Datasets
Models
Downloads: 1
1743 lines (1743 with data), 130.6 kB
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"machine_shape": "hm"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"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",
"# 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)"
],
"execution_count": 295,
"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": 296,
"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": "XPBvnB95jg4b",
"outputId": "1cad04a7-a37b-4687-e39b-ad230d763a35",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
}
},
"source": [
"Dense = tf.keras.layers.Dense\n",
"fc_model = tf.keras.Sequential(\n",
" [\n",
" tf.keras.Input(shape=(2,)),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" Dense(1, activation=None)])\n",
"fc_model.summary()"
],
"execution_count": 297,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_50\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_125 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_126 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_127 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 1053697 (4.02 MB)\n",
"Trainable params: 1053697 (4.02 MB)\n",
"Non-trainable params: 0 (0.00 Byte)\n",
"_________________________________________________________________\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "bbKsmK8wIFTp",
"outputId": "12d5f28f-dba4-4d93-da30-aed6b6f84d7b",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
}
},
"source": [
"tn_model = tf.keras.Sequential(\n",
" [\n",
" tf.keras.Input(shape=(2,)),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Here, we replace the dense layer with our MPS.\n",
" TNLayer(),\n",
" TNLayer(),\n",
" TNLayer(),\n",
" TNLayer(),\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 298,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_51\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_128 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_37 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_38 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_39 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_40 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_129 (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(20, 2) + np.array([3, 3]),\n",
" np.random.randn(20, 2) + np.array([-3, -3]),\n",
" np.random.randn(20, 2) + np.array([-3, 3]),\n",
" np.random.randn(20, 2) + np.array([3, -3])])\n",
"\n",
"Y = np.concatenate([np.ones((40)), -np.ones((40))])"
],
"execution_count": 299,
"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": "cafe4e3e-846d-42e8-c0fb-89e7811d005f"
},
"execution_count": 300,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1709522493.5341718\n",
"Mon Mar 4 03:21:33 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "edb52302-faf2-4686-969f-8d95badcdba1",
"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": 301,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"3/3 - 3s - loss: 1.0020 - 3s/epoch - 1s/step\n",
"Epoch 2/300\n",
"3/3 - 0s - loss: 1.0016 - 29ms/epoch - 10ms/step\n",
"Epoch 3/300\n",
"3/3 - 0s - loss: 1.0006 - 30ms/epoch - 10ms/step\n",
"Epoch 4/300\n",
"3/3 - 0s - loss: 1.0002 - 27ms/epoch - 9ms/step\n",
"Epoch 5/300\n",
"3/3 - 0s - loss: 1.0007 - 30ms/epoch - 10ms/step\n",
"Epoch 6/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 7/300\n",
"3/3 - 0s - loss: 1.0004 - 26ms/epoch - 9ms/step\n",
"Epoch 8/300\n",
"3/3 - 0s - loss: 1.0005 - 27ms/epoch - 9ms/step\n",
"Epoch 9/300\n",
"3/3 - 0s - loss: 1.0007 - 30ms/epoch - 10ms/step\n",
"Epoch 10/300\n",
"3/3 - 0s - loss: 1.0007 - 26ms/epoch - 9ms/step\n",
"Epoch 11/300\n",
"3/3 - 0s - loss: 1.0004 - 30ms/epoch - 10ms/step\n",
"Epoch 12/300\n",
"3/3 - 0s - loss: 1.0003 - 31ms/epoch - 10ms/step\n",
"Epoch 13/300\n",
"3/3 - 0s - loss: 1.0004 - 32ms/epoch - 11ms/step\n",
"Epoch 14/300\n",
"3/3 - 0s - loss: 1.0001 - 25ms/epoch - 8ms/step\n",
"Epoch 15/300\n",
"3/3 - 0s - loss: 1.0003 - 29ms/epoch - 10ms/step\n",
"Epoch 16/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 17/300\n",
"3/3 - 0s - loss: 1.0001 - 26ms/epoch - 9ms/step\n",
"Epoch 18/300\n",
"3/3 - 0s - loss: 1.0003 - 32ms/epoch - 11ms/step\n",
"Epoch 19/300\n",
"3/3 - 0s - loss: 1.0002 - 31ms/epoch - 10ms/step\n",
"Epoch 20/300\n",
"3/3 - 0s - loss: 1.0002 - 29ms/epoch - 10ms/step\n",
"Epoch 21/300\n",
"3/3 - 0s - loss: 1.0006 - 31ms/epoch - 10ms/step\n",
"Epoch 22/300\n",
"3/3 - 0s - loss: 1.0004 - 31ms/epoch - 10ms/step\n",
"Epoch 23/300\n",
"3/3 - 0s - loss: 1.0001 - 30ms/epoch - 10ms/step\n",
"Epoch 24/300\n",
"3/3 - 0s - loss: 1.0005 - 31ms/epoch - 10ms/step\n",
"Epoch 25/300\n",
"3/3 - 0s - loss: 1.0002 - 30ms/epoch - 10ms/step\n",
"Epoch 26/300\n",
"3/3 - 0s - loss: 0.9997 - 28ms/epoch - 9ms/step\n",
"Epoch 27/300\n",
"3/3 - 0s - loss: 0.9990 - 25ms/epoch - 8ms/step\n",
"Epoch 28/300\n",
"3/3 - 0s - loss: 0.9962 - 27ms/epoch - 9ms/step\n",
"Epoch 29/300\n",
"3/3 - 0s - loss: 0.9841 - 25ms/epoch - 8ms/step\n",
"Epoch 30/300\n",
"3/3 - 0s - loss: 0.9435 - 28ms/epoch - 9ms/step\n",
"Epoch 31/300\n",
"3/3 - 0s - loss: 0.8032 - 25ms/epoch - 8ms/step\n",
"Epoch 32/300\n",
"3/3 - 0s - loss: 0.4119 - 25ms/epoch - 8ms/step\n",
"Epoch 33/300\n",
"3/3 - 0s - loss: 0.1760 - 23ms/epoch - 8ms/step\n",
"Epoch 34/300\n",
"3/3 - 0s - loss: 0.0817 - 25ms/epoch - 8ms/step\n",
"Epoch 35/300\n",
"3/3 - 0s - loss: 0.0821 - 26ms/epoch - 9ms/step\n",
"Epoch 36/300\n",
"3/3 - 0s - loss: 0.1305 - 25ms/epoch - 8ms/step\n",
"Epoch 37/300\n",
"3/3 - 0s - loss: 0.0902 - 31ms/epoch - 10ms/step\n",
"Epoch 38/300\n",
"3/3 - 0s - loss: 0.0338 - 28ms/epoch - 9ms/step\n",
"Epoch 39/300\n",
"3/3 - 0s - loss: 0.0289 - 24ms/epoch - 8ms/step\n",
"Epoch 40/300\n",
"3/3 - 0s - loss: 0.0300 - 26ms/epoch - 9ms/step\n",
"Epoch 41/300\n",
"3/3 - 0s - loss: 0.0199 - 27ms/epoch - 9ms/step\n",
"Epoch 42/300\n",
"3/3 - 0s - loss: 0.0205 - 25ms/epoch - 8ms/step\n",
"Epoch 43/300\n",
"3/3 - 0s - loss: 0.0170 - 28ms/epoch - 9ms/step\n",
"Epoch 44/300\n",
"3/3 - 0s - loss: 0.0118 - 24ms/epoch - 8ms/step\n",
"Epoch 45/300\n",
"3/3 - 0s - loss: 0.0130 - 24ms/epoch - 8ms/step\n",
"Epoch 46/300\n",
"3/3 - 0s - loss: 0.0119 - 27ms/epoch - 9ms/step\n",
"Epoch 47/300\n",
"3/3 - 0s - loss: 0.0079 - 26ms/epoch - 9ms/step\n",
"Epoch 48/300\n",
"3/3 - 0s - loss: 0.0081 - 22ms/epoch - 7ms/step\n",
"Epoch 49/300\n",
"3/3 - 0s - loss: 0.0084 - 27ms/epoch - 9ms/step\n",
"Epoch 50/300\n",
"3/3 - 0s - loss: 0.0069 - 31ms/epoch - 10ms/step\n",
"Epoch 51/300\n",
"3/3 - 0s - loss: 0.0063 - 34ms/epoch - 11ms/step\n",
