Datasets
Models
Downloads: 1
1276 lines (1276 with data), 211.5 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": "af6d17e7-e187-4cd6-f8be-5c34f51235f2",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
}
},
"source": [
"Dense = tf.keras.layers.Dense\n",
"tn_model = tf.keras.Sequential(\n",
" [\n",
" tf.keras.Input(shape=(2,)),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Start Modified Layers\n",
" TNLayer(),\n",
" TNLayer(),\n",
" TNLayer(),\n",
" Dense(1024, activation=tf.nn.relu),\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",
" tn_layer_3 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_4 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_5 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_4 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_5 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 1069057 (4.08 MB)\n",
"Trainable params: 1069057 (4.08 MB)\n",
"Non-trainable params: 0 (0.00 Byte)\n",
"_________________________________________________________________\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "GWwoYp0WnsLA"
},
"source": [
"# Training a model\n",
"\n",
"You can train the TN model just as you would a normal neural network model! Here, we give an example of how to do it in Keras."
]
},
{
"cell_type": "code",
"metadata": {
"id": "qDFzOC7sDBJ-"
},
"source": [
"# Generate points forming concentric circles\n",
"num_points = 240 # Number of points for each circle\n",
"\n",
"# Inner circle\n",
"r1 = np.random.rand(num_points)\n",
"theta1 = np.random.rand(num_points) * 2 * np.pi\n",
"x1 = r1 * np.cos(theta1)\n",
"y1 = r1 * np.sin(theta1)\n",
"\n",
"# Outer circle\n",
"r2 = np.random.rand(num_points) + 1\n",
"theta2 = np.random.rand(num_points) * 2 * np.pi\n",
"x2 = r2 * np.cos(theta2)\n",
"y2 = r2 * np.sin(theta2)\n",
"\n",
"# Concatenate the points and labels\n",
"X = np.concatenate([np.column_stack((x1, y1)), np.column_stack((x2, y2))])\n",
"Y = np.concatenate([np.ones(num_points), -np.ones(num_points)])\n",
"\n",
"# Shuffle the data\n",
"shuffle_index = np.random.permutation(len(X))\n",
"X_shuffled = X[shuffle_index]\n",
"Y_shuffled = Y[shuffle_index]"
],
"execution_count": 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": "f75b4454-4d61-47ba-8c21-aa4b499be6be"
},
"execution_count": 17,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712724626.4715729\n",
"Wed Apr 10 04:50:26 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "67f2dec8-0240-4544-f85a-e7d7dc25a849",
"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 - 2s - loss: 1.0027 - 2s/epoch - 112ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 1.0001 - 129ms/epoch - 9ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 1.0004 - 128ms/epoch - 9ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 1.0003 - 124ms/epoch - 8ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 1.0001 - 126ms/epoch - 8ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.9530 - 121ms/epoch - 8ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.3858 - 128ms/epoch - 9ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.1574 - 125ms/epoch - 8ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.1091 - 125ms/epoch - 8ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0699 - 118ms/epoch - 8ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0852 - 119ms/epoch - 8ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0939 - 116ms/epoch - 8ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0553 - 117ms/epoch - 8ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0358 - 122ms/epoch - 8ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0275 - 122ms/epoch - 8ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0127 - 118ms/epoch - 8ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0377 - 119ms/epoch - 8ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0391 - 118ms/epoch - 8ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0357 - 124ms/epoch - 8ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0356 - 119ms/epoch - 8ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 0.0699 - 124ms/epoch - 8ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 0.0206 - 119ms/epoch - 8ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 0.0163 - 113ms/epoch - 8ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 0.0068 - 115ms/epoch - 8ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 0.0290 - 116ms/epoch - 8ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 0.0062 - 121ms/epoch - 8ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 0.0042 - 128ms/epoch - 9ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 0.0034 - 122ms/epoch - 8ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 0.0066 - 129ms/epoch - 9ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 0.0137 - 117ms/epoch - 8ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 0.0099 - 118ms/epoch - 8ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 0.0993 - 126ms/epoch - 8ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 0.0463 - 116ms/epoch - 8ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 0.0173 - 122ms/epoch - 8ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 0.0241 - 121ms/epoch - 8ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 0.0629 - 122ms/epoch - 8ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 0.0397 - 114ms/epoch - 8ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 0.0272 - 126ms/epoch - 8ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 0.0104 - 116ms/epoch - 8ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 0.0115 - 129ms/epoch - 9ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 0.0112 - 120ms/epoch - 8ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 0.0555 - 130ms/epoch - 9ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 0.0474 - 116ms/epoch - 8ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 0.0413 - 115ms/epoch - 8ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 0.0273 - 124ms/epoch - 8ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 0.0202 - 119ms/epoch - 8ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 0.0043 - 111ms/epoch - 7ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 0.0045 - 122ms/epoch - 8ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 0.0019 - 118ms/epoch - 8ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 0.0058 - 122ms/epoch - 8ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 0.0066 - 117ms/epoch - 8ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 6.1816e-04 - 117ms/epoch - 8ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 0.0035 - 117ms/epoch - 8ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 0.0023 - 119ms/epoch - 8ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 0.0311 - 116ms/epoch - 8ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 0.0387 - 122ms/epoch - 8ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 0.0250 - 117ms/epoch - 8ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 0.0453 - 117ms/epoch - 8ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 0.0620 - 112ms/epoch - 7ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 0.0824 - 114ms/epoch - 8ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 0.0209 - 121ms/epoch - 8ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 0.0209 - 114ms/epoch - 8ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 0.0149 - 115ms/epoch - 8ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 0.0239 - 121ms/epoch - 8ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 0.0460 - 117ms/epoch - 8ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 0.0243 - 123ms/epoch - 8ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 0.0221 - 115ms/epoch - 8ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 0.0083 - 118ms/epoch - 8ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 0.0295 - 123ms/epoch - 8ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 0.0049 - 120ms/epoch - 8ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 0.0095 - 116ms/epoch - 8ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 0.0066 - 124ms/epoch - 8ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 0.0072 - 121ms/epoch - 8ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 0.0040 - 116ms/epoch - 8ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 0.0083 - 117ms/epoch - 8ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 9.6276e-04 - 113ms/epoch - 8ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 8.9418e-04 - 116ms/epoch - 8ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 0.0072 - 120ms/epoch - 8ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 3.8201e-04 - 117ms/epoch - 8ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 5.3769e-04 - 114ms/epoch - 8ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 2.2807e-04 - 117ms/epoch - 8ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 2.2880e-04 - 121ms/epoch - 8ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 8.2955e-05 - 116ms/epoch - 8ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 2.4025e-05 - 116ms/epoch - 8ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 1.2500e-05 - 117ms/epoch - 8ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 1.1217e-05 - 124ms/epoch - 8ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 1.1329e-05 - 120ms/epoch - 8ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 9.8495e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 1.0169e-05 - 117ms/epoch - 8ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 9.9174e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 6.8400e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 6.6389e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 6.6738e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 6.4793e-06 - 111ms/epoch - 7ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 5.6586e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 5.7183e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 6.5940e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 1.0932e-05 - 123ms/epoch - 8ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 5.9144e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 4.1880e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 4.1014e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 4.3865e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 3.4501e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 3.5151e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 3.1576e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 3.5964e-06 - 114ms/epoch - 8ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 3.0202e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 2.8424e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 2.4865e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 2.4826e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 3.8574e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 4.1583e-06 - 114ms/epoch - 8ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 2.9682e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 2.2479e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 1.8796e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 2.4010e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 2.4268e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 1.7848e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 1.6066e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 1.7791e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 1.6322e-06 - 114ms/epoch - 8ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 1.4654e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 3.0492e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 1.3743e-05 - 119ms/epoch - 8ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 5.6597e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 2.9600e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 1.7558e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 4.3797e-06 - 114ms/epoch - 8ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 3.7079e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 2.0594e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 1.6119e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 2.4080e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 2.5460e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 1.3182e-05 - 120ms/epoch - 8ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 3.1526e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 3.1170e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 1.4654e-05 - 120ms/epoch - 8ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 4.1765e-05 - 115ms/epoch - 8ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 2.8136e-04 - 116ms/epoch - 8ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 2.8170e-04 - 116ms/epoch - 8ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 2.1612e-05 - 116ms/epoch - 8ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 1.1955e-04 - 125ms/epoch - 8ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 8.3666e-05 - 125ms/epoch - 8ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 5.7564e-04 - 122ms/epoch - 8ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 3.7727e-04 - 125ms/epoch - 8ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 4.1007e-04 - 131ms/epoch - 9ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 3.3747e-04 - 120ms/epoch - 8ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 1.7872e-04 - 124ms/epoch - 8ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 3.0657e-05 - 127ms/epoch - 8ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 2.6156e-04 - 126ms/epoch - 8ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 0.0011 - 124ms/epoch - 8ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 0.0014 - 123ms/epoch - 8ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 0.0017 - 135ms/epoch - 9ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 0.0027 - 123ms/epoch - 8ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 0.0017 - 124ms/epoch - 8ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 7.3455e-04 - 120ms/epoch - 8ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 2.4403e-04 - 128ms/epoch - 9ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 1.2162e-04 - 118ms/epoch - 8ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 8.3932e-05 - 117ms/epoch - 8ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 1.1956e-04 - 126ms/epoch - 8ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 3.2700e-05 - 120ms/epoch - 8ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 3.0789e-05 - 118ms/epoch - 8ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 1.8778e-05 - 116ms/epoch - 8ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 1.9168e-05 - 127ms/epoch - 8ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 1.3239e-05 - 121ms/epoch - 8ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 1.1212e-05 - 118ms/epoch - 8ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 9.3788e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 8.0863e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 7.4078e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 7.8772e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 7.0084e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 5.0938e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 4.8589e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 4.8949e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 5.7978e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 8.6069e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 4.7105e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 3.0087e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 3.9276e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 3.4056e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 2.7555e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 2.5321e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 3.1018e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 2.4045e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 2.0962e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 1.7065e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 1.5493e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 1.4983e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 1.5076e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 1.7212e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 1.8978e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 1.8020e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 1.4467e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 1.2366e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 1.6435e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 1.4900e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 1.7470e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 1.1409e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 8.8986e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 8.8629e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 8.7375e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 8.9272e-07 - 125ms/epoch - 8ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 8.2845e-07 - 114ms/epoch - 8ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 8.7079e-07 - 115ms/epoch - 8ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 8.7737e-07 - 116ms/epoch - 8ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 9.3557e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 9.1065e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 8.7883e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 8.1218e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 1.3600e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 1.5890e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 7.1570e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 6.0412e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 5.7872e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 5.1757e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 5.5570e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 6.9020e-07 - 133ms/epoch - 9ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 1.0060e-06 - 111ms/epoch - 7ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 5.2772e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 7.0603e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 7.5142e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 4.9105e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 7.3668e-07 - 129ms/epoch - 9ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 1.0807e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 8.9921e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 8.8698e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 7.8095e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 1.1626e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 9.0401e-07 - 128ms/epoch - 9ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 4.8346e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 3.4185e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 3.9796e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 5.3467e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 3.8659e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 4.3557e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 5.0035e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 6.2906e-07 - 113ms/epoch - 8ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 6.1259e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 3.2502e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 