Datasets
Models
Downloads: 1
1254 lines (1254 with data), 218.1 kB
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"machine_shape": "hm",
"gpuType": "V28"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "TPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "8XnVMPBXmtRa"
},
"source": [
"# TensorNetworks in Neural Networks.\n",
"\n",
"Here, we have a small toy example of how to use a TN inside of a fully connected neural network.\n",
"\n",
"First off, let's install tensornetwork"
]
},
{
"cell_type": "code",
"metadata": {
"id": "7HGRsYNAFxME"
},
"source": [
"# !pip install tensornetwork\n",
"\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import tensorflow as tf\n",
"# Import tensornetwork\n",
"import tensornetwork as tn\n",
"import random\n",
"import time\n",
"import pandas as pd\n",
"# Set the backend to tesorflow\n",
"# (default is numpy)\n",
"tn.set_default_backend(\"tensorflow\")\n",
"np.random.seed(42)\n",
"random.seed(42)\n",
"tf.random.set_seed(42)\n",
"# Explainability code assistance aided by ChatGPT3.5\n",
"# 2021 Kelly, D. TensorFlow Explainable AI tutorial https://www.youtube.com/watch?v=6xePkn3-LME"
],
"execution_count": 78,
"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": 79,
"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": "3afaf4e1-e0ee-4ecf-9132-2247c255f7b4",
"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",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 80,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_7\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_27 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_28 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_29 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 1053697 (4.02 MB)\n",
"Trainable params: 1053697 (4.02 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": 81,
"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": "9fa8525b-bc94-4336-f7e9-5c77f49700bc"
},
"execution_count": 82,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712632487.045283\n",
"Tue Apr 9 03:14:47 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "1e38dc78-2652-46a6-c47f-53d5641c6369",
"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": 83,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 0.2714 - 579ms/epoch - 39ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.1293 - 86ms/epoch - 6ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.0801 - 89ms/epoch - 6ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0728 - 87ms/epoch - 6ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0682 - 89ms/epoch - 6ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0673 - 89ms/epoch - 6ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0591 - 90ms/epoch - 6ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0578 - 83ms/epoch - 6ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0546 - 85ms/epoch - 6ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0494 - 87ms/epoch - 6ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0442 - 83ms/epoch - 6ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0365 - 88ms/epoch - 6ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0311 - 87ms/epoch - 6ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0271 - 88ms/epoch - 6ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0293 - 89ms/epoch - 6ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0244 - 84ms/epoch - 6ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0192 - 82ms/epoch - 5ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0136 - 86ms/epoch - 6ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0101 - 89ms/epoch - 6ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0085 - 88ms/epoch - 6ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 0.0101 - 89ms/epoch - 6ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 0.0066 - 84ms/epoch - 6ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 0.0064 - 89ms/epoch - 6ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 0.0035 - 87ms/epoch - 6ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 0.0053 - 86ms/epoch - 6ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 0.0050 - 84ms/epoch - 6ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 0.0029 - 86ms/epoch - 6ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 0.0026 - 89ms/epoch - 6ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 0.0020 - 84ms/epoch - 6ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 0.0019 - 86ms/epoch - 6ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 0.0020 - 85ms/epoch - 6ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 0.0027 - 82ms/epoch - 5ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 0.0029 - 89ms/epoch - 6ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 0.0019 - 85ms/epoch - 6ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 0.0025 - 88ms/epoch - 6ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 0.0016 - 87ms/epoch - 6ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 0.0016 - 85ms/epoch - 6ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 0.0011 - 84ms/epoch - 6ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 0.0012 - 85ms/epoch - 6ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 0.0012 - 94ms/epoch - 6ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 0.0013 - 88ms/epoch - 6ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 0.0011 - 92ms/epoch - 6ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 0.0014 - 88ms/epoch - 6ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 0.0020 - 92ms/epoch - 6ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 0.0026 - 89ms/epoch - 6ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 0.0023 - 87ms/epoch - 6ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 0.0021 - 82ms/epoch - 5ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 0.0016 - 85ms/epoch - 6ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 0.0013 - 89ms/epoch - 6ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 8.7429e-04 - 87ms/epoch - 6ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 5.1996e-04 - 85ms/epoch - 6ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 5.0118e-04 - 87ms/epoch - 6ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 5.4871e-04 - 89ms/epoch - 6ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 6.8111e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 0.0017 - 88ms/epoch - 6ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 0.0026 - 87ms/epoch - 6ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 0.0017 - 84ms/epoch - 6ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 0.0012 - 84ms/epoch - 6ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 0.0011 - 89ms/epoch - 6ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 0.0012 - 90ms/epoch - 6ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 0.0026 - 84ms/epoch - 6ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 0.0027 - 89ms/epoch - 6ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 