"Epoch 52/300\n",
"3/3 - 0s - loss: 0.0065 - 31ms/epoch - 10ms/step\n",
"Epoch 53/300\n",
"3/3 - 0s - loss: 0.0062 - 26ms/epoch - 9ms/step\n",
"Epoch 54/300\n",
"3/3 - 0s - loss: 0.0057 - 29ms/epoch - 10ms/step\n",
"Epoch 55/300\n",
"3/3 - 0s - loss: 0.0053 - 28ms/epoch - 9ms/step\n",
"Epoch 56/300\n",
"3/3 - 0s - loss: 0.0053 - 27ms/epoch - 9ms/step\n",
"Epoch 57/300\n",
"3/3 - 0s - loss: 0.0050 - 29ms/epoch - 10ms/step\n",
"Epoch 58/300\n",
"3/3 - 0s - loss: 0.0049 - 25ms/epoch - 8ms/step\n",
"Epoch 59/300\n",
"3/3 - 0s - loss: 0.0048 - 28ms/epoch - 9ms/step\n",
"Epoch 60/300\n",
"3/3 - 0s - loss: 0.0045 - 26ms/epoch - 9ms/step\n",
"Epoch 61/300\n",
"3/3 - 0s - loss: 0.0044 - 28ms/epoch - 9ms/step\n",
"Epoch 62/300\n",
"3/3 - 0s - loss: 0.0043 - 31ms/epoch - 10ms/step\n",
"Epoch 63/300\n",
"3/3 - 0s - loss: 0.0041 - 32ms/epoch - 11ms/step\n",
"Epoch 64/300\n",
"3/3 - 0s - loss: 0.0039 - 27ms/epoch - 9ms/step\n",
"Epoch 65/300\n",
"3/3 - 0s - loss: 0.0039 - 31ms/epoch - 10ms/step\n",
"Epoch 66/300\n",
"3/3 - 0s - loss: 0.0039 - 26ms/epoch - 9ms/step\n",
"Epoch 67/300\n",
"3/3 - 0s - loss: 0.0037 - 31ms/epoch - 10ms/step\n",
"Epoch 68/300\n",
"3/3 - 0s - loss: 0.0036 - 27ms/epoch - 9ms/step\n",
"Epoch 69/300\n",
"3/3 - 0s - loss: 0.0035 - 29ms/epoch - 10ms/step\n",
"Epoch 70/300\n",
"3/3 - 0s - loss: 0.0034 - 28ms/epoch - 9ms/step\n",
"Epoch 71/300\n",
"3/3 - 0s - loss: 0.0033 - 28ms/epoch - 9ms/step\n",
"Epoch 72/300\n",
"3/3 - 0s - loss: 0.0032 - 28ms/epoch - 9ms/step\n",
"Epoch 73/300\n",
"3/3 - 0s - loss: 0.0031 - 28ms/epoch - 9ms/step\n",
"Epoch 74/300\n",
"3/3 - 0s - loss: 0.0030 - 28ms/epoch - 9ms/step\n",
"Epoch 75/300\n",
"3/3 - 0s - loss: 0.0030 - 27ms/epoch - 9ms/step\n",
"Epoch 76/300\n",
"3/3 - 0s - loss: 0.0029 - 30ms/epoch - 10ms/step\n",
"Epoch 77/300\n",
"3/3 - 0s - loss: 0.0028 - 31ms/epoch - 10ms/step\n",
"Epoch 78/300\n",
"3/3 - 0s - loss: 0.0028 - 29ms/epoch - 10ms/step\n",
"Epoch 79/300\n",
"3/3 - 0s - loss: 0.0027 - 29ms/epoch - 10ms/step\n",
"Epoch 80/300\n",
"3/3 - 0s - loss: 0.0026 - 25ms/epoch - 8ms/step\n",
"Epoch 81/300\n",
"3/3 - 0s - loss: 0.0026 - 27ms/epoch - 9ms/step\n",
"Epoch 82/300\n",
"3/3 - 0s - loss: 0.0025 - 32ms/epoch - 11ms/step\n",
"Epoch 83/300\n",
"3/3 - 0s - loss: 0.0025 - 29ms/epoch - 10ms/step\n",
"Epoch 84/300\n",
"3/3 - 0s - loss: 0.0024 - 28ms/epoch - 9ms/step\n",
"Epoch 85/300\n",
"3/3 - 0s - loss: 0.0023 - 25ms/epoch - 8ms/step\n",
"Epoch 86/300\n",
"3/3 - 0s - loss: 0.0023 - 30ms/epoch - 10ms/step\n",
"Epoch 87/300\n",
"3/3 - 0s - loss: 0.0022 - 30ms/epoch - 10ms/step\n",
"Epoch 88/300\n",
"3/3 - 0s - loss: 0.0022 - 24ms/epoch - 8ms/step\n",
"Epoch 89/300\n",
"3/3 - 0s - loss: 0.0022 - 29ms/epoch - 10ms/step\n",
"Epoch 90/300\n",
"3/3 - 0s - loss: 0.0021 - 26ms/epoch - 9ms/step\n",
"Epoch 91/300\n",
"3/3 - 0s - loss: 0.0020 - 31ms/epoch - 10ms/step\n",
"Epoch 92/300\n",
"3/3 - 0s - loss: 0.0020 - 29ms/epoch - 10ms/step\n",
"Epoch 93/300\n",
"3/3 - 0s - loss: 0.0019 - 30ms/epoch - 10ms/step\n",
"Epoch 94/300\n",
"3/3 - 0s - loss: 0.0019 - 28ms/epoch - 9ms/step\n",
"Epoch 95/300\n",
"3/3 - 0s - loss: 0.0019 - 31ms/epoch - 10ms/step\n",
"Epoch 96/300\n",
"3/3 - 0s - loss: 0.0018 - 34ms/epoch - 11ms/step\n",
"Epoch 97/300\n",
"3/3 - 0s - loss: 0.0018 - 27ms/epoch - 9ms/step\n",
"Epoch 98/300\n",
"3/3 - 0s - loss: 0.0018 - 28ms/epoch - 9ms/step\n",
"Epoch 99/300\n",
"3/3 - 0s - loss: 0.0017 - 27ms/epoch - 9ms/step\n",
"Epoch 100/300\n",
"3/3 - 0s - loss: 0.0017 - 28ms/epoch - 9ms/step\n",
"Epoch 101/300\n",
"3/3 - 0s - loss: 0.0016 - 27ms/epoch - 9ms/step\n",
"Epoch 102/300\n",
"3/3 - 0s - loss: 0.0016 - 30ms/epoch - 10ms/step\n",
"Epoch 103/300\n",
"3/3 - 0s - loss: 0.0016 - 28ms/epoch - 9ms/step\n",
"Epoch 104/300\n",
"3/3 - 0s - loss: 0.0015 - 31ms/epoch - 10ms/step\n",
"Epoch 105/300\n",
"3/3 - 0s - loss: 0.0015 - 28ms/epoch - 9ms/step\n",
"Epoch 106/300\n",
"3/3 - 0s - loss: 0.0015 - 30ms/epoch - 10ms/step\n",
"Epoch 107/300\n",
"3/3 - 0s - loss: 0.0015 - 28ms/epoch - 9ms/step\n",
"Epoch 108/300\n",
"3/3 - 0s - loss: 0.0014 - 29ms/epoch - 10ms/step\n",
"Epoch 109/300\n",
"3/3 - 0s - loss: 0.0014 - 28ms/epoch - 9ms/step\n",
"Epoch 110/300\n",
"3/3 - 0s - loss: 0.0014 - 30ms/epoch - 10ms/step\n",
"Epoch 111/300\n",
"3/3 - 0s - loss: 0.0013 - 32ms/epoch - 11ms/step\n",
"Epoch 112/300\n",
"3/3 - 0s - loss: 0.0013 - 28ms/epoch - 9ms/step\n",
"Epoch 113/300\n",
"3/3 - 0s - loss: 0.0013 - 33ms/epoch - 11ms/step\n",
"Epoch 114/300\n",
"3/3 - 0s - loss: 0.0013 - 30ms/epoch - 10ms/step\n",
"Epoch 115/300\n",
"3/3 - 0s - loss: 0.0013 - 27ms/epoch - 9ms/step\n",
"Epoch 116/300\n",
"3/3 - 0s - loss: 0.0012 - 27ms/epoch - 9ms/step\n",
"Epoch 117/300\n",
"3/3 - 0s - loss: 0.0012 - 32ms/epoch - 11ms/step\n",
"Epoch 118/300\n",
"3/3 - 0s - loss: 0.0012 - 29ms/epoch - 10ms/step\n",
"Epoch 119/300\n",
"3/3 - 0s - loss: 0.0012 - 27ms/epoch - 9ms/step\n",
"Epoch 120/300\n",
"3/3 - 0s - loss: 0.0012 - 31ms/epoch - 10ms/step\n",
"Epoch 121/300\n",
"3/3 - 0s - loss: 0.0011 - 28ms/epoch - 9ms/step\n",
"Epoch 122/300\n",
"3/3 - 0s - loss: 0.0011 - 28ms/epoch - 9ms/step\n",
"Epoch 123/300\n",
"3/3 - 0s - loss: 0.0011 - 30ms/epoch - 10ms/step\n",
"Epoch 124/300\n",
"3/3 - 0s - loss: 0.0011 - 26ms/epoch - 9ms/step\n",
"Epoch 125/300\n",
"3/3 - 0s - loss: 0.0010 - 28ms/epoch - 9ms/step\n",
"Epoch 126/300\n",
"3/3 - 0s - loss: 0.0010 - 27ms/epoch - 9ms/step\n",
"Epoch 127/300\n",
"3/3 - 0s - loss: 0.0010 - 26ms/epoch - 9ms/step\n",
"Epoch 128/300\n",
"3/3 - 0s - loss: 9.7558e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 129/300\n",
"3/3 - 0s - loss: 9.6552e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 130/300\n",
"3/3 - 0s - loss: 9.4969e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 131/300\n",
"3/3 - 0s - loss: 9.2505e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 132/300\n",
"3/3 - 0s - loss: 9.1736e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 133/300\n",
"3/3 - 0s - loss: 8.9746e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 134/300\n",
"3/3 - 0s - loss: 8.7808e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 135/300\n",
"3/3 - 0s - loss: 8.5693e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 136/300\n",
"3/3 - 0s - loss: 8.4714e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 137/300\n",
"3/3 - 0s - loss: 8.2661e-04 - 22ms/epoch - 7ms/step\n",
"Epoch 138/300\n",
"3/3 - 0s - loss: 8.2233e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 139/300\n",
