Datasets
Models
Downloads: 1
1266 lines (1266 with data), 216.7 kB
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"machine_shape": "hm",
"gpuType": "V28"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "TPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "8XnVMPBXmtRa"
},
"source": [
"# TensorNetworks in Neural Networks.\n",
"\n",
"Here, we have a small toy example of how to use a TN inside of a fully connected neural network.\n",
"\n",
"First off, let's install tensornetwork"
]
},
{
"cell_type": "code",
"metadata": {
"id": "7HGRsYNAFxME"
},
"source": [
"# !pip install tensornetwork\n",
"\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import tensorflow as tf\n",
"# Import tensornetwork\n",
"import tensornetwork as tn\n",
"import random\n",
"import time\n",
"import pandas as pd\n",
"# Set the backend to tesorflow\n",
"# (default is numpy)\n",
"tn.set_default_backend(\"tensorflow\")\n",
"np.random.seed(42)\n",
"random.seed(42)\n",
"tf.random.set_seed(42)\n",
"# Explainability code assistance aided by ChatGPT3.5\n",
"# 2021 Kelly, D. TensorFlow Explainable AI tutorial https://www.youtube.com/watch?v=6xePkn3-LME"
],
"execution_count": 24,
"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": 25,
"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": "d9891261-1a5e-4cc2-ab4c-9f744eabeda0",
"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",
" TNLayer(),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 26,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_2\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_6 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_7 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_8 (Dense) (None, 1024) 1049600 \n",
" \n",
" tn_layer_2 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_9 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 2108417 (8.04 MB)\n",
"Trainable params: 2108417 (8.04 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": 27,
"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": "31fbd286-886a-41ea-8863-439c74ef88f9"
},
"execution_count": 28,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712557645.1784976\n",
"Mon Apr 8 06:27:25 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "f80adc02-369e-4102-f57f-d091e4a6e647",
"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": 29,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 0.4596 - 1s/epoch - 76ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.0900 - 161ms/epoch - 11ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.0593 - 161ms/epoch - 11ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0423 - 163ms/epoch - 11ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0356 - 155ms/epoch - 10ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0284 - 153ms/epoch - 10ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0241 - 149ms/epoch - 10ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0216 - 142ms/epoch - 9ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0160 - 146ms/epoch - 10ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0126 - 145ms/epoch - 10ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0142 - 142ms/epoch - 9ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0074 - 143ms/epoch - 10ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0031 - 138ms/epoch - 9ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0028 - 146ms/epoch - 10ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0025 - 142ms/epoch - 9ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0012 - 145ms/epoch - 10ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0021 - 146ms/epoch - 10ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 5.7101e-04 - 145ms/epoch - 10ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 8.0478e-04 - 142ms/epoch - 9ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0017 - 142ms/epoch - 9ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 1.4051e-04 - 152ms/epoch - 10ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 6.5652e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 6.1823e-05 - 141ms/epoch - 9ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 4.7350e-05 - 148ms/epoch - 10ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 3.7021e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 2.2576e-05 - 153ms/epoch - 10ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 1.7399e-05 - 151ms/epoch - 10ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 1.6915e-05 - 149ms/epoch - 10ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 1.4393e-05 - 145ms/epoch - 10ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 1.2778e-05 - 145ms/epoch - 10ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 9.0015e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 9.0063e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 8.0883e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 6.7527e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 7.4034e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 5.3656e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 4.7119e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 4.7796e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 5.4243e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 4.3804e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 1.3105e-05 - 141ms/epoch - 9ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 1.1770e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 2.9930e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 1.4131e-05 - 138ms/epoch - 9ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 3.3383e-05 - 140ms/epoch - 9ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 2.4509e-05 - 139ms/epoch - 9ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 3.3651e-05 - 139ms/epoch - 9ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 2.7146e-05 - 148ms/epoch - 10ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 3.3193e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 3.7846e-05 - 138ms/epoch - 9ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 1.8471e-05 - 137ms/epoch - 9ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 7.0395e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 4.5873e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 2.9096e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 1.8879e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 1.4077e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 2.4659e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 2.3153e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 2.7334e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 5.2755e-06 - 152ms/epoch - 10ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 6.8501e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 5.0631e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 1.4713e-04 - 142ms/epoch - 9ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 2.9938e-04 - 142ms/epoch - 9ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 1.0652e-04 - 137ms/epoch - 9ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 7.3446e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 1.8029e-04 - 140ms/epoch - 9ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 3.1908e-04 - 138ms/epoch - 9ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 2.3859e-04 - 142ms/epoch - 9ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 1.4657e-04 - 143ms/epoch - 10ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 7.2866e-05 - 141ms/epoch - 9ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 4.5639e-05 - 137ms/epoch - 9ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 1.6219e-05 - 140ms/epoch - 9ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 2.5756e-05 - 144ms/epoch - 10ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 3.6999e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 2.6855e-05 - 142ms/epoch - 9ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 8.5367e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 4.2186e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 3.5389e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 4.5152e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 8.1309e-06 - 154ms/epoch - 10ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 4.5184e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 1.2660e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 1.2903e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 1.5172e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 1.0556e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 5.5194e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 4.9113e-07 - 143ms/epoch - 10ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 4.1162e-07 - 151ms/epoch - 10ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 