Datasets
Models
Downloads: 1
1261 lines (1261 with data), 215.7 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": 12,
"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": 13,
"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": "3c808d59-ea05-402e-99d0-e4a7638e74a8",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
}
},
"source": [
"Dense = tf.keras.layers.Dense\n",
"tn_model = tf.keras.Sequential(\n",
" [\n",
" tf.keras.Input(shape=(2,)),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Start Modified Layers\n",
" Dense(1024, activation=tf.nn.relu),\n",
" TNLayer(),\n",
" TNLayer(),\n",
" TNLayer(),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 14,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_1\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_3 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_4 (Dense) (None, 1024) 1049600 \n",
" \n",
" tn_layer_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_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": [
"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": 15,
"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": "48537f86-f417-45b4-cbd3-cc603d2953b2"
},
"execution_count": 16,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712629362.6018586\n",
"Tue Apr 9 02:22:42 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "9e1b6837-c1d0-4f14-a097-bfef51fe0970",
"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": 17,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 2s - loss: 1.0023 - 2s/epoch - 112ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.9906 - 154ms/epoch - 10ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.5612 - 146ms/epoch - 10ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0823 - 158ms/epoch - 11ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0312 - 149ms/epoch - 10ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0222 - 145ms/epoch - 10ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0155 - 146ms/epoch - 10ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0128 - 145ms/epoch - 10ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0102 - 144ms/epoch - 10ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0089 - 136ms/epoch - 9ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0078 - 143ms/epoch - 10ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0041 - 139ms/epoch - 9ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0032 - 145ms/epoch - 10ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0023 - 138ms/epoch - 9ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0011 - 138ms/epoch - 9ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 5.7706e-04 - 137ms/epoch - 9ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 3.2449e-04 - 133ms/epoch - 9ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 1.5595e-04 - 132ms/epoch - 9ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 1.0901e-04 - 139ms/epoch - 9ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 6.7304e-05 - 135ms/epoch - 9ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 5.5328e-05 - 149ms/epoch - 10ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 4.3748e-05 - 145ms/epoch - 10ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 3.6386e-05 - 128ms/epoch - 9ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 3.0503e-05 - 131ms/epoch - 9ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 2.5983e-05 - 141ms/epoch - 9ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 2.2001e-05 - 145ms/epoch - 10ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 2.2291e-05 - 139ms/epoch - 9ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 1.7112e-05 - 139ms/epoch - 9ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 1.4114e-05 - 140ms/epoch - 9ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 1.2612e-05 - 137ms/epoch - 9ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 1.0729e-05 - 141ms/epoch - 9ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 9.9037e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 8.6799e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 7.7799e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 7.4519e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 6.9791e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 5.4919e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 5.7193e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 4.7388e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 4.2798e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 4.5251e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 4.9953e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 3.2429e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 3.5365e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 3.1862e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 3.1869e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 2.3777e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 2.8711e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 2.8337e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 3.0086e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 2.1772e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 3.5563e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 2.3495e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 1.7966e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 1.4450e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 1.4377e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 1.5704e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 1.6763e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 1.1722e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 1.5028e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 1.6344e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 1.1543e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 1.7431e-06 - 146ms/epoch - 10ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 1.5561e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 1.5953e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 1.3004e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 8.8251e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 8.2700e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 5.7995e-07 - 147ms/epoch - 10ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 7.2965e-07 - 133ms/epoch - 9ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 6.4076e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 6.8723e-07 - 144ms/epoch - 10ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 9.2234e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 6.7656e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 6.2039e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 5.0673e-07 - 133ms/epoch - 9ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 4.4696e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 4.7592e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 4.3467e-07 - 145ms/epoch - 10ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 3.7528e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 4.0700e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 3.7378e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 5.0316e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 5.2347e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 4.1687e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 2.9474e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 3.6140e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 4.1101e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 4.7197e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 6.0636e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 6.0133e-07 - 143ms/epoch - 10ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 7.5078e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 4.0856e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 2.0299e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 2.0099e-07 - 148ms/epoch - 10ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 3.4470e-07 - 148ms/epoch - 10ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 9.5238e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 