"3/3 - 0s - loss: 8.1117e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 140/300\n",
"3/3 - 0s - loss: 7.8629e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 141/300\n",
"3/3 - 0s - loss: 7.7548e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 142/300\n",
"3/3 - 0s - loss: 7.5872e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 143/300\n",
"3/3 - 0s - loss: 7.4703e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 144/300\n",
"3/3 - 0s - loss: 7.3627e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 145/300\n",
"3/3 - 0s - loss: 7.1389e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 146/300\n",
"3/3 - 0s - loss: 7.2777e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 147/300\n",
"3/3 - 0s - loss: 6.9947e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 148/300\n",
"3/3 - 0s - loss: 6.7761e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 149/300\n",
"3/3 - 0s - loss: 6.9460e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 150/300\n",
"3/3 - 0s - loss: 6.8170e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 151/300\n",
"3/3 - 0s - loss: 6.6609e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 152/300\n",
"3/3 - 0s - loss: 6.4564e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 153/300\n",
"3/3 - 0s - loss: 6.5497e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 154/300\n",
"3/3 - 0s - loss: 6.3180e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 155/300\n",
"3/3 - 0s - loss: 6.2404e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 156/300\n",
"3/3 - 0s - loss: 6.1421e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 157/300\n",
"3/3 - 0s - loss: 6.0606e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 158/300\n",
"3/3 - 0s - loss: 5.7727e-04 - 23ms/epoch - 8ms/step\n",
"Epoch 159/300\n",
"3/3 - 0s - loss: 5.8694e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 160/300\n",
"3/3 - 0s - loss: 5.7493e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 161/300\n",
"3/3 - 0s - loss: 5.5691e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 162/300\n",
"3/3 - 0s - loss: 5.3933e-04 - 23ms/epoch - 8ms/step\n",
"Epoch 163/300\n",
"3/3 - 0s - loss: 5.4575e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 164/300\n",
"3/3 - 0s - loss: 5.3009e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 165/300\n",
"3/3 - 0s - loss: 5.2142e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 166/300\n",
"3/3 - 0s - loss: 5.0512e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 167/300\n",
"3/3 - 0s - loss: 4.9881e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 168/300\n",
"3/3 - 0s - loss: 4.9349e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 169/300\n",
"3/3 - 0s - loss: 4.7837e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 170/300\n",
"3/3 - 0s - loss: 4.7525e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 171/300\n",
"3/3 - 0s - loss: 4.6933e-04 - 32ms/epoch - 11ms/step\n",
"Epoch 172/300\n",
"3/3 - 0s - loss: 4.6028e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 173/300\n",
"3/3 - 0s - loss: 4.5134e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 174/300\n",
"3/3 - 0s - loss: 4.5267e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 175/300\n",
"3/3 - 0s - loss: 4.4015e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 176/300\n",
"3/3 - 0s - loss: 4.4031e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 177/300\n",
"3/3 - 0s - loss: 4.2958e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 178/300\n",
"3/3 - 0s - loss: 4.1322e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 179/300\n",
"3/3 - 0s - loss: 4.0946e-04 - 33ms/epoch - 11ms/step\n",
"Epoch 180/300\n",
"3/3 - 0s - loss: 4.0134e-04 - 33ms/epoch - 11ms/step\n",
"Epoch 181/300\n",
"3/3 - 0s - loss: 3.9690e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 182/300\n",
"3/3 - 0s - loss: 3.9679e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 183/300\n",
"3/3 - 0s - loss: 3.7871e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 184/300\n",
"3/3 - 0s - loss: 3.8270e-04 - 32ms/epoch - 11ms/step\n",
"Epoch 185/300\n",
"3/3 - 0s - loss: 3.7045e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 186/300\n",
"3/3 - 0s - loss: 3.7061e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 187/300\n",
"3/3 - 0s - loss: 3.6014e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 188/300\n",
"3/3 - 0s - loss: 3.5368e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 189/300\n",
"3/3 - 0s - loss: 3.4790e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 190/300\n",
"3/3 - 0s - loss: 3.4964e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 191/300\n",
"3/3 - 0s - loss: 3.4267e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 192/300\n",
"3/3 - 0s - loss: 3.4079e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 193/300\n",
"3/3 - 0s - loss: 3.2477e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 194/300\n",
"3/3 - 0s - loss: 3.1852e-04 - 23ms/epoch - 8ms/step\n",
"Epoch 195/300\n",
"3/3 - 0s - loss: 3.1870e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 196/300\n",
"3/3 - 0s - loss: 3.0855e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 197/300\n",
"3/3 - 0s - loss: 3.0261e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 198/300\n",
"3/3 - 0s - loss: 2.9450e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 199/300\n",
"3/3 - 0s - loss: 3.0393e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 200/300\n",
"3/3 - 0s - loss: 2.8899e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 201/300\n",
"3/3 - 0s - loss: 2.8637e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 202/300\n",
"3/3 - 0s - loss: 2.8096e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 203/300\n",
"3/3 - 0s - loss: 2.7259e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 204/300\n",
"3/3 - 0s - loss: 2.7348e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 205/300\n",
"3/3 - 0s - loss: 2.7290e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 206/300\n",
"3/3 - 0s - loss: 2.7059e-04 - 34ms/epoch - 11ms/step\n",
"Epoch 207/300\n",
"3/3 - 0s - loss: 2.5930e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 208/300\n",
"3/3 - 0s - loss: 2.5812e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 209/300\n",
"3/3 - 0s - loss: 2.4859e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 210/300\n",
"3/3 - 0s - loss: 2.4157e-04 - 23ms/epoch - 8ms/step\n",
"Epoch 211/300\n",
"3/3 - 0s - loss: 2.4757e-04 - 23ms/epoch - 8ms/step\n",
"Epoch 212/300\n",