0.0016 - 85ms/epoch - 6ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 0.0020 - 87ms/epoch - 6ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 0.0013 - 82ms/epoch - 5ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 0.0019 - 90ms/epoch - 6ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 0.0030 - 84ms/epoch - 6ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 0.0017 - 86ms/epoch - 6ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 9.2244e-04 - 85ms/epoch - 6ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 0.0016 - 89ms/epoch - 6ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 0.0043 - 84ms/epoch - 6ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 0.0055 - 87ms/epoch - 6ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 0.0030 - 85ms/epoch - 6ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 0.0083 - 85ms/epoch - 6ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 0.0120 - 91ms/epoch - 6ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 0.0044 - 93ms/epoch - 6ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 0.0034 - 90ms/epoch - 6ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 8.8324e-04 - 87ms/epoch - 6ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 4.5802e-04 - 92ms/epoch - 6ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 3.9208e-04 - 86ms/epoch - 6ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 6.4135e-04 - 83ms/epoch - 6ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 4.1783e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 3.6402e-04 - 89ms/epoch - 6ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 4.3779e-04 - 87ms/epoch - 6ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 6.2962e-04 - 83ms/epoch - 6ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 3.8816e-04 - 87ms/epoch - 6ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 3.3188e-04 - 87ms/epoch - 6ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 3.8984e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 7.0430e-04 - 92ms/epoch - 6ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 3.0690e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 2.4709e-04 - 82ms/epoch - 5ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 2.1664e-04 - 84ms/epoch - 6ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 4.3197e-04 - 84ms/epoch - 6ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 3.1120e-04 - 86ms/epoch - 6ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 3.8053e-04 - 84ms/epoch - 6ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 0.0016 - 84ms/epoch - 6ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 0.0011 - 94ms/epoch - 6ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 0.0013 - 93ms/epoch - 6ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 9.1716e-04 - 86ms/epoch - 6ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 4.7544e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 3.8974e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 4.7615e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 5.7743e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 5.2320e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 9.6334e-04 - 85ms/epoch - 6ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 4.2335e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 5.0315e-04 - 85ms/epoch - 6ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 6.6631e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 6.3266e-04 - 92ms/epoch - 6ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 3.0573e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 3.9337e-04 - 86ms/epoch - 6ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 0.0012 - 86ms/epoch - 6ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 7.3279e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 3.2996e-04 - 86ms/epoch - 6ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 2.9676e-04 - 87ms/epoch - 6ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 6.3534e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 3.2074e-04 - 84ms/epoch - 6ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 2.0734e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 1.3858e-04 - 84ms/epoch - 6ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 7.6309e-05 - 94ms/epoch - 6ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 6.2015e-05 - 93ms/epoch - 6ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 8.2998e-05 - 86ms/epoch - 6ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 1.9199e-04 - 89ms/epoch - 6ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 8.1386e-04 - 89ms/epoch - 6ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 0.0012 - 92ms/epoch - 6ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 0.0012 - 87ms/epoch - 6ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 0.0022 - 93ms/epoch - 6ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 0.0037 - 87ms/epoch - 6ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 0.0016 - 91ms/epoch - 6ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 0.0012 - 90ms/epoch - 6ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 5.7338e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 0.0023 - 87ms/epoch - 6ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 0.0023 - 89ms/epoch - 6ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 8.4498e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 9.4130e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 0.0013 - 85ms/epoch - 6ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 8.0297e-04 - 85ms/epoch - 6ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 9.1667e-04 - 86ms/epoch - 6ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 0.0011 - 91ms/epoch - 6ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 0.0010 - 88ms/epoch - 6ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 7.6022e-04 - 87ms/epoch - 6ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 7.0527e-04 - 94ms/epoch - 6ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 0.0018 - 81ms/epoch - 5ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 0.0030 - 86ms/epoch - 6ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 0.0053 - 89ms/epoch - 6ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 0.0037 - 85ms/epoch - 6ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 0.0054 - 88ms/epoch - 6ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 0.0052 - 86ms/epoch - 6ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 0.0023 - 85ms/epoch - 6ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 0.0037 - 91ms/epoch - 6ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 0.0038 - 89ms/epoch - 6ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 0.0053 - 81ms/epoch - 5ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 0.0044 - 89ms/epoch - 6ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 0.0028 - 92ms/epoch - 6ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 