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 3.7244e-07 - 131ms/epoch - 9ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 4.8122e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 4.7904e-07 - 131ms/epoch - 9ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 4.1705e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 4.2488e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 4.0102e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 6.0897e-07 - 130ms/epoch - 9ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 5.6354e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 2.1686e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 2.9221e-07 - 147ms/epoch - 10ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 3.0145e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 3.2567e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 4.8886e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 2.6934e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 3.2738e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 4.5915e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 8.5761e-07 - 129ms/epoch - 9ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 8.4054e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 3.3502e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 3.3267e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 8.5243e-07 - 133ms/epoch - 9ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 1.9594e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 8.4892e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 9.6384e-07 - 130ms/epoch - 9ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 9.1313e-07 - 133ms/epoch - 9ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 5.5588e-07 - 129ms/epoch - 9ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 5.4270e-07 - 129ms/epoch - 9ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 3.9867e-07 - 129ms/epoch - 9ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 2.3643e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 3.1588e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 2.4307e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 3.5000e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 4.8966e-07 - 130ms/epoch - 9ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 7.7001e-07 - 130ms/epoch - 9ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 5.7966e-07 - 130ms/epoch - 9ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 9.4355e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 8.3595e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 5.7968e-07 - 131ms/epoch - 9ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 6.8738e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 4.7117e-07 - 133ms/epoch - 9ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 5.0220e-07 - 133ms/epoch - 9ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 1.2074e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 5.4583e-07 - 145ms/epoch - 10ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 3.8032e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 3.0779e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 2.4164e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 3.8289e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 5.0174e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 5.2428e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 5.3013e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 3.3106e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 2.2910e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 1.8988e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 1.6190e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 3.3357e-07 - 133ms/epoch - 9ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 6.0959e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 9.1293e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 1.0984e-05 - 133ms/epoch - 9ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 6.2221e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 1.2127e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 4.3524e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 4.1516e-07 - 133ms/epoch - 9ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 3.5502e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 2.2285e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 2.7823e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 7.8781e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 1.3520e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 6.0797e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 4.2369e-07 - 130ms/epoch - 9ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 3.4527e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 3.6727e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 7.6726e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 1.8599e-06 - 135ms/epoch - 9ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x791a7c5c6380>"
]
},
"metadata": {},
"execution_count": 62
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "6de8a38b-91e3-4d2e-cd8d-ec270fcfe548",
"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": 63,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 4ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x79197c61f130>"
]
},
"metadata": {},
"execution_count": 63
},
{
"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": "2db8b3ed-b6ff-4ca9-a3e2-bb6aa71c2dc2"
},
"execution_count": 64,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712558754.3307264\n",
"Mon Apr 8 06:45:54 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": "a2c18ca9-7e13-4e98-d790-ecfea33bafaf"
},
"execution_count": 65,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712558754.3363535\n",
"Mon Apr 8 06:45:54 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": "4057a054-9138-4c69-84cd-d6df7d2403f3"
},
"execution_count": 66,
"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",
"377 0.281677\n",
"37 0.270649\n",
"307 0.193061\n",
"327 0.186967\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 0.013439\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.006736\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.001580\n",
"1 0.002265\n",
"2 0.006773\n",
"3 0.011193\n",
"Normalized Saliency Sum: Saliency 6.450954\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.050819\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 16.120249\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 300.933319\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.002583\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 378.128571\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.004055\n",
"1 0.006625\n",
"2 0.012097\n",
"3 0.015161\n",
"4 0.016797\n",
".. ...\n",
"475 6.419893\n",
"476 6.433701\n",
"477 6.445518\n",
"478 6.450191\n",
"479 6.450956\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000008\n",
"1 0.000014\n",
"2 0.000025\n",
"3 0.000032\n",
"4 0.000035\n",
".. ...\n",
"475 0.013375\n",
"476 0.013404\n",
"477 0.013428\n",
"478 0.013438\n",
"479 0.013439\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.052514423\n",
"Normalized Saliency 25th Percentile: Saliency 0.003909\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.011281\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.007371\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": "e9fc34a6-c59d-4ebd-de6a-892042f6e75a"
},
"execution_count": 67,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712558755.7706945\n",
"Mon Apr 8 06:45:55 2024\n"
]
}
]
}
]
}