"3/3 - 0s - loss: 2.4860e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 213/300\n",
"3/3 - 0s - loss: 2.3404e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 214/300\n",
"3/3 - 0s - loss: 2.3344e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 215/300\n",
"3/3 - 0s - loss: 2.2611e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 216/300\n",
"3/3 - 0s - loss: 2.1685e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 217/300\n",
"3/3 - 0s - loss: 2.1758e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 218/300\n",
"3/3 - 0s - loss: 2.1069e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 219/300\n",
"3/3 - 0s - loss: 2.0946e-04 - 32ms/epoch - 11ms/step\n",
"Epoch 220/300\n",
"3/3 - 0s - loss: 2.1095e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 221/300\n",
"3/3 - 0s - loss: 1.9965e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 222/300\n",
"3/3 - 0s - loss: 2.0261e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 223/300\n",
"3/3 - 0s - loss: 1.9557e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 224/300\n",
"3/3 - 0s - loss: 1.9491e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 225/300\n",
"3/3 - 0s - loss: 1.9608e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 226/300\n",
"3/3 - 0s - loss: 1.8280e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 227/300\n",
"3/3 - 0s - loss: 1.8332e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 228/300\n",
"3/3 - 0s - loss: 1.8306e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 229/300\n",
"3/3 - 0s - loss: 1.7550e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 230/300\n",
"3/3 - 0s - loss: 1.7726e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 231/300\n",
"3/3 - 0s - loss: 1.6824e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 232/300\n",
"3/3 - 0s - loss: 1.6622e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 233/300\n",
"3/3 - 0s - loss: 1.6012e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 234/300\n",
"3/3 - 0s - loss: 1.5731e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 235/300\n",
"3/3 - 0s - loss: 1.5926e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 236/300\n",
"3/3 - 0s - loss: 1.4904e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 237/300\n",
"3/3 - 0s - loss: 1.5087e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 238/300\n",
"3/3 - 0s - loss: 1.4742e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 239/300\n",
"3/3 - 0s - loss: 1.4098e-04 - 32ms/epoch - 11ms/step\n",
"Epoch 240/300\n",
"3/3 - 0s - loss: 1.4520e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 241/300\n",
"3/3 - 0s - loss: 1.3536e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 242/300\n",
"3/3 - 0s - loss: 1.4048e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 243/300\n",
"3/3 - 0s - loss: 1.3667e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 244/300\n",
"3/3 - 0s - loss: 1.3354e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 245/300\n",
"3/3 - 0s - loss: 1.3164e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 246/300\n",
"3/3 - 0s - loss: 1.2150e-04 - 34ms/epoch - 11ms/step\n",
"Epoch 247/300\n",
"3/3 - 0s - loss: 1.2769e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 248/300\n",
"3/3 - 0s - loss: 1.1966e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 249/300\n",
"3/3 - 0s - loss: 1.2201e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 250/300\n",
"3/3 - 0s - loss: 1.1840e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 251/300\n",
"3/3 - 0s - loss: 1.1306e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 252/300\n",
"3/3 - 0s - loss: 1.1229e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 253/300\n",
"3/3 - 0s - loss: 1.1240e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 254/300\n",
"3/3 - 0s - loss: 1.0539e-04 - 32ms/epoch - 11ms/step\n",
"Epoch 255/300\n",
"3/3 - 0s - loss: 1.0463e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 256/300\n",
"3/3 - 0s - loss: 9.9430e-05 - 28ms/epoch - 9ms/step\n",
"Epoch 257/300\n",
"3/3 - 0s - loss: 9.9516e-05 - 33ms/epoch - 11ms/step\n",
"Epoch 258/300\n",
"3/3 - 0s - loss: 9.5395e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 259/300\n",
"3/3 - 0s - loss: 9.6994e-05 - 26ms/epoch - 9ms/step\n",
"Epoch 260/300\n",
"3/3 - 0s - loss: 9.6485e-05 - 30ms/epoch - 10ms/step\n",
"Epoch 261/300\n",
"3/3 - 0s - loss: 9.0158e-05 - 31ms/epoch - 10ms/step\n",
"Epoch 262/300\n",
"3/3 - 0s - loss: 8.7597e-05 - 31ms/epoch - 10ms/step\n",
"Epoch 263/300\n",
"3/3 - 0s - loss: 8.6762e-05 - 27ms/epoch - 9ms/step\n",
"Epoch 264/300\n",
"3/3 - 0s - loss: 8.4766e-05 - 29ms/epoch - 10ms/step\n",
"Epoch 265/300\n",
"3/3 - 0s - loss: 8.4577e-05 - 27ms/epoch - 9ms/step\n",
"Epoch 266/300\n",
"3/3 - 0s - loss: 8.0508e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 267/300\n",
"3/3 - 0s - loss: 8.1489e-05 - 24ms/epoch - 8ms/step\n",
"Epoch 268/300\n",
"3/3 - 0s - loss: 7.8976e-05 - 28ms/epoch - 9ms/step\n",
"Epoch 269/300\n",
"3/3 - 0s - loss: 8.1293e-05 - 28ms/epoch - 9ms/step\n",
"Epoch 270/300\n",
"3/3 - 0s - loss: 7.3270e-05 - 27ms/epoch - 9ms/step\n",
"Epoch 271/300\n",
"3/3 - 0s - loss: 7.6427e-05 - 27ms/epoch - 9ms/step\n",
"Epoch 272/300\n",
"3/3 - 0s - loss: 7.3495e-05 - 31ms/epoch - 10ms/step\n",
"Epoch 273/300\n",
"3/3 - 0s - loss: 6.9721e-05 - 26ms/epoch - 9ms/step\n",
"Epoch 274/300\n",
"3/3 - 0s - loss: 7.0466e-05 - 23ms/epoch - 8ms/step\n",
"Epoch 275/300\n",
"3/3 - 0s - loss: 6.7535e-05 - 27ms/epoch - 9ms/step\n",
"Epoch 276/300\n",
"3/3 - 0s - loss: 6.6942e-05 - 29ms/epoch - 10ms/step\n",
"Epoch 277/300\n",
"3/3 - 0s - loss: 6.3328e-05 - 30ms/epoch - 10ms/step\n",
"Epoch 278/300\n",
"3/3 - 0s - loss: 6.3240e-05 - 27ms/epoch - 9ms/step\n",
"Epoch 279/300\n",
"3/3 - 0s - loss: 6.1593e-05 - 23ms/epoch - 8ms/step\n",
"Epoch 280/300\n",
"3/3 - 0s - loss: 6.0376e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 281/300\n",
"3/3 - 0s - loss: 5.9723e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 282/300\n",
"3/3 - 0s - loss: 5.7997e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 283/300\n",
"3/3 - 0s - loss: 5.5533e-05 - 22ms/epoch - 7ms/step\n",
"Epoch 284/300\n",
"3/3 - 0s - loss: 5.5269e-05 - 28ms/epoch - 9ms/step\n",
"Epoch 285/300\n",
"3/3 - 0s - loss: 5.3363e-05 - 24ms/epoch - 8ms/step\n",
"Epoch 286/300\n",
"3/3 - 0s - loss: 5.2167e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 287/300\n",
"3/3 - 0s - loss: 5.1013e-05 - 30ms/epoch - 10ms/step\n",
"Epoch 288/300\n",
"3/3 - 0s - loss: 4.9477e-05 - 27ms/epoch - 9ms/step\n",
"Epoch 289/300\n",
