Datasets
Models
Downloads: 1
1263 lines (1263 with data), 217.2 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": 112,
"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": 113,
"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": "ed355a09-dd85-4a11-bd9f-87e7094b9044",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
}
},
"source": [
"Dense = tf.keras.layers.Dense\n",
"tn_model = tf.keras.Sequential(\n",
" [\n",
" tf.keras.Input(shape=(2,)),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Start Modified Layers\n",
" TNLayer(),\n",
" TNLayer(),\n",
" TNLayer(),\n",
" TNLayer(),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 114,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_9\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_24 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_24 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_25 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_26 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_27 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_25 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 24577 (96.00 KB)\n",
"Trainable params: 24577 (96.00 KB)\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": 115,
"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": "85650c4f-07c0-4215-b51e-40a790d57ff7"
},
"execution_count": 116,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712552342.897352\n",
"Mon Apr 8 04:59:02 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "f6349ce6-e54a-4f2f-b77f-fbeacaed0711",
"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": 117,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 2s - loss: 1.0023 - 2s/epoch - 122ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 1.0001 - 91ms/epoch - 6ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 1.0005 - 88ms/epoch - 6ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 1.0004 - 92ms/epoch - 6ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 1.0003 - 90ms/epoch - 6ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 1.0003 - 90ms/epoch - 6ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 1.0004 - 85ms/epoch - 6ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.9974 - 82ms/epoch - 5ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.4429 - 83ms/epoch - 6ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0625 - 81ms/epoch - 5ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0234 - 82ms/epoch - 5ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0092 - 82ms/epoch - 5ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0068 - 79ms/epoch - 5ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0053 - 80ms/epoch - 5ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0043 - 80ms/epoch - 5ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0037 - 83ms/epoch - 6ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0031 - 82ms/epoch - 5ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0026 - 83ms/epoch - 6ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0023 - 81ms/epoch - 5ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0020 - 81ms/epoch - 5ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 0.0017 - 80ms/epoch - 5ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 0.0015 - 80ms/epoch - 5ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 0.0011 - 80ms/epoch - 5ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 0.0012 - 83ms/epoch - 6ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 0.0015 - 82ms/epoch - 5ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 7.0450e-04 - 81ms/epoch - 5ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 9.1766e-04 - 81ms/epoch - 5ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 4.1546e-04 - 82ms/epoch - 5ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 3.0934e-04 - 82ms/epoch - 5ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 2.0369e-04 - 81ms/epoch - 5ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 1.5018e-04 - 82ms/epoch - 5ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 1.1558e-04 - 82ms/epoch - 5ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 8.8176e-05 - 78ms/epoch - 5ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 5.6936e-05 - 81ms/epoch - 5ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 3.7160e-05 - 83ms/epoch - 6ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 2.6037e-05 - 83ms/epoch - 6ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 1.9247e-05 - 84ms/epoch - 6ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 1.3705e-05 - 82ms/epoch - 5ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 1.0664e-05 - 79ms/epoch - 5ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 7.8889e-06 - 82ms/epoch - 5ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 5.5915e-06 - 84ms/epoch - 6ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 4.6318e-06 - 86ms/epoch - 6ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 3.6520e-06 - 80ms/epoch - 5ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 3.1932e-06 - 82ms/epoch - 5ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 2.4692e-06 - 82ms/epoch - 5ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 2.2238e-06 - 83ms/epoch - 6ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 1.8553e-06 - 83ms/epoch - 6ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 1.6105e-06 - 85ms/epoch - 6ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 1.5849e-06 - 81ms/epoch - 5ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 1.2703e-06 - 84ms/epoch - 6ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 1.2136e-06 - 81ms/epoch - 5ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 1.2484e-06 - 82ms/epoch - 5ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 9.5818e-07 - 82ms/epoch - 5ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 9.3466e-07 - 80ms/epoch - 5ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 8.7745e-07 - 85ms/epoch - 6ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 7.9988e-07 - 80ms/epoch - 5ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 6.9264e-07 - 84ms/epoch - 6ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 7.0913e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 6.0713e-07 - 81ms/epoch - 5ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 5.6198e-07 - 80ms/epoch - 5ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 5.3677e-07 - 80ms/epoch - 5ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 5.1303e-07 - 82ms/epoch - 5ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 4.9514e-07 - 82ms/epoch - 5ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 