4.7514e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 4.2262e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 5.5411e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 7.0864e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 7.3565e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 2.8039e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 6.2565e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 8.1194e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 2.3275e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 1.5602e-07 - 150ms/epoch - 10ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 2.4584e-07 - 146ms/epoch - 10ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 4.1746e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 5.3068e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 7.3204e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 4.2593e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 2.6789e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 4.5678e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 2.8433e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 3.8066e-07 - 145ms/epoch - 10ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 5.2131e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 1.7634e-07 - 143ms/epoch - 10ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 3.7407e-07 - 144ms/epoch - 10ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 4.4106e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 8.0679e-07 - 132ms/epoch - 9ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 6.1608e-07 - 131ms/epoch - 9ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 1.9484e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 4.5165e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 8.8788e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 5.7550e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 7.5652e-07 - 146ms/epoch - 10ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 1.7415e-07 - 129ms/epoch - 9ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 1.4050e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 4.4889e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 2.5769e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 9.6239e-08 - 145ms/epoch - 10ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 9.1075e-08 - 134ms/epoch - 9ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 1.3652e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 2.6676e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 1.6852e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 4.6818e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 1.5227e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 3.3067e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 5.4272e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 5.6386e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 5.6606e-06 - 155ms/epoch - 10ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 1.6365e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 1.6474e-05 - 145ms/epoch - 10ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 9.3042e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 9.6566e-05 - 145ms/epoch - 10ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 2.1648e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 5.2532e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 3.4926e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 8.0521e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 3.1964e-05 - 138ms/epoch - 9ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 3.4562e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 8.6546e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 9.2345e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 4.4599e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 5.9688e-07 - 133ms/epoch - 9ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 6.1978e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 1.9239e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 2.2603e-05 - 133ms/epoch - 9ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 7.7122e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 1.9163e-05 - 146ms/epoch - 10ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 2.4814e-05 - 147ms/epoch - 10ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 1.2499e-05 - 135ms/epoch - 9ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 1.6434e-05 - 135ms/epoch - 9ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 3.4881e-06 - 149ms/epoch - 10ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 1.5414e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 2.2177e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 3.0337e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 9.9807e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 9.1658e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 9.2456e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 6.8986e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 5.6179e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 2.5409e-07 - 146ms/epoch - 10ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 1.0637e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 7.9126e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 1.0082e-05 - 148ms/epoch - 10ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 4.9868e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 1.5570e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 6.9806e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 1.5793e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 1.7619e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 2.5507e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 2.0161e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 6.7953e-07 - 146ms/epoch - 10ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 7.5379e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 7.4271e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 2.7531e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 1.2936e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 3.3066e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 2.8955e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 7.3270e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 2.8361e-05 - 132ms/epoch - 9ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 1.0773e-04 - 140ms/epoch - 9ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 4.8606e-04 - 137ms/epoch - 9ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 3.3941e-04 - 135ms/epoch - 9ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 1.0259e-04 - 138ms/epoch - 9ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 0.0016 - 145ms/epoch - 10ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 0.0392 - 135ms/epoch - 9ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 0.0377 - 132ms/epoch - 9ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 0.0138 - 138ms/epoch - 9ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 0.0195 - 142ms/epoch - 9ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 0.0055 - 140ms/epoch - 9ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 0.0026 - 132ms/epoch - 9ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 2.5955e-04 - 139ms/epoch - 9ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 6.7278e-04 - 133ms/epoch - 9ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 4.7487e-04 - 135ms/epoch - 9ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 4.8858e-05 - 133ms/epoch - 9ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 3.3928e-05 - 133ms/epoch - 9ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 8.3198e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 5.0191e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 7.1540e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 2.4392e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 2.6106e-06 - 146ms/epoch - 10ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 8.1394e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 8.8305e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 7.0251e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 