"3/3 - 0s - loss: 4.8851e-05 - 29ms/epoch - 10ms/step\n",
"Epoch 290/300\n",
"3/3 - 0s - loss: 4.7838e-05 - 28ms/epoch - 9ms/step\n",
"Epoch 291/300\n",
"3/3 - 0s - loss: 4.8683e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 292/300\n",
"3/3 - 0s - loss: 4.5610e-05 - 26ms/epoch - 9ms/step\n",
"Epoch 293/300\n",
"3/3 - 0s - loss: 4.4947e-05 - 26ms/epoch - 9ms/step\n",
"Epoch 294/300\n",
"3/3 - 0s - loss: 4.4995e-05 - 27ms/epoch - 9ms/step\n",
"Epoch 295/300\n",
"3/3 - 0s - loss: 4.2466e-05 - 33ms/epoch - 11ms/step\n",
"Epoch 296/300\n",
"3/3 - 0s - loss: 4.2640e-05 - 29ms/epoch - 10ms/step\n",
"Epoch 297/300\n",
"3/3 - 0s - loss: 4.0049e-05 - 24ms/epoch - 8ms/step\n",
"Epoch 298/300\n",
"3/3 - 0s - loss: 4.0360e-05 - 28ms/epoch - 9ms/step\n",
"Epoch 299/300\n",
"3/3 - 0s - loss: 3.9327e-05 - 28ms/epoch - 9ms/step\n",
"Epoch 300/300\n",
"3/3 - 0s - loss: 3.7798e-05 - 24ms/epoch - 8ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7cd650fe1810>"
]
},
"metadata": {},
"execution_count": 301
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "6df73727-0feb-4408-f59a-6be13568b6fb",
"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": 302,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"14/14 [==============================] - 1s 5ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7cd650b32b00>"
]
},
"metadata": {},
"execution_count": 302
},
{
"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": "wfZCzuq9KY9b",
"outputId": "01392988-50b0-4d6b-d1da-305e15eed3d2"
},
"execution_count": 303,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1709522506.7699714\n",
"Mon Mar 4 03:21:46 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": "Ft6S13x6KuEQ",
"outputId": "65505936-3528-4dd8-ec7a-9c069aaf8761"
},
"execution_count": 304,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1709522506.7803874\n",
"Mon Mar 4 03:21:46 2024\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "BMxSJo5gtOmQ"
},
"source": [
"# VS Fully Connected"
]
},
{
"cell_type": "code",
"metadata": {
"id": "NKQx7stYswzU",
"outputId": "0147db4a-ea14-4c85-c244-3ef6f7d57588",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 11458
}
},
"source": [
"fc_model.compile(optimizer=\"adam\", loss=\"mean_squared_error\")\n",
"fc_model.fit(X, Y, epochs=300, verbose=2)\n",
"# 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 = fc_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": 305,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"3/3 - 1s - loss: 0.5656 - 725ms/epoch - 242ms/step\n",
"Epoch 2/300\n",
"3/3 - 0s - loss: 0.1959 - 26ms/epoch - 9ms/step\n",
"Epoch 3/300\n",
"3/3 - 0s - loss: 0.1423 - 35ms/epoch - 12ms/step\n",
"Epoch 4/300\n",
"3/3 - 0s - loss: 0.0917 - 33ms/epoch - 11ms/step\n",
"Epoch 5/300\n",
"3/3 - 0s - loss: 0.0828 - 27ms/epoch - 9ms/step\n",
"Epoch 6/300\n",
"3/3 - 0s - loss: 0.0827 - 35ms/epoch - 12ms/step\n",
"Epoch 7/300\n",
"3/3 - 0s - loss: 0.0680 - 32ms/epoch - 11ms/step\n",
"Epoch 8/300\n",
"3/3 - 0s - loss: 0.0680 - 29ms/epoch - 10ms/step\n",
"Epoch 9/300\n",
"3/3 - 0s - loss: 0.0605 - 30ms/epoch - 10ms/step\n",
"Epoch 10/300\n",
"3/3 - 0s - loss: 0.0632 - 27ms/epoch - 9ms/step\n",
"Epoch 11/300\n",
"3/3 - 0s - loss: 0.0537 - 33ms/epoch - 11ms/step\n",
"Epoch 12/300\n",
"3/3 - 0s - loss: 0.0523 - 37ms/epoch - 12ms/step\n",
"Epoch 13/300\n",
"3/3 - 0s - loss: 0.0522 - 32ms/epoch - 11ms/step\n",
"Epoch 14/300\n",
"3/3 - 0s - loss: 0.0483 - 33ms/epoch - 11ms/step\n",
"Epoch 15/300\n",
"3/3 - 0s - loss: 0.0498 - 31ms/epoch - 10ms/step\n",
"Epoch 16/300\n",
"3/3 - 0s - loss: 0.0444 - 33ms/epoch - 11ms/step\n",
"Epoch 17/300\n",
"3/3 - 0s - loss: 0.0487 - 35ms/epoch - 12ms/step\n",
"Epoch 18/300\n",
"3/3 - 0s - loss: 0.0467 - 37ms/epoch - 12ms/step\n",
"Epoch 19/300\n",
"3/3 - 0s - loss: 0.0419 - 32ms/epoch - 11ms/step\n",
"Epoch 20/300\n",
"3/3 - 0s - loss: 0.0439 - 33ms/epoch - 11ms/step\n",
"Epoch 21/300\n",
"3/3 - 0s - loss: 0.0406 - 28ms/epoch - 9ms/step\n",
"Epoch 22/300\n",
"3/3 - 0s - loss: 0.0414 - 30ms/epoch - 10ms/step\n",
"Epoch 23/300\n",
"3/3 - 0s - loss: 0.0421 - 31ms/epoch - 10ms/step\n",
"Epoch 24/300\n",
"3/3 - 0s - loss: 0.0378 - 32ms/epoch - 11ms/step\n",
"Epoch 25/300\n",
"3/3 - 0s - loss: 0.0382 - 31ms/epoch - 10ms/step\n",
"Epoch 26/300\n",
"3/3 - 0s - loss: 0.0425 - 28ms/epoch - 9ms/step\n",
"Epoch 27/300\n",
"3/3 - 0s - loss: 0.0505 - 33ms/epoch - 11ms/step\n",
"Epoch 28/300\n",
"3/3 - 0s - loss: 0.0423 - 27ms/epoch - 9ms/step\n",
"Epoch 29/300\n",
"3/3 - 0s - loss: 0.0513 - 32ms/epoch - 11ms/step\n",
"Epoch 30/300\n",
"3/3 - 0s - loss: 0.0385 - 28ms/epoch - 9ms/step\n",
"Epoch 31/300\n",
"3/3 - 0s - loss: 0.0392 - 32ms/epoch - 11ms/step\n",
"Epoch 32/300\n",
"3/3 - 0s - loss: 0.0417 - 30ms/epoch - 10ms/step\n",
"Epoch 33/300\n",
"3/3 - 0s - loss: 0.0414 - 29ms/epoch - 10ms/step\n",
"Epoch 34/300\n",
"3/3 - 0s - loss: 0.0374 - 28ms/epoch - 9ms/step\n",
"Epoch 35/300\n",
"3/3 - 0s - loss: 0.0348 - 34ms/epoch - 11ms/step\n",
"Epoch 36/300\n",
"3/3 - 0s - loss: 0.0319 - 30ms/epoch - 10ms/step\n",
"Epoch 37/300\n",
"3/3 - 0s - loss: 0.0429 - 28ms/epoch - 9ms/step\n",
"Epoch 38/300\n",
"3/3 - 0s - loss: 0.0382 - 34ms/epoch - 11ms/step\n",
"Epoch 39/300\n",
"3/3 - 0s - loss: 0.0266 - 31ms/epoch - 10ms/step\n",
"Epoch 40/300\n",
"3/3 - 0s - loss: 0.0399 - 37ms/epoch - 12ms/step\n",
"Epoch 41/300\n",
"3/3 - 0s - loss: 0.0336 - 38ms/epoch - 13ms/step\n",
"Epoch 42/300\n",
"3/3 - 0s - loss: 0.0293 - 38ms/epoch - 13ms/step\n",
"Epoch 43/300\n",
"3/3 - 0s - loss: 0.0304 - 31ms/epoch - 10ms/step\n",
"Epoch 44/300\n",
"3/3 - 0s - loss: 0.0370 - 31ms/epoch - 10ms/step\n",
"Epoch 45/300\n",
"3/3 - 0s - loss: 0.0295 - 36ms/epoch - 12ms/step\n",
"Epoch 46/300\n",
"3/3 - 0s - loss: 0.0278 - 34ms/epoch - 11ms/step\n",
"Epoch 47/300\n",
"3/3 - 0s - loss: 0.0298 - 34ms/epoch - 11ms/step\n",
"Epoch 48/300\n",
"3/3 - 0s - loss: 0.0244 - 36ms/epoch - 12ms/step\n",
"Epoch 49/300\n",
"3/3 - 0s - loss: 0.0270 - 31ms/epoch - 10ms/step\n",
"Epoch 50/300\n",
"3/3 - 0s - loss: 0.0191 - 29ms/epoch - 10ms/step\n",
"Epoch 51/300\n",
"3/3 - 0s - loss: 0.0257 - 31ms/epoch - 10ms/step\n",
"Epoch 52/300\n",
"3/3 - 0s - loss: 0.0229 - 36ms/epoch - 12ms/step\n",
"Epoch 53/300\n",
"3/3 - 0s - loss: 0.0226 - 35ms/epoch - 12ms/step\n",
"Epoch 54/300\n",
"3/3 - 0s - loss: 0.0251 - 39ms/epoch - 13ms/step\n",
"Epoch 55/300\n",
"3/3 - 0s - loss: 0.0231 - 31ms/epoch - 10ms/step\n",
"Epoch 56/300\n",
"3/3 - 0s - loss: 0.0268 - 38ms/epoch - 13ms/step\n",
"Epoch 57/300\n",