4.6032e-07 - 81ms/epoch - 5ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 4.1981e-07 - 83ms/epoch - 6ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 4.0167e-07 - 81ms/epoch - 5ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 4.4213e-07 - 82ms/epoch - 5ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 4.0864e-07 - 78ms/epoch - 5ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 3.2905e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 3.2923e-07 - 81ms/epoch - 5ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 3.2367e-07 - 80ms/epoch - 5ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 3.7152e-07 - 83ms/epoch - 6ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 3.9542e-07 - 82ms/epoch - 5ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 2.8547e-07 - 80ms/epoch - 5ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 2.5947e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 2.6818e-07 - 82ms/epoch - 5ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 2.5150e-07 - 84ms/epoch - 6ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 2.2458e-07 - 84ms/epoch - 6ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 2.3941e-07 - 86ms/epoch - 6ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 2.1686e-07 - 80ms/epoch - 5ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 2.0006e-07 - 76ms/epoch - 5ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 2.2165e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 1.9540e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 1.9383e-07 - 82ms/epoch - 5ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 1.6780e-07 - 78ms/epoch - 5ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 1.7891e-07 - 81ms/epoch - 5ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 1.4455e-07 - 80ms/epoch - 5ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 1.4312e-07 - 81ms/epoch - 5ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 1.3741e-07 - 83ms/epoch - 6ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 1.4256e-07 - 82ms/epoch - 5ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 1.4384e-07 - 81ms/epoch - 5ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 1.5084e-07 - 82ms/epoch - 5ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 1.7159e-07 - 83ms/epoch - 6ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 1.8747e-07 - 78ms/epoch - 5ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 1.4050e-07 - 85ms/epoch - 6ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 1.2748e-07 - 83ms/epoch - 6ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 1.0618e-07 - 80ms/epoch - 5ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 9.5334e-08 - 83ms/epoch - 6ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 9.9949e-08 - 78ms/epoch - 5ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 1.0011e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 1.1610e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 8.8411e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 8.8899e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 1.0584e-07 - 81ms/epoch - 5ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 1.0151e-07 - 81ms/epoch - 5ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 7.9297e-08 - 83ms/epoch - 6ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 8.6043e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 7.7374e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 7.0073e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 6.7736e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 6.9635e-08 - 77ms/epoch - 5ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 6.8498e-08 - 83ms/epoch - 6ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 7.6980e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 7.9861e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 7.9624e-08 - 84ms/epoch - 6ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 5.8298e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 7.1730e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 7.6578e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 6.2245e-08 - 77ms/epoch - 5ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 6.8476e-08 - 77ms/epoch - 5ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 7.0325e-08 - 84ms/epoch - 6ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 9.4982e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 6.9053e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 4.7322e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 4.9496e-08 - 83ms/epoch - 6ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 5.4143e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 7.0646e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 6.6119e-08 - 76ms/epoch - 5ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 4.5644e-08 - 74ms/epoch - 5ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 5.1707e-08 - 83ms/epoch - 6ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 6.4311e-08 - 78ms/epoch - 5ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 4.7626e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 5.5205e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 4.1580e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 4.3228e-08 - 78ms/epoch - 5ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 4.1294e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 5.6828e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 4.9107e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 4.9520e-08 - 78ms/epoch - 5ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 6.4712e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 6.0934e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 5.7863e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 3.6919e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 3.9416e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 3.6595e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 3.3184e-08 - 78ms/epoch - 5ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 3.1759e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 3.6447e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 2.8699e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 4.3291e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 5.1986e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 5.5157e-08 - 77ms/epoch - 5ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 3.6466e-08 - 76ms/epoch - 5ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 2.8317e-08 - 76ms/epoch - 5ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 