6.6641e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 1.6898e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 3.4867e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 1.5160e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 4.2673e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 1.8946e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 1.7528e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 2.2586e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 1.6487e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 2.3663e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 5.8775e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 5.0285e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 6.0507e-07 - 145ms/epoch - 10ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 4.4688e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 4.5072e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 6.6730e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 5.7912e-07 - 143ms/epoch - 10ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 2.4674e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 5.2798e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 5.0092e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 1.4810e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 2.1483e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 2.3617e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 2.9863e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 3.7696e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 9.1047e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 5.2968e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 4.4978e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 2.2756e-06 - 147ms/epoch - 10ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 3.2244e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 1.4069e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 2.4956e-06 - 148ms/epoch - 10ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 7.8208e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 7.2930e-05 - 147ms/epoch - 10ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 7.5156e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 1.5827e-04 - 144ms/epoch - 10ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 8.1541e-05 - 148ms/epoch - 10ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 1.1598e-04 - 142ms/epoch - 9ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 3.0179e-04 - 148ms/epoch - 10ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 1.4994e-04 - 139ms/epoch - 9ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 2.0718e-04 - 151ms/epoch - 10ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 1.6426e-04 - 150ms/epoch - 10ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 1.7565e-04 - 143ms/epoch - 10ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 6.0723e-04 - 141ms/epoch - 9ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 0.0010 - 140ms/epoch - 9ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 0.0224 - 142ms/epoch - 9ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 0.0204 - 143ms/epoch - 10ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 0.0771 - 142ms/epoch - 9ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 0.0191 - 147ms/epoch - 10ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 0.0079 - 139ms/epoch - 9ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 0.0015 - 152ms/epoch - 10ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 6.2062e-04 - 145ms/epoch - 10ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 0.0018 - 137ms/epoch - 9ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 0.0107 - 143ms/epoch - 10ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 0.0013 - 141ms/epoch - 9ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 0.0058 - 140ms/epoch - 9ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 0.0011 - 141ms/epoch - 9ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 4.5834e-04 - 138ms/epoch - 9ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 9.4040e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 3.7628e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 2.4223e-05 - 140ms/epoch - 9ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 2.4311e-05 - 141ms/epoch - 9ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 3.1346e-04 - 137ms/epoch - 9ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 4.6921e-04 - 139ms/epoch - 9ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 0.0011 - 143ms/epoch - 10ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 0.0017 - 139ms/epoch - 9ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 9.8783e-04 - 139ms/epoch - 9ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 2.6252e-04 - 138ms/epoch - 9ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 9.2279e-05 - 135ms/epoch - 9ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 2.6364e-05 - 140ms/epoch - 9ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 2.1225e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 1.0382e-05 - 139ms/epoch - 9ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 6.0338e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 5.0824e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 4.5271e-06 - 146ms/epoch - 10ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 3.2592e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 2.8089e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 2.3096e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 2.1345e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 1.8826e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 1.6172e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 1.4956e-06 - 141ms/epoch - 9ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 1.6851e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 2.0563e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 1.9804e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 2.1727e-06 - 135ms/epoch - 9ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 1.9076e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 1.1727e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 8.3909e-07 - 144ms/epoch - 10ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 9.0962e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 7.1694e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 7.2677e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 6.1015e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 6.0704e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 5.7970e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 5.3282e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 8.3602e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 1.1133e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 9.3223e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 7.1232e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 8.5941e-07 - 147ms/epoch - 10ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 7.5460e-07 - 133ms/epoch - 9ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 4.4763e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 4.9094e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 5.7433e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 3.8595e-07 - 145ms/epoch - 10ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 3.5951e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 3.1175e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 2.7243e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 2.7250e-07 - 143ms/epoch - 10ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 2.7385e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 3.1850e-07 - 146ms/epoch - 10ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 3.7277e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 3.4504e-07 - 143ms/epoch - 10ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 2.7649e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 2.6075e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 2.5181e-07 - 131ms/epoch - 9ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 1.9769e-07 - 131ms/epoch - 9ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 3.3854e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 4.2555e-07 - 131ms/epoch - 9ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 5.2804e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 4.9708e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 7.8789e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 1.1664e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 1.1443e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 4.8366e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 