"3/3 - 0s - loss: 0.0274 - 31ms/epoch - 10ms/step\n",
"Epoch 58/300\n",
"3/3 - 0s - loss: 0.0182 - 30ms/epoch - 10ms/step\n",
"Epoch 59/300\n",
"3/3 - 0s - loss: 0.0233 - 32ms/epoch - 11ms/step\n",
"Epoch 60/300\n",
"3/3 - 0s - loss: 0.0189 - 32ms/epoch - 11ms/step\n",
"Epoch 61/300\n",
"3/3 - 0s - loss: 0.0133 - 30ms/epoch - 10ms/step\n",
"Epoch 62/300\n",
"3/3 - 0s - loss: 0.0144 - 28ms/epoch - 9ms/step\n",
"Epoch 63/300\n",
"3/3 - 0s - loss: 0.0157 - 25ms/epoch - 8ms/step\n",
"Epoch 64/300\n",
"3/3 - 0s - loss: 0.0119 - 28ms/epoch - 9ms/step\n",
"Epoch 65/300\n",
"3/3 - 0s - loss: 0.0188 - 34ms/epoch - 11ms/step\n",
"Epoch 66/300\n",
"3/3 - 0s - loss: 0.0130 - 28ms/epoch - 9ms/step\n",
"Epoch 67/300\n",
"3/3 - 0s - loss: 0.0116 - 23ms/epoch - 8ms/step\n",
"Epoch 68/300\n",
"3/3 - 0s - loss: 0.0110 - 30ms/epoch - 10ms/step\n",
"Epoch 69/300\n",
"3/3 - 0s - loss: 0.0073 - 29ms/epoch - 10ms/step\n",
"Epoch 70/300\n",
"3/3 - 0s - loss: 0.0097 - 30ms/epoch - 10ms/step\n",
"Epoch 71/300\n",
"3/3 - 0s - loss: 0.0088 - 31ms/epoch - 10ms/step\n",
"Epoch 72/300\n",
"3/3 - 0s - loss: 0.0063 - 28ms/epoch - 9ms/step\n",
"Epoch 73/300\n",
"3/3 - 0s - loss: 0.0058 - 30ms/epoch - 10ms/step\n",
"Epoch 74/300\n",
"3/3 - 0s - loss: 0.0060 - 28ms/epoch - 9ms/step\n",
"Epoch 75/300\n",
"3/3 - 0s - loss: 0.0094 - 31ms/epoch - 10ms/step\n",
"Epoch 76/300\n",
"3/3 - 0s - loss: 0.0106 - 37ms/epoch - 12ms/step\n",
"Epoch 77/300\n",
"3/3 - 0s - loss: 0.0083 - 32ms/epoch - 11ms/step\n",
"Epoch 78/300\n",
"3/3 - 0s - loss: 0.0048 - 30ms/epoch - 10ms/step\n",
"Epoch 79/300\n",
"3/3 - 0s - loss: 0.0048 - 27ms/epoch - 9ms/step\n",
"Epoch 80/300\n",
"3/3 - 0s - loss: 0.0046 - 28ms/epoch - 9ms/step\n",
"Epoch 81/300\n",
"3/3 - 0s - loss: 0.0029 - 26ms/epoch - 9ms/step\n",
"Epoch 82/300\n",
"3/3 - 0s - loss: 0.0026 - 31ms/epoch - 10ms/step\n",
"Epoch 83/300\n",
"3/3 - 0s - loss: 0.0030 - 32ms/epoch - 11ms/step\n",
"Epoch 84/300\n",
"3/3 - 0s - loss: 0.0032 - 28ms/epoch - 9ms/step\n",
"Epoch 85/300\n",
"3/3 - 0s - loss: 0.0040 - 29ms/epoch - 10ms/step\n",
"Epoch 86/300\n",
"3/3 - 0s - loss: 0.0045 - 31ms/epoch - 10ms/step\n",
"Epoch 87/300\n",
"3/3 - 0s - loss: 0.0047 - 35ms/epoch - 12ms/step\n",
"Epoch 88/300\n",
"3/3 - 0s - loss: 0.0033 - 28ms/epoch - 9ms/step\n",
"Epoch 89/300\n",
"3/3 - 0s - loss: 0.0034 - 29ms/epoch - 10ms/step\n",
"Epoch 90/300\n",
"3/3 - 0s - loss: 0.0083 - 33ms/epoch - 11ms/step\n",
"Epoch 91/300\n",
"3/3 - 0s - loss: 0.0109 - 37ms/epoch - 12ms/step\n",
"Epoch 92/300\n",
"3/3 - 0s - loss: 0.0065 - 30ms/epoch - 10ms/step\n",
"Epoch 93/300\n",
"3/3 - 0s - loss: 0.0046 - 35ms/epoch - 12ms/step\n",
"Epoch 94/300\n",
"3/3 - 0s - loss: 0.0068 - 31ms/epoch - 10ms/step\n",
"Epoch 95/300\n",
"3/3 - 0s - loss: 0.0096 - 25ms/epoch - 8ms/step\n",
"Epoch 96/300\n",
"3/3 - 0s - loss: 0.0103 - 30ms/epoch - 10ms/step\n",
"Epoch 97/300\n",
"3/3 - 0s - loss: 0.0119 - 29ms/epoch - 10ms/step\n",
"Epoch 98/300\n",
"3/3 - 0s - loss: 0.0069 - 34ms/epoch - 11ms/step\n",
"Epoch 99/300\n",
"3/3 - 0s - loss: 0.0075 - 26ms/epoch - 9ms/step\n",
"Epoch 100/300\n",
"3/3 - 0s - loss: 0.0057 - 33ms/epoch - 11ms/step\n",
"Epoch 101/300\n",
"3/3 - 0s - loss: 0.0032 - 29ms/epoch - 10ms/step\n",
"Epoch 102/300\n",
"3/3 - 0s - loss: 0.0039 - 27ms/epoch - 9ms/step\n",
"Epoch 103/300\n",
"3/3 - 0s - loss: 0.0029 - 28ms/epoch - 9ms/step\n",
"Epoch 104/300\n",
"3/3 - 0s - loss: 0.0031 - 26ms/epoch - 9ms/step\n",
"Epoch 105/300\n",
"3/3 - 0s - loss: 0.0021 - 30ms/epoch - 10ms/step\n",
"Epoch 106/300\n",
"3/3 - 0s - loss: 0.0015 - 33ms/epoch - 11ms/step\n",
"Epoch 107/300\n",
"3/3 - 0s - loss: 0.0014 - 33ms/epoch - 11ms/step\n",
"Epoch 108/300\n",
"3/3 - 0s - loss: 0.0013 - 34ms/epoch - 11ms/step\n",
"Epoch 109/300\n",
"3/3 - 0s - loss: 0.0022 - 30ms/epoch - 10ms/step\n",
"Epoch 110/300\n",
"3/3 - 0s - loss: 0.0019 - 31ms/epoch - 10ms/step\n",
"Epoch 111/300\n",
"3/3 - 0s - loss: 0.0020 - 32ms/epoch - 11ms/step\n",
"Epoch 112/300\n",
"3/3 - 0s - loss: 6.9314e-04 - 32ms/epoch - 11ms/step\n",
"Epoch 113/300\n",
"3/3 - 0s - loss: 9.3566e-04 - 33ms/epoch - 11ms/step\n",
"Epoch 114/300\n",
"3/3 - 0s - loss: 0.0015 - 30ms/epoch - 10ms/step\n",
"Epoch 115/300\n",
"3/3 - 0s - loss: 0.0017 - 33ms/epoch - 11ms/step\n",
"Epoch 116/300\n",
"3/3 - 0s - loss: 0.0020 - 29ms/epoch - 10ms/step\n",
"Epoch 117/300\n",
"3/3 - 0s - loss: 0.0018 - 30ms/epoch - 10ms/step\n",
"Epoch 118/300\n",
"3/3 - 0s - loss: 0.0010 - 34ms/epoch - 11ms/step\n",
"Epoch 119/300\n",
"3/3 - 0s - loss: 8.8028e-04 - 36ms/epoch - 12ms/step\n",
"Epoch 120/300\n",
"3/3 - 0s - loss: 7.2462e-04 - 34ms/epoch - 11ms/step\n",
"Epoch 121/300\n",
"3/3 - 0s - loss: 8.0890e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 122/300\n",
"3/3 - 0s - loss: 9.8991e-04 - 33ms/epoch - 11ms/step\n",
"Epoch 123/300\n",
"3/3 - 0s - loss: 7.1008e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 124/300\n",
"3/3 - 0s - loss: 4.9597e-04 - 33ms/epoch - 11ms/step\n",
"Epoch 125/300\n",
"3/3 - 0s - loss: 4.7966e-04 - 32ms/epoch - 11ms/step\n",
"Epoch 126/300\n",
"3/3 - 0s - loss: 3.0518e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 127/300\n",
"3/3 - 0s - loss: 2.7030e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 128/300\n",
"3/3 - 0s - loss: 3.4302e-04 - 36ms/epoch - 12ms/step\n",
"Epoch 129/300\n",
"3/3 - 0s - loss: 3.2476e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 130/300\n",
"3/3 - 0s - loss: 1.6305e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 131/300\n",
"3/3 - 0s - loss: 1.8642e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 132/300\n",
"3/3 - 0s - loss: 8.2074e-05 - 30ms/epoch - 10ms/step\n",
"Epoch 133/300\n",
"3/3 - 0s - loss: 6.5955e-05 - 27ms/epoch - 9ms/step\n",
"Epoch 134/300\n",
"3/3 - 0s - loss: 6.8692e-05 - 26ms/epoch - 9ms/step\n",
"Epoch 135/300\n",
"3/3 - 0s - loss: 1.1016e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 136/300\n",
"3/3 - 0s - loss: 1.4056e-04 - 33ms/epoch - 11ms/step\n",
"Epoch 137/300\n",
"3/3 - 0s - loss: 1.0764e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 138/300\n",
"3/3 - 0s - loss: 9.8001e-05 - 30ms/epoch - 10ms/step\n",
"Epoch 139/300\n",
"3/3 - 0s - loss: 2.1907e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 140/300\n",
"3/3 - 0s - loss: 2.4921e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 141/300\n",
"3/3 - 0s - loss: 4.0704e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 142/300\n",
"3/3 - 0s - loss: 5.5095e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 143/300\n",