2.7270e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 3.9941e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 3.9469e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 2.5646e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 4.0869e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 4.5544e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 2.3503e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 2.7303e-08 - 78ms/epoch - 5ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 2.4988e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 1.8176e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 2.0288e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 3.8430e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 3.4578e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 1.9074e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 2.4827e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 2.6616e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 2.2846e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 2.1199e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 4.7579e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 8.3255e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 5.0756e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 5.4033e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 2.0528e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 1.9469e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 8.1006e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 2.3062e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 1.6355e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 2.3190e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 5.3269e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 2.5803e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 3.6270e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 1.7121e-08 - 83ms/epoch - 6ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 2.0334e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 3.9499e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 2.5330e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 5.8988e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 5.9025e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 3.9299e-08 - 82ms/epoch - 5ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 1.9420e-08 - 76ms/epoch - 5ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 1.9973e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 2.8395e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 1.4813e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 1.9806e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 1.9818e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 1.7352e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 2.7630e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 1.7630e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 5.2531e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 2.6860e-07 - 77ms/epoch - 5ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 2.0178e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 3.5091e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 5.1028e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 2.8756e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 6.5668e-08 - 83ms/epoch - 6ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 6.6639e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 2.8417e-08 - 78ms/epoch - 5ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 1.2078e-07 - 78ms/epoch - 5ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 1.9274e-07 - 80ms/epoch - 5ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 1.3398e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 1.3052e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 2.9878e-06 - 79ms/epoch - 5ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 2.1111e-05 - 77ms/epoch - 5ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 3.5600e-05 - 78ms/epoch - 5ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 2.9252e-05 - 79ms/epoch - 5ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 4.1608e-06 - 80ms/epoch - 5ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 1.0514e-06 - 82ms/epoch - 5ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 1.6997e-07 - 76ms/epoch - 5ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 4.7819e-08 - 83ms/epoch - 6ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 3.8990e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 3.9120e-08 - 77ms/epoch - 5ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.5999e-07 - 78ms/epoch - 5ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 2.8020e-07 - 78ms/epoch - 5ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 2.9802e-07 - 75ms/epoch - 5ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 6.4092e-07 - 77ms/epoch - 5ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 3.3013e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 1.0623e-07 - 78ms/epoch - 5ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 3.7146e-08 - 81ms/epoch - 5ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 2.5384e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 2.1562e-08 - 76ms/epoch - 5ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 1.8133e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 2.5202e-08 - 78ms/epoch - 5ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 2.5245e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 3.6754e-08 - 75ms/epoch - 5ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 6.0783e-08 - 79ms/epoch - 5ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 2.8932e-08 - 76ms/epoch - 5ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 1.5447e-08 - 74ms/epoch - 5ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 1.2878e-08 - 76ms/epoch - 5ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 1.8558e-08 - 80ms/epoch - 5ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 5.5826e-08 - 77ms/epoch - 5ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 1.0892e-07 - 80ms/epoch - 5ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 4.0216e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 5.8055e-07 - 82ms/epoch - 5ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 8.0538e-07 - 83ms/epoch - 6ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 5.6357e-07 - 82ms/epoch - 5ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 6.8374e-08 - 84ms/epoch - 6ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 2.2411e-07 - 81ms/epoch - 5ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 