0.0012 - 91ms/epoch - 6ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 4.1524e-04 - 89ms/epoch - 6ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 6.8341e-04 - 93ms/epoch - 6ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 7.8988e-04 - 85ms/epoch - 6ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 3.1412e-04 - 83ms/epoch - 6ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 2.5703e-04 - 86ms/epoch - 6ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 1.7197e-04 - 84ms/epoch - 6ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 1.6843e-04 - 89ms/epoch - 6ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 2.4099e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 2.4133e-04 - 87ms/epoch - 6ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 1.7025e-04 - 89ms/epoch - 6ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 1.5751e-04 - 85ms/epoch - 6ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 9.3037e-05 - 87ms/epoch - 6ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 1.8196e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 1.6943e-04 - 95ms/epoch - 6ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 1.2871e-04 - 85ms/epoch - 6ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 1.2971e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 8.8773e-05 - 85ms/epoch - 6ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 6.0957e-05 - 87ms/epoch - 6ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 4.1420e-05 - 84ms/epoch - 6ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 4.2402e-05 - 85ms/epoch - 6ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 7.2425e-05 - 90ms/epoch - 6ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 6.8186e-05 - 87ms/epoch - 6ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 3.8417e-05 - 87ms/epoch - 6ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 3.4929e-05 - 90ms/epoch - 6ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 4.4462e-05 - 83ms/epoch - 6ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 1.1581e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 3.0874e-04 - 92ms/epoch - 6ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 2.5585e-04 - 89ms/epoch - 6ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 2.1703e-04 - 84ms/epoch - 6ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 1.4935e-04 - 92ms/epoch - 6ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 2.1436e-04 - 92ms/epoch - 6ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 1.5151e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 1.6994e-04 - 89ms/epoch - 6ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 1.1531e-04 - 84ms/epoch - 6ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 1.8209e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 3.7532e-04 - 89ms/epoch - 6ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 4.1799e-04 - 83ms/epoch - 6ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 4.5131e-04 - 86ms/epoch - 6ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 6.9389e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 0.0013 - 90ms/epoch - 6ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 0.0018 - 96ms/epoch - 6ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 0.0027 - 93ms/epoch - 6ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 0.0023 - 85ms/epoch - 6ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 0.0059 - 90ms/epoch - 6ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 0.0038 - 85ms/epoch - 6ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 0.0024 - 88ms/epoch - 6ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 0.0012 - 86ms/epoch - 6ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 9.8891e-04 - 93ms/epoch - 6ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 4.5638e-04 - 89ms/epoch - 6ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 1.5692e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 8.1551e-05 - 87ms/epoch - 6ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 5.9910e-05 - 87ms/epoch - 6ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 7.1066e-05 - 94ms/epoch - 6ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 1.1261e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 8.9431e-05 - 84ms/epoch - 6ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 7.7240e-05 - 86ms/epoch - 6ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 9.9448e-05 - 87ms/epoch - 6ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 1.0351e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 1.2219e-04 - 89ms/epoch - 6ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 0.0014 - 83ms/epoch - 6ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 0.0016 - 85ms/epoch - 6ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 0.0014 - 85ms/epoch - 6ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 0.0012 - 92ms/epoch - 6ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 5.5148e-04 - 83ms/epoch - 6ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 3.4695e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 3.5848e-04 - 84ms/epoch - 6ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 3.1042e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 2.9025e-04 - 86ms/epoch - 6ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 2.9548e-04 - 86ms/epoch - 6ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.7971e-04 - 83ms/epoch - 6ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 1.1542e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 8.9400e-05 - 87ms/epoch - 6ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 9.8796e-05 - 90ms/epoch - 6ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 2.0494e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 7.6713e-05 - 85ms/epoch - 6ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 4.7378e-05 - 90ms/epoch - 6ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 3.3668e-05 - 89ms/epoch - 6ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 2.9855e-05 - 84ms/epoch - 6ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 3.4421e-05 - 91ms/epoch - 6ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 2.0796e-05 - 85ms/epoch - 6ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 2.0459e-05 - 84ms/epoch - 6ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 3.1105e-05 - 87ms/epoch - 6ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 2.2771e-05 - 90ms/epoch - 6ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 5.8132e-05 - 87ms/epoch - 6ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 1.1315e-04 - 86ms/epoch - 6ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 6.2222e-05 - 82ms/epoch - 5ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 6.0036e-05 - 81ms/epoch - 5ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 2.5933e-05 - 89ms/epoch - 6ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 2.1214e-05 - 87ms/epoch - 6ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 