"3/3 - 0s - loss: 8.7078e-04 - 23ms/epoch - 8ms/step\n",
"Epoch 144/300\n",
"3/3 - 0s - loss: 9.0852e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 145/300\n",
"3/3 - 0s - loss: 0.0014 - 31ms/epoch - 10ms/step\n",
"Epoch 146/300\n",
"3/3 - 0s - loss: 0.0021 - 29ms/epoch - 10ms/step\n",
"Epoch 147/300\n",
"3/3 - 0s - loss: 0.0012 - 30ms/epoch - 10ms/step\n",
"Epoch 148/300\n",
"3/3 - 0s - loss: 0.0011 - 26ms/epoch - 9ms/step\n",
"Epoch 149/300\n",
"3/3 - 0s - loss: 0.0014 - 25ms/epoch - 8ms/step\n",
"Epoch 150/300\n",
"3/3 - 0s - loss: 0.0013 - 29ms/epoch - 10ms/step\n",
"Epoch 151/300\n",
"3/3 - 0s - loss: 0.0012 - 32ms/epoch - 11ms/step\n",
"Epoch 152/300\n",
"3/3 - 0s - loss: 0.0011 - 29ms/epoch - 10ms/step\n",
"Epoch 153/300\n",
"3/3 - 0s - loss: 8.8283e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 154/300\n",
"3/3 - 0s - loss: 5.0875e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 155/300\n",
"3/3 - 0s - loss: 4.6452e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 156/300\n",
"3/3 - 0s - loss: 4.4445e-04 - 32ms/epoch - 11ms/step\n",
"Epoch 157/300\n",
"3/3 - 0s - loss: 4.5507e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 158/300\n",
"3/3 - 0s - loss: 5.0221e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 159/300\n",
"3/3 - 0s - loss: 7.1127e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 160/300\n",
"3/3 - 0s - loss: 5.3585e-04 - 33ms/epoch - 11ms/step\n",
"Epoch 161/300\n",
"3/3 - 0s - loss: 3.0625e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 162/300\n",
"3/3 - 0s - loss: 3.6777e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 163/300\n",
"3/3 - 0s - loss: 2.5530e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 164/300\n",
"3/3 - 0s - loss: 1.7076e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 165/300\n",
"3/3 - 0s - loss: 2.1320e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 166/300\n",
"3/3 - 0s - loss: 2.7991e-04 - 37ms/epoch - 12ms/step\n",
"Epoch 167/300\n",
"3/3 - 0s - loss: 3.3069e-04 - 38ms/epoch - 13ms/step\n",
"Epoch 168/300\n",
"3/3 - 0s - loss: 2.9444e-04 - 34ms/epoch - 11ms/step\n",
"Epoch 169/300\n",
"3/3 - 0s - loss: 4.0663e-04 - 34ms/epoch - 11ms/step\n",
"Epoch 170/300\n",
"3/3 - 0s - loss: 3.3016e-04 - 33ms/epoch - 11ms/step\n",
"Epoch 171/300\n",
"3/3 - 0s - loss: 2.0864e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 172/300\n",
"3/3 - 0s - loss: 3.1231e-04 - 35ms/epoch - 12ms/step\n",
"Epoch 173/300\n",
"3/3 - 0s - loss: 2.9278e-04 - 34ms/epoch - 11ms/step\n",
"Epoch 174/300\n",
"3/3 - 0s - loss: 3.0427e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 175/300\n",
"3/3 - 0s - loss: 4.5326e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 176/300\n",
"3/3 - 0s - loss: 3.3629e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 177/300\n",
"3/3 - 0s - loss: 2.4525e-04 - 32ms/epoch - 11ms/step\n",
"Epoch 178/300\n",
"3/3 - 0s - loss: 2.5538e-04 - 34ms/epoch - 11ms/step\n",
"Epoch 179/300\n",
"3/3 - 0s - loss: 3.3784e-04 - 35ms/epoch - 12ms/step\n",
"Epoch 180/300\n",
"3/3 - 0s - loss: 1.9497e-04 - 33ms/epoch - 11ms/step\n",
"Epoch 181/300\n",
"3/3 - 0s - loss: 1.9737e-04 - 43ms/epoch - 14ms/step\n",
"Epoch 182/300\n",
"3/3 - 0s - loss: 2.2758e-04 - 34ms/epoch - 11ms/step\n",
"Epoch 183/300\n",
"3/3 - 0s - loss: 2.9136e-04 - 36ms/epoch - 12ms/step\n",
"Epoch 184/300\n",
"3/3 - 0s - loss: 1.1060e-04 - 32ms/epoch - 11ms/step\n",
"Epoch 185/300\n",
"3/3 - 0s - loss: 5.0481e-05 - 33ms/epoch - 11ms/step\n",
"Epoch 186/300\n",
"3/3 - 0s - loss: 4.0821e-05 - 31ms/epoch - 10ms/step\n",
"Epoch 187/300\n",
"3/3 - 0s - loss: 5.7687e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 188/300\n",
"3/3 - 0s - loss: 5.1819e-05 - 36ms/epoch - 12ms/step\n",
"Epoch 189/300\n",
"3/3 - 0s - loss: 4.4923e-05 - 35ms/epoch - 12ms/step\n",
"Epoch 190/300\n",
"3/3 - 0s - loss: 5.0681e-05 - 31ms/epoch - 10ms/step\n",
"Epoch 191/300\n",
"3/3 - 0s - loss: 3.9062e-05 - 30ms/epoch - 10ms/step\n",
"Epoch 192/300\n",
"3/3 - 0s - loss: 3.1511e-05 - 32ms/epoch - 11ms/step\n",
"Epoch 193/300\n",
"3/3 - 0s - loss: 3.9896e-05 - 35ms/epoch - 12ms/step\n",
"Epoch 194/300\n",
"3/3 - 0s - loss: 3.6009e-05 - 32ms/epoch - 11ms/step\n",
"Epoch 195/300\n",
"3/3 - 0s - loss: 3.8435e-05 - 35ms/epoch - 12ms/step\n",
"Epoch 196/300\n",
"3/3 - 0s - loss: 6.6916e-05 - 31ms/epoch - 10ms/step\n",
"Epoch 197/300\n",
"3/3 - 0s - loss: 1.2784e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 198/300\n",
"3/3 - 0s - loss: 8.5005e-05 - 29ms/epoch - 10ms/step\n",
"Epoch 199/300\n",
"3/3 - 0s - loss: 6.0588e-05 - 30ms/epoch - 10ms/step\n",
"Epoch 200/300\n",
"3/3 - 0s - loss: 6.8180e-05 - 29ms/epoch - 10ms/step\n",
"Epoch 201/300\n",
"3/3 - 0s - loss: 4.7230e-05 - 32ms/epoch - 11ms/step\n",
"Epoch 202/300\n",
"3/3 - 0s - loss: 3.8133e-05 - 29ms/epoch - 10ms/step\n",
"Epoch 203/300\n",
"3/3 - 0s - loss: 7.4671e-05 - 26ms/epoch - 9ms/step\n",
"Epoch 204/300\n",
"3/3 - 0s - loss: 8.1094e-05 - 32ms/epoch - 11ms/step\n",
"Epoch 205/300\n",
"3/3 - 0s - loss: 7.8872e-05 - 30ms/epoch - 10ms/step\n",
"Epoch 206/300\n",
"3/3 - 0s - loss: 8.7357e-05 - 31ms/epoch - 10ms/step\n",
"Epoch 207/300\n",
"3/3 - 0s - loss: 4.8380e-05 - 31ms/epoch - 10ms/step\n",
"Epoch 208/300\n",
"3/3 - 0s - loss: 7.0697e-05 - 29ms/epoch - 10ms/step\n",
"Epoch 209/300\n",
"3/3 - 0s - loss: 5.2098e-05 - 33ms/epoch - 11ms/step\n",
"Epoch 210/300\n",
"3/3 - 0s - loss: 5.4029e-05 - 28ms/epoch - 9ms/step\n",
"Epoch 211/300\n",
"3/3 - 0s - loss: 2.8489e-05 - 28ms/epoch - 9ms/step\n",
"Epoch 212/300\n",
"3/3 - 0s - loss: 3.3961e-05 - 31ms/epoch - 10ms/step\n",
"Epoch 213/300\n",
"3/3 - 0s - loss: 4.1667e-05 - 29ms/epoch - 10ms/step\n",
"Epoch 214/300\n",
"3/3 - 0s - loss: 3.7597e-05 - 30ms/epoch - 10ms/step\n",
"Epoch 215/300\n",
"3/3 - 0s - loss: 2.7004e-05 - 33ms/epoch - 11ms/step\n",
"Epoch 216/300\n",
"3/3 - 0s - loss: 2.9110e-05 - 34ms/epoch - 11ms/step\n",
"Epoch 217/300\n",
"3/3 - 0s - loss: 3.6687e-05 - 34ms/epoch - 11ms/step\n",
"Epoch 218/300\n",
"3/3 - 0s - loss: 7.2615e-05 - 32ms/epoch - 11ms/step\n",
"Epoch 219/300\n",
"3/3 - 0s - loss: 1.0681e-04 - 23ms/epoch - 8ms/step\n",
"Epoch 220/300\n",
"3/3 - 0s - loss: 1.9565e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 221/300\n",
"3/3 - 0s - loss: 1.9595e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 222/300\n",
"3/3 - 0s - loss: 1.7055e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 223/300\n",
"3/3 - 0s - loss: 1.4371e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 224/300\n",