3.4675e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 3.5498e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 3.6183e-07 - 117ms/epoch - 8ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 4.0099e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 4.4384e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 3.9386e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 4.1813e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 3.3183e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 4.8635e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 1.3074e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 1.4316e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 1.3622e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 7.7590e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 4.2076e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 1.1982e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 6.8098e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 6.5617e-07 - 114ms/epoch - 8ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 1.3310e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 1.3673e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 1.9538e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 2.0983e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 4.1548e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 9.9403e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 1.5665e-05 - 115ms/epoch - 8ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 3.3098e-05 - 119ms/epoch - 8ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 4.6091e-05 - 130ms/epoch - 9ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 2.1121e-05 - 126ms/epoch - 8ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 1.0240e-05 - 125ms/epoch - 8ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 7.2234e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 3.7222e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 1.0461e-05 - 117ms/epoch - 8ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 7.5162e-05 - 122ms/epoch - 8ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 1.7698e-05 - 124ms/epoch - 8ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 5.7091e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 2.5482e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 8.8477e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 5.5165e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 2.1345e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 2.1122e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 2.8828e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 2.2532e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 5.0579e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 1.3522e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 8.2302e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 4.6004e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 2.9580e-05 - 122ms/epoch - 8ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 6.5228e-05 - 118ms/epoch - 8ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 4.8317e-05 - 120ms/epoch - 8ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 1.2214e-04 - 113ms/epoch - 8ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 2.0404e-04 - 120ms/epoch - 8ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 1.1471e-04 - 116ms/epoch - 8ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 5.3146e-05 - 117ms/epoch - 8ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 1.3847e-04 - 117ms/epoch - 8ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 1.2737e-04 - 118ms/epoch - 8ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 2.6073e-04 - 125ms/epoch - 8ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 0.0885 - 118ms/epoch - 8ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 0.1206 - 127ms/epoch - 8ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 0.0641 - 126ms/epoch - 8ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 0.0164 - 120ms/epoch - 8ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 0.0201 - 126ms/epoch - 8ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 0.1688 - 125ms/epoch - 8ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7ccec41674c0>"
]
},
"metadata": {},
"execution_count": 18
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "76140dfb-9a06-49a3-c0b1-3c53cba7ec25",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 443
}
},
"source": [
"# Plotting code, feel free to ignore.\n",
"h = 1.0\n",
"x_min, x_max = X[:, 0].min() - 5, X[:, 0].max() + 5\n",
"y_min, y_max = X[:, 1].min() - 5, X[:, 1].max() + 5\n",
"xx, yy = np.meshgrid(np.arange(x_min, x_max, h),\n",
" np.arange(y_min, y_max, h))\n",
"\n",
"# here \"model\" is your model's prediction (classification) function\n",
"Z = tn_model.predict(np.c_[xx.ravel(), yy.ravel()])\n",
"\n",
"# Put the result into a color plot\n",
"Z = Z.reshape(xx.shape)\n",
"plt.contourf(xx, yy, Z)\n",
"plt.axis('off')\n",
"\n",
"# Plot also the training points\n",
"plt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired)"
],
"execution_count": 19,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"7/7 [==============================] - 0s 5ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7ccdd821f430>"
]
},
"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": "1273cef4-41a3-453c-de6f-e1285871a406"
},
"execution_count": 20,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712724665.6232631\n",
"Wed Apr 10 04:51:05 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": "a57d5817-72df-49b1-d18c-cffceaa61232"
},
"execution_count": 21,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712724665.6294029\n",
"Wed Apr 10 04:51:05 2024\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Function to compute saliency map\n",
"@tf.function\n",
"def compute_saliency(input_image):\n",
" with tf.GradientTape() as tape:\n",
" tape.watch(input_image)\n",
" predictions = tn_model(input_image)\n",
" grads = tape.gradient(predictions, input_image)\n",
" saliency_map = tf.reduce_max(tf.abs(grads), axis=-1)\n",
" return saliency_map\n",
"\n",
"# Function to compute saliency map using Gradient\n",
"@tf.function\n",
"def compute_gradient_saliency(input_image):\n",
" with tf.GradientTape() as tape:\n",
" tape.watch(input_image)\n",
" predictions = tn_model(input_image)\n",
" grads = tape.gradient(predictions, input_image)\n",
" saliency_map = tf.reduce_max(tf.abs(grads), axis=-1)\n",
" return saliency_map\n",
