Datasets
Models
Downloads: 1
1749 lines (1749 with data), 131.6 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": 38,
"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": 39,
"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": "5f691219-ec64-4c70-86e7-ab47fd67ab33",
"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": 40,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_6\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_15 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_16 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_17 (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": "3a08b760-85ba-4c51-ea5a-1b26d89a4179",
"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",
" TNLayer(),\n",
" TNLayer(),\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 41,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_7\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_18 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_16 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_17 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_18 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_19 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_20 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_21 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_19 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 34817 (136.00 KB)\n",
"Trainable params: 34817 (136.00 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": 42,
"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": "edf43350-1423-4b33-81ec-ef615fdf2ea1"
},
"execution_count": 43,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1710189536.5157213\n",
"Mon Mar 11 20:38:56 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "7a4981e9-49db-4d34-c76c-a9a5ca0ccf6c",
"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": 44,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"3/3 - 4s - loss: 1.0020 - 4s/epoch - 1s/step\n",
"Epoch 2/300\n",
"3/3 - 0s - loss: 1.0016 - 31ms/epoch - 10ms/step\n",
"Epoch 3/300\n",
"3/3 - 0s - loss: 1.0006 - 29ms/epoch - 10ms/step\n",
"Epoch 4/300\n",
"3/3 - 0s - loss: 1.0002 - 29ms/epoch - 10ms/step\n",
"Epoch 5/300\n",
"3/3 - 0s - loss: 1.0006 - 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: 1.0003 - 28ms/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: 1.0006 - 29ms/epoch - 10ms/step\n",
"Epoch 10/300\n",
"3/3 - 0s - loss: 1.0006 - 27ms/epoch - 9ms/step\n",
"Epoch 11/300\n",
"3/3 - 0s - loss: 1.0004 - 29ms/epoch - 10ms/step\n",
"Epoch 12/300\n",
"3/3 - 0s - loss: 1.0003 - 29ms/epoch - 10ms/step\n",
"Epoch 13/300\n",
"3/3 - 0s - loss: 1.0004 - 29ms/epoch - 10ms/step\n",
"Epoch 14/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 15/300\n",
"3/3 - 0s - loss: 1.0003 - 28ms/epoch - 9ms/step\n",
"Epoch 16/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 17/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 18/300\n",
"3/3 - 0s - loss: 1.0003 - 28ms/epoch - 9ms/step\n",
"Epoch 19/300\n",
"3/3 - 0s - loss: 1.0002 - 27ms/epoch - 9ms/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: 1.0005 - 27ms/epoch - 9ms/step\n",
"Epoch 22/300\n",
"3/3 - 0s - loss: 1.0003 - 32ms/epoch - 11ms/step\n",
"Epoch 23/300\n",
"3/3 - 0s - loss: 1.0001 - 31ms/epoch - 10ms/step\n",
"Epoch 24/300\n",
"3/3 - 0s - loss: 1.0005 - 29ms/epoch - 10ms/step\n",
"Epoch 25/300\n",
"3/3 - 0s - loss: 1.0003 - 27ms/epoch - 9ms/step\n",
"Epoch 26/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 27/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 28/300\n",
"3/3 - 0s - loss: 1.0002 - 29ms/epoch - 10ms/step\n",