"3/3 - 0s - loss: 1.0054e-04 - 33ms/epoch - 11ms/step\n",
"Epoch 225/300\n",
"3/3 - 0s - loss: 7.8233e-05 - 32ms/epoch - 11ms/step\n",
"Epoch 226/300\n",
"3/3 - 0s - loss: 2.0859e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 227/300\n",
"3/3 - 0s - loss: 2.3248e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 228/300\n",
"3/3 - 0s - loss: 3.5742e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 229/300\n",
"3/3 - 0s - loss: 3.2267e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 230/300\n",
"3/3 - 0s - loss: 2.6533e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 231/300\n",
"3/3 - 0s - loss: 3.3579e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 232/300\n",
"3/3 - 0s - loss: 2.2141e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 233/300\n",
"3/3 - 0s - loss: 1.3816e-04 - 32ms/epoch - 11ms/step\n",
"Epoch 234/300\n",
"3/3 - 0s - loss: 1.2997e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 235/300\n",
"3/3 - 0s - loss: 1.2696e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 236/300\n",
"3/3 - 0s - loss: 7.3166e-05 - 34ms/epoch - 11ms/step\n",
"Epoch 237/300\n",
"3/3 - 0s - loss: 4.9531e-05 - 26ms/epoch - 9ms/step\n",
"Epoch 238/300\n",
"3/3 - 0s - loss: 5.9576e-05 - 31ms/epoch - 10ms/step\n",
"Epoch 239/300\n",
"3/3 - 0s - loss: 6.9014e-05 - 26ms/epoch - 9ms/step\n",
"Epoch 240/300\n",
"3/3 - 0s - loss: 1.2079e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 241/300\n",
"3/3 - 0s - loss: 1.0165e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 242/300\n",
"3/3 - 0s - loss: 1.1189e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 243/300\n",
"3/3 - 0s - loss: 1.2715e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 244/300\n",
"3/3 - 0s - loss: 2.3746e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 245/300\n",
"3/3 - 0s - loss: 7.2393e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 246/300\n",
"3/3 - 0s - loss: 8.1162e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 247/300\n",
"3/3 - 0s - loss: 6.6941e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 248/300\n",
"3/3 - 0s - loss: 6.1267e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 249/300\n",
"3/3 - 0s - loss: 5.4795e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 250/300\n",
"3/3 - 0s - loss: 8.4581e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 251/300\n",
"3/3 - 0s - loss: 4.3189e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 252/300\n",
"3/3 - 0s - loss: 6.3720e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 253/300\n",
"3/3 - 0s - loss: 8.4664e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 254/300\n",
"3/3 - 0s - loss: 0.0025 - 28ms/epoch - 9ms/step\n",
"Epoch 255/300\n",
"3/3 - 0s - loss: 0.0032 - 25ms/epoch - 8ms/step\n",
"Epoch 256/300\n",
"3/3 - 0s - loss: 0.0040 - 29ms/epoch - 10ms/step\n",
"Epoch 257/300\n",
"3/3 - 0s - loss: 0.0021 - 29ms/epoch - 10ms/step\n",
"Epoch 258/300\n",
"3/3 - 0s - loss: 0.0023 - 32ms/epoch - 11ms/step\n",
"Epoch 259/300\n",
"3/3 - 0s - loss: 0.0034 - 30ms/epoch - 10ms/step\n",
"Epoch 260/300\n",
"3/3 - 0s - loss: 0.0045 - 31ms/epoch - 10ms/step\n",
"Epoch 261/300\n",
"3/3 - 0s - loss: 0.0064 - 32ms/epoch - 11ms/step\n",
"Epoch 262/300\n",
"3/3 - 0s - loss: 0.0050 - 28ms/epoch - 9ms/step\n",
"Epoch 263/300\n",
"3/3 - 0s - loss: 0.0068 - 32ms/epoch - 11ms/step\n",
"Epoch 264/300\n",
"3/3 - 0s - loss: 0.0042 - 39ms/epoch - 13ms/step\n",
"Epoch 265/300\n",
"3/3 - 0s - loss: 0.0047 - 38ms/epoch - 13ms/step\n",
"Epoch 266/300\n",
"3/3 - 0s - loss: 0.0045 - 33ms/epoch - 11ms/step\n",
"Epoch 267/300\n",
"3/3 - 0s - loss: 0.0046 - 31ms/epoch - 10ms/step\n",
"Epoch 268/300\n",
"3/3 - 0s - loss: 0.0032 - 28ms/epoch - 9ms/step\n",
"Epoch 269/300\n",
"3/3 - 0s - loss: 0.0031 - 33ms/epoch - 11ms/step\n",
"Epoch 270/300\n",
"3/3 - 0s - loss: 0.0041 - 36ms/epoch - 12ms/step\n",
"Epoch 271/300\n",
"3/3 - 0s - loss: 0.0034 - 33ms/epoch - 11ms/step\n",
"Epoch 272/300\n",
"3/3 - 0s - loss: 0.0043 - 34ms/epoch - 11ms/step\n",
"Epoch 273/300\n",
"3/3 - 0s - loss: 0.0034 - 30ms/epoch - 10ms/step\n",
"Epoch 274/300\n",
"3/3 - 0s - loss: 0.0036 - 26ms/epoch - 9ms/step\n",
"Epoch 275/300\n",
"3/3 - 0s - loss: 0.0030 - 32ms/epoch - 11ms/step\n",
"Epoch 276/300\n",
"3/3 - 0s - loss: 0.0027 - 31ms/epoch - 10ms/step\n",
"Epoch 277/300\n",
"3/3 - 0s - loss: 0.0033 - 27ms/epoch - 9ms/step\n",
"Epoch 278/300\n",
"3/3 - 0s - loss: 0.0024 - 27ms/epoch - 9ms/step\n",
"Epoch 279/300\n",
"3/3 - 0s - loss: 0.0017 - 31ms/epoch - 10ms/step\n",
"Epoch 280/300\n",
"3/3 - 0s - loss: 0.0017 - 29ms/epoch - 10ms/step\n",
"Epoch 281/300\n",
"3/3 - 0s - loss: 0.0015 - 29ms/epoch - 10ms/step\n",
"Epoch 282/300\n",
"3/3 - 0s - loss: 0.0015 - 29ms/epoch - 10ms/step\n",
"Epoch 283/300\n",
"3/3 - 0s - loss: 0.0019 - 30ms/epoch - 10ms/step\n",
"Epoch 284/300\n",
"3/3 - 0s - loss: 0.0042 - 33ms/epoch - 11ms/step\n",
"Epoch 285/300\n",
"3/3 - 0s - loss: 0.0026 - 37ms/epoch - 12ms/step\n",
"Epoch 286/300\n",
"3/3 - 0s - loss: 0.0035 - 32ms/epoch - 11ms/step\n",
"Epoch 287/300\n",
"3/3 - 0s - loss: 0.0033 - 32ms/epoch - 11ms/step\n",
"Epoch 288/300\n",
"3/3 - 0s - loss: 0.0059 - 30ms/epoch - 10ms/step\n",
"Epoch 289/300\n",
"3/3 - 0s - loss: 0.0073 - 31ms/epoch - 10ms/step\n",
"Epoch 290/300\n",
"3/3 - 0s - loss: 0.0060 - 31ms/epoch - 10ms/step\n",
"Epoch 291/300\n",
"3/3 - 0s - loss: 0.0032 - 31ms/epoch - 10ms/step\n",
"Epoch 292/300\n",
"3/3 - 0s - loss: 0.0022 - 30ms/epoch - 10ms/step\n",
"Epoch 293/300\n",
"3/3 - 0s - loss: 0.0021 - 31ms/epoch - 10ms/step\n",
"Epoch 294/300\n",
"3/3 - 0s - loss: 0.0025 - 35ms/epoch - 12ms/step\n",
"Epoch 295/300\n",
"3/3 - 0s - loss: 0.0011 - 27ms/epoch - 9ms/step\n",
"Epoch 296/300\n",
"3/3 - 0s - loss: 6.3007e-04 - 32ms/epoch - 11ms/step\n",
"Epoch 297/300\n",
"3/3 - 0s - loss: 4.8764e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 298/300\n",
"3/3 - 0s - loss: 5.1926e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 299/300\n",
"3/3 - 0s - loss: 7.6698e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 300/300\n",
"3/3 - 0s - loss: 7.6851e-04 - 32ms/epoch - 11ms/step\n",
"14/14 [==============================] - 0s 4ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7cd6507df970>"
]
},
"metadata": {},
"execution_count": 305
},
{
"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": "YyOarWssKyjN",
"outputId": "207d8779-fa07-4d1f-d1fa-524625cff163"
},
"execution_count": 306,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1709522518.0176697\n",
"Mon Mar 4 03:21:58 2024\n"
]
}
]
}
]
}