"\n",
"# Compute saliency map for the entire grid\n",
"def compute_saliency_map_grid():\n",
" xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))\n",
" input_image = np.c_[xx.ravel(), yy.ravel()]\n",
" saliency_map = compute_saliency(tf.constant(input_image, dtype=tf.float32)).numpy()\n",
" saliency_map = saliency_map.reshape(xx.shape)\n",
" return xx, yy, saliency_map\n",
"\n",
"# Compute and plot saliency map for the entire grid\n",
"xx, yy, saliency_map = compute_saliency_map_grid()\n",
"\n",
"# Compute saliency maps for all data points\n",
"def compute_saliency_maps():\n",
" saliency_maps = []\n",
" for data_point in X:\n",
" saliency_map = compute_gradient_saliency(tf.constant(data_point[None, :], dtype=tf.float32)).numpy()\n",
" saliency_maps.append(saliency_map)\n",
" return saliency_maps\n",
"\n",
"# Find the indices of the data points with the highest saliency values\n",
"def find_top_indices(saliency_maps, top_k):\n",
" top_indices = np.argsort(np.max(saliency_maps, axis=1))[-top_k:]\n",
" return top_indices\n",
"\n",
"def plot_most_diagnostic(top_indices, top_k, normalized_saliency_values):\n",
" plt.figure(figsize=(8, 6))\n",
" plt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired)\n",
" plt.scatter(X[top_indices, 0], X[top_indices, 1], marker='o', s=200, facecolors='none', edgecolors='r', linewidths=2)\n",
" for i, index in enumerate(top_indices):\n",
" plt.annotate(f'{normalized_saliency_values.iloc[index][\"Saliency\"]:.4f}', (X[index, 0], X[index, 1]), xytext=(X[index, 0]+0.35, X[index, 1]+0.25), arrowprops=dict(facecolor='black', arrowstyle='->'))\n",
" plt.title(f'Saliency Most Diagnostic Data Points (Top {top_k})')\n",
" plt.xlabel('Feature 1')\n",
" plt.ylabel('Feature 2')\n",
" plt.grid(True)\n",
" plt.axis('equal')\n",
" plt.show()\n",
"\n",
"# Compute saliency maps for all data points\n",
"saliency_maps = compute_saliency_maps()\n",
"\n",
"# Find the indices of the data points with the highest saliency values\n",
"top_k = 5 # Number of top diagnostic data points to select\n",
"top_indices = find_top_indices(saliency_maps, top_k)\n",
"\n",
"# Create a DataFrame to store the saliency values\n",
"saliency_df = pd.DataFrame(data=saliency_maps, columns=[\"Saliency\"])\n",
"\n",
"# Save the saliency values to a CSV file\n",
"saliency_df.to_csv(\"saliency_values.csv\", index=False)\n",
"\n",
"print(\"Saliency values saved to saliency_values.csv\")\n",
"\n",
"# Normalizing the saliency values\n",
"normalized_saliency = (saliency_df - saliency_df.min()) / (saliency_df.max() - saliency_df.min())\n",
"\n",
"# Saving the normalized saliency values to a new CSV file\n",
"normalized_saliency.to_csv(\"normalized_saliency_values.csv\", index=False)\n",
"\n",
"# Plot the most diagnostic data points\n",
"plot_most_diagnostic(top_indices, top_k, normalized_saliency)\n",
"\n",
"print(\"Normalized saliency values saved to normalized_saliency_values.csv\")\n",
"print(\"Normalized Saliency Top-k:\")\n",
"print(normalized_saliency.nlargest(top_k, 'Saliency'))\n",
"print(\"Normalized Saliency Max:\", normalized_saliency.max())\n",
"print(\"Normalized Saliency Min:\", normalized_saliency.min())\n",
"print(\"Normalized Saliency Mean:\", normalized_saliency.mean())\n",
"print(\"Normalized Saliency Median:\", normalized_saliency.median())\n",
"print(\"Normalized Saliency Mode:\", normalized_saliency.mode())\n",
"sum_normalized_values = normalized_saliency.sum()\n",
"print(\"Normalized Saliency Sum:\", sum_normalized_values)\n",
"print(\"#\")\n",
"print(\"#\")\n",
"print(\"#\")\n",
"print(\"Normalized Saliency Standard Deviation:\", normalized_saliency.std())\n",
"print(\"Normalized Saliency Skewness:\", normalized_saliency.skew())\n",
"print(\"Normalized Saliency Kurtosis:\", normalized_saliency.kurtosis())\n",
"print(\"Normalized Saliency Variance:\", normalized_saliency.var())\n",
"coefficient_variation = (normalized_saliency.std() / normalized_saliency.mean()) * 100\n",
"print(\"Normalized Saliency Coefficient of Variation:\", coefficient_variation)\n",
"print(\"#\")\n",
"print(\"#\")\n",
"print(\"#\")\n",
"cumulative_sum = normalized_saliency.cumsum()\n",
"print(\"Cumulative Sum of Normalized Saliency Values:\", cumulative_sum)\n",
"mean_cumulative_sum = cumulative_sum / len(normalized_saliency)\n",
"print(\"Mean of Cumulative Sum of Normalized Saliency Values:\", mean_cumulative_sum)\n",
"rms = np.sqrt(np.mean(normalized_saliency**2))\n",
"print(\"Normalized Saliency Root Mean Square:\", rms)\n",
"q1 = normalized_saliency.quantile(0.25)\n",
"q2 = normalized_saliency.quantile(0.75)\n",
"iqr = q2 - q1\n",
"print(\"Normalized Saliency 25th Percentile:\", q1)\n",
"print(\"Normalized Saliency 75th Percentile:\", q2)\n",
"print(\"Normalized Saliency Interquartile Range:\", iqr)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1849
},
"id": "95xed6YyDClf",
"outputId": "e669768a-149a-4e5b-cbb6-0b23b61a6e40"
},
"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",
"139 1.000000\n",
"69 0.986766\n",
"410 0.984481\n",
"376 0.983670\n",
"226 0.950027\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 0.068376\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.029878\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.0\n",
"Normalized Saliency Sum: Saliency 32.820667\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.187386\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 3.957261\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 14.56973\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.035113\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 274.050385\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.001696\n",
"1 0.794942\n",
"2 0.800613\n",
"3 0.803725\n",
"4 0.803729\n",
".. ...\n",
"475 32.652084\n",
"476 32.686058\n",
"477 32.720955\n",
"478 32.782532\n",
"479 32.820656\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000004\n",
"1 0.001656\n",
"2 0.001668\n",
"3 0.001674\n",
"4 0.001674\n",
".. ...\n",
"475 0.068025\n",
"476 0.068096\n",
"477 0.068169\n",
"478 0.068297\n",
"479 0.068376\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.19928774\n",
"Normalized Saliency 25th Percentile: Saliency 0.001747\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.038126\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.036379\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": "89d4c556-7db7-4fdc-df2d-a28c71996730"
},
"execution_count": 23,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712724667.605155\n",
"Wed Apr 10 04:51:07 2024\n"
]
}
]
}
]
}