"Epoch 29/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 30/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 31/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 32/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 33/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 34/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 35/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 36/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 37/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 38/300\n",
"3/3 - 0s - loss: 1.0001 - 26ms/epoch - 9ms/step\n",
"Epoch 39/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 40/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 41/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 42/300\n",
"3/3 - 0s - loss: 1.0006 - 29ms/epoch - 10ms/step\n",
"Epoch 43/300\n",
"3/3 - 0s - loss: 1.0001 - 30ms/epoch - 10ms/step\n",
"Epoch 44/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 45/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 46/300\n",
"3/3 - 0s - loss: 1.0001 - 26ms/epoch - 9ms/step\n",
"Epoch 47/300\n",
"3/3 - 0s - loss: 1.0006 - 28ms/epoch - 9ms/step\n",
"Epoch 48/300\n",
"3/3 - 0s - loss: 1.0005 - 27ms/epoch - 9ms/step\n",
"Epoch 49/300\n",
"3/3 - 0s - loss: 1.0002 - 27ms/epoch - 9ms/step\n",
"Epoch 50/300\n",
"3/3 - 0s - loss: 1.0002 - 29ms/epoch - 10ms/step\n",
"Epoch 51/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 52/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 53/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 54/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 55/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 56/300\n",
"3/3 - 0s - loss: 1.0002 - 27ms/epoch - 9ms/step\n",
"Epoch 57/300\n",
"3/3 - 0s - loss: 1.0002 - 27ms/epoch - 9ms/step\n",
"Epoch 58/300\n",
"3/3 - 0s - loss: 1.0004 - 27ms/epoch - 9ms/step\n",
"Epoch 59/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 60/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 61/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 62/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 63/300\n",
"3/3 - 0s - loss: 0.9999 - 28ms/epoch - 9ms/step\n",
"Epoch 64/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 65/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 66/300\n",
"3/3 - 0s - loss: 1.0005 - 29ms/epoch - 10ms/step\n",
"Epoch 67/300\n",
"3/3 - 0s - loss: 1.0003 - 28ms/epoch - 9ms/step\n",
"Epoch 68/300\n",
"3/3 - 0s - loss: 1.0007 - 27ms/epoch - 9ms/step\n",
"Epoch 69/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 70/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 71/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 72/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 73/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 74/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 75/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 76/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 77/300\n",
"3/3 - 0s - loss: 1.0001 - 26ms/epoch - 9ms/step\n",
"Epoch 78/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 79/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 80/300\n",
"3/3 - 0s - loss: 1.0008 - 29ms/epoch - 10ms/step\n",
"Epoch 81/300\n",
"3/3 - 0s - loss: 1.0000 - 31ms/epoch - 10ms/step\n",
"Epoch 82/300\n",
"3/3 - 0s - loss: 1.0005 - 29ms/epoch - 10ms/step\n",
"Epoch 83/300\n",
"3/3 - 0s - loss: 1.0003 - 26ms/epoch - 9ms/step\n",
"Epoch 84/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 85/300\n",
"3/3 - 0s - loss: 1.0002 - 26ms/epoch - 9ms/step\n",
"Epoch 86/300\n",
"3/3 - 0s - loss: 1.0007 - 26ms/epoch - 9ms/step\n",