1.9596e-06 - 77ms/epoch - 5ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 1.2029e-06 - 76ms/epoch - 5ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 8.3382e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 6.8643e-07 - 73ms/epoch - 5ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 4.7310e-07 - 74ms/epoch - 5ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 2.2977e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 5.5573e-07 - 74ms/epoch - 5ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 3.7477e-07 - 80ms/epoch - 5ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 8.7104e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 3.8224e-07 - 81ms/epoch - 5ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 7.6775e-07 - 79ms/epoch - 5ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 5.7607e-07 - 81ms/epoch - 5ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 5.4436e-07 - 84ms/epoch - 6ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 3.3816e-07 - 83ms/epoch - 6ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 6.7341e-07 - 83ms/epoch - 6ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 7.1618e-07 - 82ms/epoch - 5ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 2.4733e-06 - 83ms/epoch - 6ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 1.4974e-05 - 83ms/epoch - 6ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 1.3281e-04 - 86ms/epoch - 6ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 3.2570e-05 - 86ms/epoch - 6ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 3.1326e-05 - 77ms/epoch - 5ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 1.0913e-05 - 71ms/epoch - 5ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 3.4005e-06 - 71ms/epoch - 5ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 2.5370e-06 - 69ms/epoch - 5ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 2.0095e-05 - 74ms/epoch - 5ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 3.7085e-05 - 72ms/epoch - 5ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 1.7602e-05 - 70ms/epoch - 5ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 3.6483e-06 - 73ms/epoch - 5ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 1.2294e-06 - 75ms/epoch - 5ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 4.0860e-07 - 76ms/epoch - 5ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 1.5341e-07 - 77ms/epoch - 5ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 7.5417e-08 - 77ms/epoch - 5ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 4.9809e-08 - 74ms/epoch - 5ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 5.5516e-08 - 77ms/epoch - 5ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 1.2391e-07 - 75ms/epoch - 5ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 1.7403e-07 - 75ms/epoch - 5ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 1.1984e-07 - 74ms/epoch - 5ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 1.6888e-07 - 73ms/epoch - 5ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 2.2621e-07 - 75ms/epoch - 5ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 5.2946e-07 - 76ms/epoch - 5ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 7.8615e-07 - 76ms/epoch - 5ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 4.7022e-07 - 76ms/epoch - 5ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 2.8115e-06 - 73ms/epoch - 5ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 4.2802e-06 - 70ms/epoch - 5ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 3.8310e-06 - 68ms/epoch - 5ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 6.0209e-07 - 67ms/epoch - 4ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 1.1753e-06 - 68ms/epoch - 5ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 6.7159e-07 - 69ms/epoch - 5ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 4.5403e-06 - 71ms/epoch - 5ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 4.6579e-06 - 73ms/epoch - 5ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7ce244117d00>"
]
},
"metadata": {},
"execution_count": 117
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "c9c92937-208a-4273-b681-0f4db5137bf4",
"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": 118,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 1s 4ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7ce4ac08d4e0>"
]
},
"metadata": {},
"execution_count": 118
},
{
"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": "3d74cbd7-6a3b-4c6d-800f-c3bca63acd32"
},
"execution_count": 119,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712552370.0450635\n",
"Mon Apr 8 04:59:30 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": "3ba45ee1-ecf0-49c8-b4bb-f4a755739623"
},
"execution_count": 120,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712552370.050427\n",
"Mon Apr 8 04:59:30 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": "419a5ab1-6ad5-4a69-bc18-39298f99486f"
},
"execution_count": 121,
"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",
"37 1.000000\n",
"327 0.788523\n",
"239 0.256525\n",
"377 0.250029\n",
"370 0.212747\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 0.006721\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.001185\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.000263\n",
"1 0.001046\n",
"2 0.001047\n",
"3 0.001396\n",
"4 0.001918\n",
"Normalized Saliency Sum: Saliency 3.225892\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.060893\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 13.894728\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 205.504089\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.003708\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 906.061768\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.001926\n",
"1 0.002209\n",
"2 0.003142\n",
"3 0.003565\n",
"4 0.005477\n",
".. ...\n",
"475 3.221718\n",
"476 3.224924\n",
"477 3.225128\n",
"478 3.225525\n",
"479 3.225891\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000004\n",
"1 0.000005\n",
"2 0.000007\n",
"3 0.000007\n",
"4 0.000011\n",
".. ...\n",
"475 0.006712\n",
"476 0.006719\n",
"477 0.006719\n",
"478 0.006720\n",
"479 0.006721\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.061199527\n",
"Normalized Saliency 25th Percentile: Saliency 0.00056\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.001903\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.001343\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": "b48008ae-8822-4b41-89bf-ca2cfa6cdc58"
},
"execution_count": 122,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712552371.726914\n",
"Mon Apr 8 04:59:31 2024\n"
]
}
]
}
]
}