1.6812e-05 - 85ms/epoch - 6ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 2.2084e-05 - 96ms/epoch - 6ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 2.0861e-05 - 85ms/epoch - 6ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 2.3978e-05 - 81ms/epoch - 5ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 3.0084e-05 - 86ms/epoch - 6ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 5.1138e-05 - 86ms/epoch - 6ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 4.0925e-04 - 85ms/epoch - 6ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 3.0997e-04 - 86ms/epoch - 6ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 4.5107e-04 - 94ms/epoch - 6ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 1.4809e-04 - 83ms/epoch - 6ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 1.8585e-04 - 83ms/epoch - 6ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 9.5996e-05 - 90ms/epoch - 6ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 1.8349e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 6.0883e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 5.5981e-04 - 87ms/epoch - 6ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 9.4921e-04 - 82ms/epoch - 5ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 9.9603e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 2.7108e-04 - 84ms/epoch - 6ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 1.3879e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 4.3921e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 2.1250e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 1.1415e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 4.2961e-05 - 86ms/epoch - 6ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 2.9805e-05 - 85ms/epoch - 6ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 3.0000e-05 - 86ms/epoch - 6ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 2.6439e-05 - 88ms/epoch - 6ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 2.4280e-05 - 84ms/epoch - 6ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 3.5861e-05 - 84ms/epoch - 6ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 5.6697e-05 - 82ms/epoch - 5ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 1.1826e-04 - 83ms/epoch - 6ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 1.7676e-04 - 86ms/epoch - 6ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 1.4394e-04 - 85ms/epoch - 6ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 6.7492e-05 - 83ms/epoch - 6ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 2.8368e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 4.4343e-04 - 82ms/epoch - 5ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 0.0015 - 87ms/epoch - 6ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 0.0025 - 87ms/epoch - 6ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 0.0028 - 82ms/epoch - 5ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 0.0036 - 86ms/epoch - 6ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 0.0055 - 88ms/epoch - 6ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 0.0046 - 93ms/epoch - 6ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 0.0042 - 87ms/epoch - 6ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 0.0021 - 86ms/epoch - 6ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 0.0012 - 86ms/epoch - 6ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 0.0011 - 88ms/epoch - 6ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 5.5122e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 2.4556e-04 - 85ms/epoch - 6ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 8.4603e-05 - 86ms/epoch - 6ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 5.9042e-05 - 89ms/epoch - 6ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 6.4341e-05 - 86ms/epoch - 6ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 3.7147e-05 - 83ms/epoch - 6ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 3.7238e-05 - 81ms/epoch - 5ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 2.9006e-05 - 84ms/epoch - 6ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 6.3348e-05 - 86ms/epoch - 6ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 4.8962e-05 - 87ms/epoch - 6ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 4.8473e-05 - 89ms/epoch - 6ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7f3a583d5ea0>"
]
},
"metadata": {},
"execution_count": 83
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "7874ddd9-03a1-42b5-984e-fc8c7884765a",
"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": 84,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 2ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7f3a38253bb0>"
]
},
"metadata": {},
"execution_count": 84
},
{
"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": "07849fc7-dc53-497a-eec2-3d14babd79d0"
},
"execution_count": 85,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712632514.7857358\n",
"Tue Apr 9 03:15:14 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": "b5b12a62-285c-4d8b-a942-51714f814ccd"
},
"execution_count": 86,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712632514.7912495\n",
"Tue Apr 9 03:15:14 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": 1932
},
"id": "95xed6YyDClf",
"outputId": "72619b43-abfa-487a-94c9-17e060ab4832"
},
"execution_count": 87,
"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 0.775038\n",
"210 0.603358\n",
"287 0.531959\n",
"327 0.471177\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 0.034292\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.013815\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.003787\n",
"1 0.009879\n",
"2 0.011526\n",
"3 0.014812\n",
"4 0.022427\n",
"Normalized Saliency Sum: Saliency 16.460354\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.087326\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 6.325647\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 50.395641\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.007626\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 254.650925\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.014487\n",
"1 0.025445\n",
"2 0.033492\n",
"3 0.047529\n",
"4 0.059055\n",
".. ...\n",
"475 16.188976\n",
"476 16.436771\n",
"477 16.448076\n",
"478 16.456465\n",
"479 16.460358\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000030\n",
"1 0.000053\n",
"2 0.000070\n",
"3 0.000099\n",
"4 0.000123\n",
".. ...\n",
"475 0.033727\n",
"476 0.034243\n",
"477 0.034267\n",
"478 0.034284\n",
"479 0.034292\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.09373313\n",
"Normalized Saliency 25th Percentile: Saliency 0.007899\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.020838\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.012939\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": "afa1e566-d49d-4cb5-a124-bd8fd2d12714"
},
"execution_count": 88,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712632515.7770238\n",
"Tue Apr 9 03:15:15 2024\n"
]
}
]
}
]
}