5.3166e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 4.7738e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 5.6335e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 4.6916e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 2.4280e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 1.7683e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 1.9707e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 1.4286e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 1.9430e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 5.3178e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 2.4770e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 4.3158e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 2.8119e-06 - 150ms/epoch - 10ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 5.5019e-06 - 132ms/epoch - 9ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 1.3437e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 7.2669e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 1.6040e-06 - 138ms/epoch - 9ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 3.9313e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 2.2018e-06 - 137ms/epoch - 9ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 1.7076e-06 - 136ms/epoch - 9ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 1.4083e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 3.4460e-06 - 139ms/epoch - 9ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 1.7740e-05 - 140ms/epoch - 9ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 1.7413e-04 - 141ms/epoch - 9ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 5.1958e-04 - 139ms/epoch - 9ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 0.0011 - 136ms/epoch - 9ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 4.7786e-04 - 139ms/epoch - 9ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 2.5757e-04 - 141ms/epoch - 9ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 1.1262e-04 - 139ms/epoch - 9ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 5.2177e-05 - 138ms/epoch - 9ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 1.8057e-05 - 143ms/epoch - 10ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 7.3675e-06 - 133ms/epoch - 9ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 4.3644e-06 - 144ms/epoch - 10ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 4.6340e-06 - 143ms/epoch - 10ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 2.2899e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 1.1734e-06 - 140ms/epoch - 9ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 7.9005e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 9.2919e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 1.1421e-06 - 146ms/epoch - 10ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 7.8003e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 6.5824e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 8.7615e-07 - 144ms/epoch - 10ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 2.0486e-06 - 145ms/epoch - 10ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 1.1591e-06 - 142ms/epoch - 9ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 5.0865e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 3.3701e-07 - 143ms/epoch - 10ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 3.8552e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 2.8410e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 2.6901e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 5.4019e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 3.6835e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 1.8413e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 1.8903e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 2.5259e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 2.3102e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 1.4415e-07 - 137ms/epoch - 9ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 1.6178e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 2.5782e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 2.6849e-07 - 139ms/epoch - 9ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 1.3731e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 1.3111e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 1.0946e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 1.1098e-07 - 147ms/epoch - 10ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 1.1533e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 1.1140e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 9.3388e-08 - 137ms/epoch - 9ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 9.9449e-08 - 137ms/epoch - 9ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 1.2577e-07 - 142ms/epoch - 9ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 1.1881e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 1.2302e-07 - 134ms/epoch - 9ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 1.9124e-07 - 136ms/epoch - 9ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 1.3167e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 8.8856e-08 - 136ms/epoch - 9ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 1.2490e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 2.0714e-07 - 135ms/epoch - 9ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 8.3097e-08 - 136ms/epoch - 9ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 2.2303e-07 - 141ms/epoch - 9ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 1.2463e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 1.7163e-07 - 138ms/epoch - 9ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 2.5927e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 1.1516e-07 - 140ms/epoch - 9ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 7.9806e-08 - 144ms/epoch - 10ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 8.4468e-08 - 147ms/epoch - 10ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 5.5845e-08 - 136ms/epoch - 9ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 6.0022e-08 - 138ms/epoch - 9ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x791a7c285450>"
]
},
"metadata": {},
"execution_count": 29
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "adc10289-7555-45c0-d2ca-d7d4e4ee4268",
"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": 30,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 4ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x791a8b9918d0>"
]
},
"metadata": {},
"execution_count": 30
},
{
"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": "59e24ff6-276a-422f-8699-2a52ab734f9f"
},
"execution_count": 31,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712557689.924187\n",
"Mon Apr 8 06:28:09 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": "f7179a4e-60ca-4528-bb09-5e8eb4ed8abe"
},
"execution_count": 32,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712557689.9296703\n",
"Mon Apr 8 06:28:09 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": "0c37ce75-5f5b-4797-e5d9-a0cab383194a"
},
"execution_count": 33,
"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",
"377 0.542108\n",
"370 0.413502\n",
"327 0.324662\n",
"239 0.100158\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 0.007584\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.00123\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.000107\n",
"1 0.000161\n",
"2 0.000163\n",
"3 0.000302\n",
"4 0.000371\n",
"5 0.000617\n",
"6 0.000653\n",
"7 0.001035\n",
"8 0.001060\n",
"9 0.001229\n",
"10 0.001837\n",
"Normalized Saliency Sum: Saliency 3.640355\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.057376\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 13.655527\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 209.406281\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.003292\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 756.537598\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000439\n",
"1 0.001141\n",
"2 0.001245\n",
"3 0.004247\n",
"4 0.004410\n",
".. ...\n",
"475 3.624543\n",
"476 3.637910\n",
"477 3.639095\n",
"478 3.639982\n",
"479 3.640354\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 9.151120e-07\n",
"1 2.377406e-06\n",
"2 2.593042e-06\n",
"3 8.848824e-06\n",
"4 9.188099e-06\n",
".. ...\n",
"475 7.551131e-03\n",
"476 7.578979e-03\n",
"477 7.581448e-03\n",
"478 7.583297e-03\n",
"479 7.584070e-03\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.057816148\n",
"Normalized Saliency 25th Percentile: Saliency 0.000746\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.002193\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.001448\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": "e2be7142-98fe-411a-fd4e-02e43bf2dd2d"
},
"execution_count": 34,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712557691.511843\n",
"Mon Apr 8 06:28:11 2024\n"
]
}
]
}
]
}