3.2679e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 2.6548e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 3.5851e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 1.5423e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 1.3178e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 1.7254e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 4.2786e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.1862e-05 - 133ms/epoch - 9ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 9.6563e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 2.0964e-05 - 140ms/epoch - 9ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 8.5643e-05 - 139ms/epoch - 9ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 4.1786e-05 - 150ms/epoch - 10ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 4.7944e-05 - 140ms/epoch - 9ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 3.9703e-05 - 146ms/epoch - 10ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 1.2832e-05 - 144ms/epoch - 10ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 6.7227e-06 - 151ms/epoch - 10ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 3.8113e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 9.5597e-07 - 143ms/epoch - 10ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 1.1737e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 1.0910e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 1.7457e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 3.7447e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 3.9271e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 2.5178e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 3.2126e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 1.4829e-05 - 136ms/epoch - 9ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 1.4423e-05 - 148ms/epoch - 10ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 3.6717e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 1.4867e-05 - 136ms/epoch - 9ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 3.2324e-06 - 153ms/epoch - 10ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 1.6197e-05 - 136ms/epoch - 9ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 3.6362e-05 - 144ms/epoch - 10ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 6.3972e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 1.6149e-05 - 134ms/epoch - 9ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 7.7918e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 3.5361e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 1.5141e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 7.2885e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 8.9155e-07 - 145ms/epoch - 10ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 7.2521e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 9.8633e-07 - 145ms/epoch - 10ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 7.0972e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 1.5330e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 1.2545e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 1.9454e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 3.5455e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 1.4731e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 2.4346e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 5.9880e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 5.8232e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 9.2542e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 3.2311e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 5.1786e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 8.9309e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 7.2971e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 9.0776e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 6.0646e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 5.0237e-05 - 136ms/epoch - 9ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 1.1623e-04 - 143ms/epoch - 10ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 1.3644e-04 - 138ms/epoch - 9ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 2.6279e-05 - 135ms/epoch - 9ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 2.6289e-05 - 138ms/epoch - 9ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 5.4674e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 2.5049e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 1.8671e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 1.1172e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 2.1117e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 1.3882e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 2.3600e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 3.2002e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 2.0273e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 3.4148e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 4.5122e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 4.0646e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 6.7980e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 3.6694e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 4.2123e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 3.2939e-06 - 134ms/epoch - 9ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 3.0305e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 4.1590e-06 - 152ms/epoch - 10ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 3.6715e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 5.3078e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 7.8226e-06 - 142ms/epoch - 9ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7f3b9c312140>"
]
},
"metadata": {},
"execution_count": 17
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "b11a1b13-a1da-4f13-d048-15bc0e6b3912",
"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": 18,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 5ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7f3b9c0cbfa0>"
]
},
"metadata": {},
"execution_count": 18
},
{
"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": "2e754400-1b5c-4bfe-afdb-615cc61fee00"
},
"execution_count": 19,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712629407.1935997\n",
"Tue Apr 9 02:23:27 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": "fcb8b4b8-c52e-45fd-c424-427034f13592"
},
"execution_count": 20,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712629407.2004821\n",
"Tue Apr 9 02:23:27 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": 1896
},
"id": "95xed6YyDClf",
"outputId": "8a764653-283b-4934-82ba-7278134dd448"
},
"execution_count": 21,
"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 0.475301\n",
"327 0.272977\n",
"287 0.188370\n",
"110 0.086599\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 0.008758\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.003249\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.002016\n",
"1 0.002130\n",
"2 0.020702\n",
"Normalized Saliency Sum: Saliency 4.203701\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.052813\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 15.664974\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 273.821655\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.002789\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 603.043823\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.004572\n",
"1 0.008663\n",
"2 0.011174\n",
"3 0.014982\n",
"4 0.021191\n",
".. ...\n",
"475 4.194695\n",
"476 4.198860\n",
"477 4.199698\n",
"478 4.201726\n",
"479 4.203698\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000010\n",
"1 0.000018\n",
"2 0.000023\n",
"3 0.000031\n",
"4 0.000044\n",
".. ...\n",
"475 0.008739\n",
"476 0.008748\n",
"477 0.008749\n",
"478 0.008754\n",
"479 0.008758\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.05347973\n",
"Normalized Saliency 25th Percentile: Saliency 0.002008\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.004802\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.002794\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": "c8da2271-6e44-49bf-a733-38faec72cf78"
},
"execution_count": 22,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712629409.3076527\n",
"Tue Apr 9 02:23:29 2024\n"
]
}
]
}
]
}