"Epoch 87/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 88/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 89/300\n",
"3/3 - 0s - loss: 1.0003 - 29ms/epoch - 10ms/step\n",
"Epoch 90/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 91/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 92/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 93/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 94/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 95/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 96/300\n",
"3/3 - 0s - loss: 1.0003 - 27ms/epoch - 9ms/step\n",
"Epoch 97/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 98/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 99/300\n",
"3/3 - 0s - loss: 1.0005 - 29ms/epoch - 10ms/step\n",
"Epoch 100/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 101/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 102/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 103/300\n",
"3/3 - 0s - loss: 1.0000 - 26ms/epoch - 9ms/step\n",
"Epoch 104/300\n",
"3/3 - 0s - loss: 1.0003 - 28ms/epoch - 9ms/step\n",
"Epoch 105/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 106/300\n",
"3/3 - 0s - loss: 1.0001 - 26ms/epoch - 9ms/step\n",
"Epoch 107/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 108/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 109/300\n",
"3/3 - 0s - loss: 1.0001 - 31ms/epoch - 10ms/step\n",
"Epoch 110/300\n",
"3/3 - 0s - loss: 1.0000 - 30ms/epoch - 10ms/step\n",
"Epoch 111/300\n",
"3/3 - 0s - loss: 1.0005 - 30ms/epoch - 10ms/step\n",
"Epoch 112/300\n",
"3/3 - 0s - loss: 1.0002 - 32ms/epoch - 11ms/step\n",
"Epoch 113/300\n",
"3/3 - 0s - loss: 1.0000 - 31ms/epoch - 10ms/step\n",
"Epoch 114/300\n",
"3/3 - 0s - loss: 1.0007 - 32ms/epoch - 11ms/step\n",
"Epoch 115/300\n",
"3/3 - 0s - loss: 1.0001 - 30ms/epoch - 10ms/step\n",
"Epoch 116/300\n",
"3/3 - 0s - loss: 1.0000 - 30ms/epoch - 10ms/step\n",
"Epoch 117/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 118/300\n",
"3/3 - 0s - loss: 1.0001 - 30ms/epoch - 10ms/step\n",
"Epoch 119/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 120/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 121/300\n",
"3/3 - 0s - loss: 1.0001 - 31ms/epoch - 10ms/step\n",
"Epoch 122/300\n",
"3/3 - 0s - loss: 1.0002 - 29ms/epoch - 10ms/step\n",
"Epoch 123/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 124/300\n",
"3/3 - 0s - loss: 1.0002 - 30ms/epoch - 10ms/step\n",
"Epoch 125/300\n",
"3/3 - 0s - loss: 1.0000 - 30ms/epoch - 10ms/step\n",
"Epoch 126/300\n",
"3/3 - 0s - loss: 1.0002 - 31ms/epoch - 10ms/step\n",
"Epoch 127/300\n",
"3/3 - 0s - loss: 1.0002 - 29ms/epoch - 10ms/step\n",
"Epoch 128/300\n",
"3/3 - 0s - loss: 1.0003 - 29ms/epoch - 10ms/step\n",
"Epoch 129/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 130/300\n",
"3/3 - 0s - loss: 1.0002 - 29ms/epoch - 10ms/step\n",
"Epoch 131/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 132/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 133/300\n",
"3/3 - 0s - loss: 1.0003 - 29ms/epoch - 10ms/step\n",
"Epoch 134/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 135/300\n",
"3/3 - 0s - loss: 1.0002 - 29ms/epoch - 10ms/step\n",
"Epoch 136/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 137/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 138/300\n",
"3/3 - 0s - loss: 1.0001 - 30ms/epoch - 10ms/step\n",
"Epoch 139/300\n",
"3/3 - 0s - loss: 1.0001 - 30ms/epoch - 10ms/step\n",
"Epoch 140/300\n",
"3/3 - 0s - loss: 1.0001 - 31ms/epoch - 10ms/step\n",
"Epoch 141/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 142/300\n",
"3/3 - 0s - loss: 1.0001 - 30ms/epoch - 10ms/step\n",
"Epoch 143/300\n",
