Datasets
Models
Downloads: 1
1269 lines (1269 with data), 217.1 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": 111,
"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": 112,
"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": "e73467d2-f662-490e-a7aa-a2389d9de69c",
"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",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 113,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_10\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_39 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_40 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_41 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_42 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_43 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_44 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 4202497 (16.03 MB)\n",
"Trainable params: 4202497 (16.03 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": 114,
"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": "7e617d2b-818c-411a-d972-83765cf4d432"
},
"execution_count": 115,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712633512.1726055\n",
"Tue Apr 9 03:31:52 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "19a1db2f-2eff-4006-be5e-0d156bba6165",
"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": 116,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 2s - loss: 0.3995 - 2s/epoch - 106ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.0835 - 227ms/epoch - 15ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.0665 - 222ms/epoch - 15ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0604 - 229ms/epoch - 15ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0467 - 221ms/epoch - 15ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0436 - 224ms/epoch - 15ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0307 - 234ms/epoch - 16ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0331 - 223ms/epoch - 15ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0235 - 215ms/epoch - 14ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0117 - 222ms/epoch - 15ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0075 - 212ms/epoch - 14ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0040 - 214ms/epoch - 14ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0019 - 213ms/epoch - 14ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 8.0409e-04 - 213ms/epoch - 14ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 3.5338e-04 - 211ms/epoch - 14ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 2.7500e-04 - 219ms/epoch - 15ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 1.4137e-04 - 212ms/epoch - 14ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 7.3902e-05 - 219ms/epoch - 15ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 6.8938e-05 - 214ms/epoch - 14ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 5.3015e-05 - 217ms/epoch - 14ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 3.8961e-05 - 223ms/epoch - 15ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 1.2927e-05 - 217ms/epoch - 14ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 5.4862e-06 - 218ms/epoch - 15ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 3.6421e-06 - 214ms/epoch - 14ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 2.9553e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 3.3966e-06 - 218ms/epoch - 15ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 2.4142e-06 - 213ms/epoch - 14ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 2.5910e-06 - 217ms/epoch - 14ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 2.0016e-06 - 223ms/epoch - 15ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 1.9114e-06 - 211ms/epoch - 14ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 1.7772e-06 - 214ms/epoch - 14ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 1.4619e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 2.3254e-06 - 219ms/epoch - 15ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 1.6899e-06 - 214ms/epoch - 14ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 1.2195e-06 - 209ms/epoch - 14ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 1.9170e-06 - 212ms/epoch - 14ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 3.5204e-06 - 219ms/epoch - 15ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 3.9870e-06 - 232ms/epoch - 15ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 2.9870e-06 - 221ms/epoch - 15ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 2.4278e-06 - 224ms/epoch - 15ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 1.7503e-06 - 219ms/epoch - 15ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 2.7260e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 2.1749e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 1.7086e-06 - 210ms/epoch - 14ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 3.1332e-06 - 216ms/epoch - 14ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 1.8809e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 3.2021e-06 - 214ms/epoch - 14ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 2.3873e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 2.2355e-06 - 219ms/epoch - 15ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 1.5892e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 2.5073e-06 - 214ms/epoch - 14ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 4.5464e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 3.0941e-06 - 223ms/epoch - 15ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 1.5494e-06 - 227ms/epoch - 15ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 7.7380e-07 - 224ms/epoch - 15ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 9.2731e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 6.2758e-07 - 221ms/epoch - 15ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 5.0509e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 7.7814e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 3.6241e-06 - 218ms/epoch - 15ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 6.6170e-06 - 217ms/epoch - 14ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 1.3975e-05 - 224ms/epoch - 15ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 3.2633e-05 - 222ms/epoch - 15ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 1.3519e-04 - 223ms/epoch - 15ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 4.2859e-04 - 226ms/epoch - 15ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 3.0421e-04 - 222ms/epoch - 15ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 2.0320e-04 - 220ms/epoch - 15ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 2.8297e-04 - 222ms/epoch - 15ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 1.2090e-04 - 219ms/epoch - 15ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 8.4500e-05 - 220ms/epoch - 15ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 1.0154e-04 - 220ms/epoch - 15ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 1.6030e-04 - 221ms/epoch - 15ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 1.0955e-04 - 226ms/epoch - 15ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 8.8745e-05 - 215ms/epoch - 14ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 9.3804e-05 - 215ms/epoch - 14ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 5.5132e-05 - 223ms/epoch - 15ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 3.9813e-05 - 224ms/epoch - 15ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 1.9907e-05 - 223ms/epoch - 15ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 9.5258e-06 - 216ms/epoch - 14ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 5.3013e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 5.9655e-06 - 221ms/epoch - 15ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 2.0654e-06 - 227ms/epoch - 15ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 1.1072e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 2.3478e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 5.6556e-06 - 214ms/epoch - 14ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 4.3312e-06 - 216ms/epoch - 14ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 2.2460e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 1.6429e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 1.5641e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 1.2753e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 1.2071e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 8.2661e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 1.3435e-06 - 221ms/epoch - 15ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 1.8474e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 4.3307e-06 - 219ms/epoch - 15ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 4.6144e-06 - 213ms/epoch - 14ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 3.6902e-06 - 219ms/epoch - 15ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 1.3215e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 4.9025e-07 - 229ms/epoch - 15ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 3.5547e-07 - 219ms/epoch - 15ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 4.1841e-07 - 223ms/epoch - 15ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 6.6328e-07 - 222ms/epoch - 15ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 4.2234e-07 - 215ms/epoch - 14ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 3.5341e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 4.5735e-07 - 219ms/epoch - 15ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 1.0093e-06 - 217ms/epoch - 14ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 5.4835e-07 - 224ms/epoch - 15ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 4.1003e-07 - 215ms/epoch - 14ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 3.2820e-07 - 221ms/epoch - 15ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 2.6149e-07 - 219ms/epoch - 15ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 5.5196e-07 - 204ms/epoch - 14ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 1.1609e-06 - 212ms/epoch - 14ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 7.5770e-07 - 209ms/epoch - 14ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 1.3896e-06 - 209ms/epoch - 14ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 2.1359e-06 - 217ms/epoch - 14ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 2.0262e-06 - 212ms/epoch - 14ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 1.6945e-06 - 216ms/epoch - 14ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 2.9700e-06 - 210ms/epoch - 14ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 1.8103e-06 - 206ms/epoch - 14ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 1.7075e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 6.2669e-06 - 210ms/epoch - 14ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 4.4346e-06 - 211ms/epoch - 14ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 1.6191e-05 - 211ms/epoch - 14ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 2.0569e-05 - 216ms/epoch - 14ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 7.2792e-05 - 221ms/epoch - 15ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 4.4419e-04 - 213ms/epoch - 14ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 9.6645e-04 - 211ms/epoch - 14ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 0.0023 - 213ms/epoch - 14ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 0.0687 - 215ms/epoch - 14ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 0.0865 - 211ms/epoch - 14ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 0.0430 - 213ms/epoch - 14ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 0.0208 - 209ms/epoch - 14ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 0.0176 - 214ms/epoch - 14ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 0.0125 - 213ms/epoch - 14ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 0.0702 - 212ms/epoch - 14ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 0.0193 - 224ms/epoch - 15ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 0.0121 - 213ms/epoch - 14ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 0.0031 - 218ms/epoch - 15ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 0.0016 - 218ms/epoch - 15ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 6.8329e-04 - 215ms/epoch - 14ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 3.2500e-04 - 216ms/epoch - 14ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 1.6948e-04 - 222ms/epoch - 15ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 8.7526e-05 - 214ms/epoch - 14ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 4.0895e-05 - 218ms/epoch - 15ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 1.1683e-05 - 215ms/epoch - 14ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 6.1002e-06 - 216ms/epoch - 14ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 5.3396e-06 - 219ms/epoch - 15ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 3.8489e-06 - 227ms/epoch - 15ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 3.5475e-06 - 216ms/epoch - 14ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 2.7110e-06 - 218ms/epoch - 15ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 1.8562e-06 - 210ms/epoch - 14ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 1.7475e-06 - 223ms/epoch - 15ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 1.7861e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 2.6028e-06 - 224ms/epoch - 15ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 1.8135e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 1.2572e-06 - 218ms/epoch - 15ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 1.4899e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 1.1333e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 1.0912e-06 - 218ms/epoch - 15ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 1.3267e-06 - 222ms/epoch - 15ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 1.0048e-06 - 218ms/epoch - 15ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 1.5094e-06 - 214ms/epoch - 14ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 1.1921e-06 - 221ms/epoch - 15ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 9.4154e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 8.1184e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 1.1060e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 8.2452e-07 - 214ms/epoch - 14ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 7.7814e-07 - 213ms/epoch - 14ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 6.2812e-07 - 213ms/epoch - 14ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 5.5906e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 5.7763e-07 - 215ms/epoch - 14ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 6.0124e-07 - 215ms/epoch - 14ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 5.6366e-07 - 214ms/epoch - 14ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 4.8546e-07 - 214ms/epoch - 14ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 5.1247e-07 - 215ms/epoch - 14ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 4.7437e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 4.4568e-07 - 221ms/epoch - 15ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 4.4012e-07 - 226ms/epoch - 15ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 4.3060e-07 - 221ms/epoch - 15ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 4.5783e-07 - 219ms/epoch - 15ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 5.7435e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 7.2972e-07 - 227ms/epoch - 15ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 9.9825e-07 - 219ms/epoch - 15ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 7.2642e-07 - 211ms/epoch - 14ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 5.2617e-07 - 218ms/epoch - 15ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 4.0739e-07 - 210ms/epoch - 14ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 5.0748e-07 - 213ms/epoch - 14ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 4.7751e-07 - 214ms/epoch - 14ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 4.5314e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 4.5999e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 9.5548e-07 - 218ms/epoch - 15ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 8.1412e-07 - 216ms/epoch - 14ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 5.4394e-07 - 213ms/epoch - 14ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 3.3357e-07 - 215ms/epoch - 14ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 4.5870e-07 - 218ms/epoch - 15ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 4.0929e-07 - 219ms/epoch - 15ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 3.2792e-07 - 216ms/epoch - 14ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 3.5312e-07 - 215ms/epoch - 14ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 4.0331e-07 - 221ms/epoch - 15ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 3.5040e-07 - 212ms/epoch - 14ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 2.3749e-07 - 223ms/epoch - 15ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 2.5087e-07 - 221ms/epoch - 15ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 3.9427e-07 - 216ms/epoch - 14ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 3.2875e-07 - 218ms/epoch - 15ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 2.9031e-07 - 224ms/epoch - 15ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 4.5240e-07 - 215ms/epoch - 14ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 4.2370e-07 - 212ms/epoch - 14ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 4.1039e-07 - 216ms/epoch - 14ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 2.9710e-07 - 224ms/epoch - 15ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 2.1226e-07 - 210ms/epoch - 14ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 2.6100e-07 - 212ms/epoch - 14ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 2.2351e-07 - 211ms/epoch - 14ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 2.2122e-07 - 208ms/epoch - 14ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 4.0052e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 2.5502e-07 - 211ms/epoch - 14ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 2.7832e-07 - 218ms/epoch - 15ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 3.2260e-07 - 216ms/epoch - 14ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 2.8672e-07 - 225ms/epoch - 15ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 4.6504e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 3.9270e-07 - 219ms/epoch - 15ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 4.6854e-07 - 215ms/epoch - 14ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 2.4811e-07 - 212ms/epoch - 14ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 2.3926e-07 - 211ms/epoch - 14ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 1.8885e-07 - 208ms/epoch - 14ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 2.8526e-07 - 211ms/epoch - 14ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 3.0971e-07 - 224ms/epoch - 15ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 4.6602e-07 - 211ms/epoch - 14ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 2.6519e-07 - 206ms/epoch - 14ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 2.9897e-07 - 212ms/epoch - 14ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 4.1450e-07 - 211ms/epoch - 14ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 3.0217e-07 - 223ms/epoch - 15ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 5.1960e-07 - 214ms/epoch - 14ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 5.1065e-07 - 216ms/epoch - 14ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 7.7324e-07 - 209ms/epoch - 14ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 3.6377e-07 - 214ms/epoch - 14ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 1.2495e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 3.5064e-06 - 214ms/epoch - 14ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 9.8035e-06 - 211ms/epoch - 14ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 2.3452e-05 - 207ms/epoch - 14ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 8.8962e-06 - 215ms/epoch - 14ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 5.3072e-06 - 211ms/epoch - 14ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 1.2240e-05 - 211ms/epoch - 14ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 2.1522e-05 - 212ms/epoch - 14ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 1.0035e-05 - 212ms/epoch - 14ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 2.5452e-05 - 217ms/epoch - 14ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 3.3206e-05 - 221ms/epoch - 15ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 9.8002e-06 - 213ms/epoch - 14ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 1.5047e-05 - 222ms/epoch - 15ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 