"3/3 - 0s - loss: 1.0002 - 32ms/epoch - 11ms/step\n",
"Epoch 144/300\n",
"3/3 - 0s - loss: 1.0000 - 33ms/epoch - 11ms/step\n",
"Epoch 145/300\n",
"3/3 - 0s - loss: 1.0000 - 30ms/epoch - 10ms/step\n",
"Epoch 146/300\n",
"3/3 - 0s - loss: 0.9999 - 30ms/epoch - 10ms/step\n",
"Epoch 147/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 148/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 149/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 150/300\n",
"3/3 - 0s - loss: 1.0002 - 30ms/epoch - 10ms/step\n",
"Epoch 151/300\n",
"3/3 - 0s - loss: 1.0002 - 32ms/epoch - 11ms/step\n",
"Epoch 152/300\n",
"3/3 - 0s - loss: 1.0002 - 29ms/epoch - 10ms/step\n",
"Epoch 153/300\n",
"3/3 - 0s - loss: 1.0001 - 33ms/epoch - 11ms/step\n",
"Epoch 154/300\n",
"3/3 - 0s - loss: 1.0001 - 30ms/epoch - 10ms/step\n",
"Epoch 155/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 156/300\n",
"3/3 - 0s - loss: 1.0001 - 30ms/epoch - 10ms/step\n",
"Epoch 157/300\n",
"3/3 - 0s - loss: 1.0001 - 33ms/epoch - 11ms/step\n",
"Epoch 158/300\n",
"3/3 - 0s - loss: 1.0000 - 31ms/epoch - 10ms/step\n",
"Epoch 159/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 160/300\n",
"3/3 - 0s - loss: 1.0000 - 25ms/epoch - 8ms/step\n",
"Epoch 161/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 162/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 163/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 164/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 165/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 166/300\n",
"3/3 - 0s - loss: 1.0000 - 26ms/epoch - 9ms/step\n",
"Epoch 167/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 168/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 169/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 170/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 171/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 172/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 173/300\n",
"3/3 - 0s - loss: 1.0001 - 26ms/epoch - 9ms/step\n",
"Epoch 174/300\n",
"3/3 - 0s - loss: 1.0002 - 31ms/epoch - 10ms/step\n",
"Epoch 175/300\n",
"3/3 - 0s - loss: 1.0002 - 30ms/epoch - 10ms/step\n",
"Epoch 176/300\n",
"3/3 - 0s - loss: 1.0001 - 31ms/epoch - 10ms/step\n",
"Epoch 177/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 178/300\n",
"3/3 - 0s - loss: 1.0003 - 30ms/epoch - 10ms/step\n",
"Epoch 179/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 180/300\n",
"3/3 - 0s - loss: 1.0002 - 27ms/epoch - 9ms/step\n",
"Epoch 181/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 182/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 183/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 184/300\n",
"3/3 - 0s - loss: 1.0000 - 30ms/epoch - 10ms/step\n",
"Epoch 185/300\n",
"3/3 - 0s - loss: 1.0002 - 29ms/epoch - 10ms/step\n",
"Epoch 186/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 187/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 188/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 189/300\n",
"3/3 - 0s - loss: 1.0001 - 24ms/epoch - 8ms/step\n",
"Epoch 190/300\n",
"3/3 - 0s - loss: 1.0000 - 25ms/epoch - 8ms/step\n",
"Epoch 191/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 192/300\n",
"3/3 - 0s - loss: 1.0000 - 26ms/epoch - 9ms/step\n",
"Epoch 193/300\n",
"3/3 - 0s - loss: 1.0001 - 26ms/epoch - 9ms/step\n",
"Epoch 194/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 195/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 196/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 197/300\n",
"3/3 - 0s - loss: 0.9999 - 27ms/epoch - 9ms/step\n",
"Epoch 198/300\n",
"3/3 - 0s - loss: 0.9999 - 28ms/epoch - 9ms/step\n",
"Epoch 199/300\n",