4.0225e-06 - 217ms/epoch - 14ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 2.6586e-06 - 217ms/epoch - 14ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 3.2015e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 2.8425e-06 - 221ms/epoch - 15ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 5.9957e-06 - 217ms/epoch - 14ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 1.5291e-05 - 214ms/epoch - 14ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 2.1222e-06 - 212ms/epoch - 14ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 1.0007e-06 - 218ms/epoch - 15ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 3.7360e-07 - 212ms/epoch - 14ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 2.4658e-07 - 215ms/epoch - 14ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 3.3486e-07 - 208ms/epoch - 14ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 3.1640e-07 - 212ms/epoch - 14ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 3.2486e-07 - 210ms/epoch - 14ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 2.9455e-07 - 209ms/epoch - 14ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 3.7095e-07 - 212ms/epoch - 14ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 9.8343e-07 - 216ms/epoch - 14ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 1.0174e-06 - 220ms/epoch - 15ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 2.0521e-06 - 217ms/epoch - 14ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 2.5841e-06 - 217ms/epoch - 14ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 1.0759e-05 - 219ms/epoch - 15ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 6.8029e-05 - 218ms/epoch - 15ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 6.9197e-05 - 214ms/epoch - 14ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 4.7190e-05 - 219ms/epoch - 15ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 3.3867e-05 - 225ms/epoch - 15ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 1.6403e-05 - 222ms/epoch - 15ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 7.1787e-06 - 214ms/epoch - 14ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 3.5519e-06 - 217ms/epoch - 14ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 2.4091e-06 - 214ms/epoch - 14ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 1.0577e-06 - 212ms/epoch - 14ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 7.4828e-07 - 215ms/epoch - 14ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 8.5446e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 2.6364e-07 - 211ms/epoch - 14ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 2.8558e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 2.8800e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 1.2841e-06 - 211ms/epoch - 14ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 3.7483e-07 - 213ms/epoch - 14ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 1.1840e-07 - 215ms/epoch - 14ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 1.4062e-07 - 210ms/epoch - 14ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 1.1793e-07 - 210ms/epoch - 14ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 1.8523e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 1.8107e-07 - 219ms/epoch - 15ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 9.1769e-08 - 218ms/epoch - 15ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 1.1504e-07 - 216ms/epoch - 14ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 1.2349e-07 - 216ms/epoch - 14ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 8.6497e-08 - 219ms/epoch - 15ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 1.4298e-07 - 211ms/epoch - 14ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 1.2796e-07 - 220ms/epoch - 15ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 1.4177e-07 - 212ms/epoch - 14ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 1.2004e-07 - 217ms/epoch - 14ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 6.8396e-08 - 216ms/epoch - 14ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 9.4889e-08 - 212ms/epoch - 14ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 5.0150e-07 - 216ms/epoch - 14ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7f3a18491ab0>"
]
},
"metadata": {},
"execution_count": 116
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "3d5c3242-c381-401d-e1b4-208a8259b32f",
"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": 117,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 4ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7f3a187c45b0>"
]
},
"metadata": {},
"execution_count": 117
},
{
"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": "af38a7c1-aa11-4744-ba7d-219e5b7078b1"
},
"execution_count": 118,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712633579.7624621\n",
"Tue Apr 9 03:32:59 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": "7b29e2e5-484a-422f-acca-edf3fb2036e3"
},
"execution_count": 119,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712633579.7681003\n",
"Tue Apr 9 03:32:59 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": 2042
},
"id": "95xed6YyDClf",
"outputId": "602b84a7-c25e-4d21-c9be-0a975408779d"
},
"execution_count": 120,
"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",
"423 1.000000\n",
"37 0.936091\n",
"239 0.909907\n",
"307 0.907316\n",
"327 0.613618\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 0.049668\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.021433\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.000901\n",
"1 0.001036\n",
"2 0.004119\n",
"3 0.009281\n",
"4 0.011882\n",
"5 0.012402\n",
"6 0.017544\n",
"7 0.035603\n",
"8 0.036837\n",
"9 0.045876\n",
"10 0.050620\n",
"Normalized Saliency Sum: Saliency 23.840805\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.105348\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 6.032055\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 44.163254\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.011098\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 212.102554\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.001730\n",
"1 0.006601\n",
"2 0.009896\n",
"3 0.016197\n",
"4 0.020316\n",
".. ...\n",
"475 23.711437\n",
"476 23.767391\n",
"477 23.791277\n",
"478 23.799913\n",
"479 23.840788\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000004\n",
"1 0.000014\n",
"2 0.000021\n",
"3 0.000034\n",
"4 0.000042\n",
".. ...\n",
"475 0.049399\n",
"476 0.049515\n",
"477 0.049565\n",
"478 0.049583\n",
"479 0.049668\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.116370045\n",
"Normalized Saliency 25th Percentile: Saliency 0.008842\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.045194\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.036352\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": "3f1e0488-f3b6-47f1-e6af-844cc9d5d529"
},
"execution_count": 121,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712633581.3675525\n",
"Tue Apr 9 03:33:01 2024\n"
]
}
]
}
]
}