"3/3 - 0s - loss: 1.0004 - 29ms/epoch - 10ms/step\n",
"Epoch 200/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 201/300\n",
"3/3 - 0s - loss: 1.0002 - 30ms/epoch - 10ms/step\n",
"Epoch 202/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 203/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 204/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 205/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 206/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 207/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 208/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 209/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 210/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 211/300\n",
"3/3 - 0s - loss: 1.0003 - 26ms/epoch - 9ms/step\n",
"Epoch 212/300\n",
"3/3 - 0s - loss: 1.0000 - 25ms/epoch - 8ms/step\n",
"Epoch 213/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 214/300\n",
"3/3 - 0s - loss: 1.0000 - 31ms/epoch - 10ms/step\n",
"Epoch 215/300\n",
"3/3 - 0s - loss: 1.0000 - 30ms/epoch - 10ms/step\n",
"Epoch 216/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 217/300\n",
"3/3 - 0s - loss: 1.0002 - 27ms/epoch - 9ms/step\n",
"Epoch 218/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 219/300\n",
"3/3 - 0s - loss: 1.0000 - 30ms/epoch - 10ms/step\n",
"Epoch 220/300\n",
"3/3 - 0s - loss: 1.0001 - 30ms/epoch - 10ms/step\n",
"Epoch 221/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 222/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 223/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 224/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 225/300\n",
"3/3 - 0s - loss: 1.0002 - 27ms/epoch - 9ms/step\n",
"Epoch 226/300\n",
"3/3 - 0s - loss: 1.0002 - 29ms/epoch - 10ms/step\n",
"Epoch 227/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 228/300\n",
"3/3 - 0s - loss: 1.0001 - 31ms/epoch - 10ms/step\n",
"Epoch 229/300\n",
"3/3 - 0s - loss: 1.0002 - 26ms/epoch - 9ms/step\n",
"Epoch 230/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 231/300\n",
"3/3 - 0s - loss: 1.0002 - 26ms/epoch - 9ms/step\n",
"Epoch 232/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 233/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 234/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 235/300\n",
"3/3 - 0s - loss: 1.0003 - 29ms/epoch - 10ms/step\n",
"Epoch 236/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 237/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 238/300\n",
"3/3 - 0s - loss: 0.9999 - 27ms/epoch - 9ms/step\n",
"Epoch 239/300\n",
"3/3 - 0s - loss: 1.0004 - 26ms/epoch - 9ms/step\n",
"Epoch 240/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 241/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 242/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 243/300\n",
"3/3 - 0s - loss: 1.0000 - 26ms/epoch - 9ms/step\n",
"Epoch 244/300\n",
"3/3 - 0s - loss: 1.0000 - 26ms/epoch - 9ms/step\n",
"Epoch 245/300\n",
"3/3 - 0s - loss: 1.0001 - 27ms/epoch - 9ms/step\n",
"Epoch 246/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 247/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 248/300\n",
"3/3 - 0s - loss: 1.0000 - 26ms/epoch - 9ms/step\n",
"Epoch 249/300\n",
"3/3 - 0s - loss: 1.0001 - 30ms/epoch - 10ms/step\n",
"Epoch 250/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 251/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 252/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 253/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 254/300\n",
"3/3 - 0s - loss: 1.0001 - 26ms/epoch - 9ms/step\n",
"Epoch 255/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 256/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 257/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 258/300\n",
"3/3 - 0s - loss: 1.0001 - 26ms/epoch - 9ms/step\n",
"Epoch 259/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 260/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 261/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 262/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 263/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 264/300\n",
"3/3 - 0s - loss: 1.0000 - 26ms/epoch - 9ms/step\n",
"Epoch 265/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 266/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 267/300\n",
"3/3 - 0s - loss: 1.0000 - 25ms/epoch - 8ms/step\n",
"Epoch 268/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 269/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 270/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 271/300\n",
"3/3 - 0s - loss: 1.0000 - 30ms/epoch - 10ms/step\n",
"Epoch 272/300\n",
"3/3 - 0s - loss: 1.0000 - 30ms/epoch - 10ms/step\n",
"Epoch 273/300\n",
"3/3 - 0s - loss: 1.0002 - 29ms/epoch - 10ms/step\n",
"Epoch 274/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 275/300\n",
"3/3 - 0s - loss: 1.0001 - 30ms/epoch - 10ms/step\n",
"Epoch 276/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 277/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 278/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 279/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 280/300\n",
"3/3 - 0s - loss: 1.0003 - 29ms/epoch - 10ms/step\n",
"Epoch 281/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 282/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 283/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 284/300\n",
"3/3 - 0s - loss: 1.0000 - 30ms/epoch - 10ms/step\n",
"Epoch 285/300\n",
"3/3 - 0s - loss: 1.0000 - 30ms/epoch - 10ms/step\n",
"Epoch 286/300\n",
"3/3 - 0s - loss: 1.0000 - 30ms/epoch - 10ms/step\n",
"Epoch 287/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n",
"Epoch 288/300\n",
"3/3 - 0s - loss: 1.0002 - 28ms/epoch - 9ms/step\n",
"Epoch 289/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 290/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 291/300\n",
"3/3 - 0s - loss: 1.0001 - 29ms/epoch - 10ms/step\n",
"Epoch 292/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 293/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 294/300\n",
"3/3 - 0s - loss: 1.0000 - 27ms/epoch - 9ms/step\n",
"Epoch 295/300\n",
"3/3 - 0s - loss: 1.0001 - 28ms/epoch - 9ms/step\n",
"Epoch 296/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 297/300\n",
"3/3 - 0s - loss: 1.0000 - 26ms/epoch - 9ms/step\n",
"Epoch 298/300\n",
"3/3 - 0s - loss: 1.0000 - 26ms/epoch - 9ms/step\n",
"Epoch 299/300\n",
"3/3 - 0s - loss: 1.0000 - 29ms/epoch - 10ms/step\n",
"Epoch 300/300\n",
"3/3 - 0s - loss: 1.0000 - 28ms/epoch - 9ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7ded3354c7c0>"
]
},
"metadata": {},
"execution_count": 44
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "44986da9-5c05-44f5-baa7-67549eb28c03",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 442
}
},
"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": 45,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"14/14 [==============================] - 1s 6ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7ded44cc2290>"
]
},
"metadata": {},
"execution_count": 45
},
{
"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": "6fb0eba7-1a46-40ed-8259-dfb94a1769df"
},
"execution_count": 46,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1710189551.834038\n",
"Mon Mar 11 20:39:11 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": "17ab2ca0-ae19-4878-d428-4fe9864d8308"
},
"execution_count": 47,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1710189551.8469098\n",
"Mon Mar 11 20:39:11 2024\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "BMxSJo5gtOmQ"
},
"source": [
"# VS Fully Connected"
]
},
{
"cell_type": "code",
"metadata": {
"id": "NKQx7stYswzU",
"outputId": "233495a1-15c5-4f02-f97f-333ac5ce691d",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 11384
}
},
"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": 48,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"3/3 - 1s - loss: 0.5656 - 644ms/epoch - 215ms/step\n",
"Epoch 2/300\n",
"3/3 - 0s - loss: 0.1959 - 29ms/epoch - 10ms/step\n",
"Epoch 3/300\n",
"3/3 - 0s - loss: 0.1423 - 27ms/epoch - 9ms/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 - 25ms/epoch - 8ms/step\n",
"Epoch 6/300\n",
"3/3 - 0s - loss: 0.0827 - 23ms/epoch - 8ms/step\n",
"Epoch 7/300\n",
"3/3 - 0s - loss: 0.0680 - 26ms/epoch - 9ms/step\n",
"Epoch 8/300\n",
"3/3 - 0s - loss: 0.0680 - 25ms/epoch - 8ms/step\n",
"Epoch 9/300\n",
"3/3 - 0s - loss: 0.0605 - 27ms/epoch - 9ms/step\n",
"Epoch 10/300\n",
"3/3 - 0s - loss: 0.0632 - 23ms/epoch - 8ms/step\n",
"Epoch 11/300\n",
"3/3 - 0s - loss: 0.0537 - 30ms/epoch - 10ms/step\n",
"Epoch 12/300\n",
"3/3 - 0s - loss: 0.0523 - 24ms/epoch - 8ms/step\n",
"Epoch 13/300\n",
"3/3 - 0s - loss: 0.0522 - 27ms/epoch - 9ms/step\n",
"Epoch 14/300\n",
"3/3 - 0s - loss: 0.0483 - 26ms/epoch - 9ms/step\n",
"Epoch 15/300\n",
"3/3 - 0s - loss: 0.0498 - 24ms/epoch - 8ms/step\n",
"Epoch 16/300\n",
"3/3 - 0s - loss: 0.0444 - 25ms/epoch - 8ms/step\n",
"Epoch 17/300\n",
"3/3 - 0s - loss: 0.0487 - 25ms/epoch - 8ms/step\n",
"Epoch 18/300\n",
"3/3 - 0s - loss: 0.0467 - 25ms/epoch - 8ms/step\n",
"Epoch 19/300\n",
"3/3 - 0s - loss: 0.0419 - 24ms/epoch - 8ms/step\n",
"Epoch 20/300\n",
"3/3 - 0s - loss: 0.0439 - 22ms/epoch - 7ms/step\n",
"Epoch 21/300\n",
"3/3 - 0s - loss: 0.0406 - 24ms/epoch - 8ms/step\n",
"Epoch 22/300\n",
"3/3 - 0s - loss: 0.0414 - 27ms/epoch - 9ms/step\n",
"Epoch 23/300\n",
"3/3 - 0s - loss: 0.0421 - 26ms/epoch - 9ms/step\n",
"Epoch 24/300\n",
"3/3 - 0s - loss: 0.0378 - 26ms/epoch - 9ms/step\n",
"Epoch 25/300\n",
"3/3 - 0s - loss: 0.0382 - 26ms/epoch - 9ms/step\n",
"Epoch 26/300\n",
"3/3 - 0s - loss: 0.0425 - 24ms/epoch - 8ms/step\n",
"Epoch 27/300\n",
"3/3 - 0s - loss: 0.0505 - 23ms/epoch - 8ms/step\n",
"Epoch 28/300\n",
"3/3 - 0s - loss: 0.0423 - 26ms/epoch - 9ms/step\n",
"Epoch 29/300\n",
"3/3 - 0s - loss: 0.0513 - 25ms/epoch - 8ms/step\n",
"Epoch 30/300\n",
"3/3 - 0s - loss: 0.0385 - 23ms/epoch - 8ms/step\n",
"Epoch 31/300\n",
"3/3 - 0s - loss: 0.0392 - 28ms/epoch - 9ms/step\n",
"Epoch 32/300\n",
"3/3 - 0s - loss: 0.0417 - 28ms/epoch - 9ms/step\n",
"Epoch 33/300\n",
"3/3 - 0s - loss: 0.0414 - 26ms/epoch - 9ms/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 - 27ms/epoch - 9ms/step\n",
"Epoch 36/300\n",
"3/3 - 0s - loss: 0.0319 - 26ms/epoch - 9ms/step\n",
"Epoch 37/300\n",
"3/3 - 0s - loss: 0.0429 - 23ms/epoch - 8ms/step\n",
"Epoch 38/300\n",
"3/3 - 0s - loss: 0.0382 - 25ms/epoch - 8ms/step\n",
"Epoch 39/300\n",
"3/3 - 0s - loss: 0.0266 - 24ms/epoch - 8ms/step\n",
"Epoch 40/300\n",
"3/3 - 0s - loss: 0.0399 - 28ms/epoch - 9ms/step\n",
"Epoch 41/300\n",
"3/3 - 0s - loss: 0.0336 - 26ms/epoch - 9ms/step\n",
"Epoch 42/300\n",
"3/3 - 0s - loss: 0.0293 - 26ms/epoch - 9ms/step\n",
"Epoch 43/300\n",
"3/3 - 0s - loss: 0.0304 - 28ms/epoch - 9ms/step\n",
"Epoch 44/300\n",
"3/3 - 0s - loss: 0.0370 - 27ms/epoch - 9ms/step\n",
"Epoch 45/300\n",
"3/3 - 0s - loss: 0.0295 - 28ms/epoch - 9ms/step\n",
"Epoch 46/300\n",
"3/3 - 0s - loss: 0.0278 - 28ms/epoch - 9ms/step\n",
"Epoch 47/300\n",
"3/3 - 0s - loss: 0.0298 - 26ms/epoch - 9ms/step\n",
"Epoch 48/300\n",
"3/3 - 0s - loss: 0.0244 - 25ms/epoch - 8ms/step\n",
"Epoch 49/300\n",
"3/3 - 0s - loss: 0.0270 - 28ms/epoch - 9ms/step\n",
"Epoch 50/300\n",
"3/3 - 0s - loss: 0.0191 - 25ms/epoch - 8ms/step\n",
"Epoch 51/300\n",
"3/3 - 0s - loss: 0.0257 - 22ms/epoch - 7ms/step\n",
"Epoch 52/300\n",
"3/3 - 0s - loss: 0.0229 - 25ms/epoch - 8ms/step\n",
"Epoch 53/300\n",
"3/3 - 0s - loss: 0.0226 - 29ms/epoch - 10ms/step\n",
"Epoch 54/300\n",
"3/3 - 0s - loss: 0.0251 - 22ms/epoch - 7ms/step\n",
"Epoch 55/300\n",
"3/3 - 0s - loss: 0.0231 - 24ms/epoch - 8ms/step\n",
"Epoch 56/300\n",
"3/3 - 0s - loss: 0.0268 - 25ms/epoch - 8ms/step\n",
"Epoch 57/300\n",
"3/3 - 0s - loss: 0.0274 - 27ms/epoch - 9ms/step\n",
"Epoch 58/300\n",
"3/3 - 0s - loss: 0.0182 - 25ms/epoch - 8ms/step\n",
"Epoch 59/300\n",
"3/3 - 0s - loss: 0.0233 - 28ms/epoch - 9ms/step\n",
"Epoch 60/300\n",
"3/3 - 0s - loss: 0.0189 - 24ms/epoch - 8ms/step\n",
"Epoch 61/300\n",
"3/3 - 0s - loss: 0.0133 - 22ms/epoch - 7ms/step\n",
"Epoch 62/300\n",
"3/3 - 0s - loss: 0.0144 - 24ms/epoch - 8ms/step\n",
"Epoch 63/300\n",
"3/3 - 0s - loss: 0.0157 - 26ms/epoch - 9ms/step\n",
"Epoch 64/300\n",
"3/3 - 0s - loss: 0.0119 - 23ms/epoch - 8ms/step\n",
"Epoch 65/300\n",
"3/3 - 0s - loss: 0.0188 - 28ms/epoch - 9ms/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 - 21ms/epoch - 7ms/step\n",
"Epoch 68/300\n",
"3/3 - 0s - loss: 0.0110 - 23ms/epoch - 8ms/step\n",
"Epoch 69/300\n",
"3/3 - 0s - loss: 0.0073 - 22ms/epoch - 7ms/step\n",
"Epoch 70/300\n",
"3/3 - 0s - loss: 0.0097 - 25ms/epoch - 8ms/step\n",
"Epoch 71/300\n",
"3/3 - 0s - loss: 0.0088 - 29ms/epoch - 10ms/step\n",
"Epoch 72/300\n",
"3/3 - 0s - loss: 0.0063 - 25ms/epoch - 8ms/step\n",
"Epoch 73/300\n",
"3/3 - 0s - loss: 0.0058 - 23ms/epoch - 8ms/step\n",
"Epoch 74/300\n",
"3/3 - 0s - loss: 0.0060 - 24ms/epoch - 8ms/step\n",
"Epoch 75/300\n",
"3/3 - 0s - loss: 0.0094 - 21ms/epoch - 7ms/step\n",
"Epoch 76/300\n",
"3/3 - 0s - loss: 0.0106 - 23ms/epoch - 8ms/step\n",
"Epoch 77/300\n",
"3/3 - 0s - loss: 0.0083 - 24ms/epoch - 8ms/step\n",
"Epoch 78/300\n",
"3/3 - 0s - loss: 0.0048 - 23ms/epoch - 8ms/step\n",
"Epoch 79/300\n",
"3/3 - 0s - loss: 0.0048 - 22ms/epoch - 7ms/step\n",
"Epoch 80/300\n",
"3/3 - 0s - loss: 0.0046 - 25ms/epoch - 8ms/step\n",
"Epoch 81/300\n",
"3/3 - 0s - loss: 0.0029 - 24ms/epoch - 8ms/step\n",
"Epoch 82/300\n",
"3/3 - 0s - loss: 0.0026 - 24ms/epoch - 8ms/step\n",
"Epoch 83/300\n",
"3/3 - 0s - loss: 0.0030 - 24ms/epoch - 8ms/step\n",
"Epoch 84/300\n",
"3/3 - 0s - loss: 0.0032 - 23ms/epoch - 8ms/step\n",
"Epoch 85/300\n",
"3/3 - 0s - loss: 0.0040 - 27ms/epoch - 9ms/step\n",
"Epoch 86/300\n",
"3/3 - 0s - loss: 0.0045 - 24ms/epoch - 8ms/step\n",
"Epoch 87/300\n",
"3/3 - 0s - loss: 0.0047 - 27ms/epoch - 9ms/step\n",
"Epoch 88/300\n",
"3/3 - 0s - loss: 0.0033 - 23ms/epoch - 8ms/step\n",
"Epoch 89/300\n",
"3/3 - 0s - loss: 0.0034 - 26ms/epoch - 9ms/step\n",
"Epoch 90/300\n",
"3/3 - 0s - loss: 0.0083 - 27ms/epoch - 9ms/step\n",
"Epoch 91/300\n",
"3/3 - 0s - loss: 0.0109 - 23ms/epoch - 8ms/step\n",
"Epoch 92/300\n",
"3/3 - 0s - loss: 0.0065 - 26ms/epoch - 9ms/step\n",
"Epoch 93/300\n",
"3/3 - 0s - loss: 0.0046 - 27ms/epoch - 9ms/step\n",
"Epoch 94/300\n",
"3/3 - 0s - loss: 0.0068 - 23ms/epoch - 8ms/step\n",
"Epoch 95/300\n",
"3/3 - 0s - loss: 0.0096 - 26ms/epoch - 9ms/step\n",
"Epoch 96/300\n",
"3/3 - 0s - loss: 0.0103 - 26ms/epoch - 9ms/step\n",
"Epoch 97/300\n",
"3/3 - 0s - loss: 0.0119 - 24ms/epoch - 8ms/step\n",
"Epoch 98/300\n",
"3/3 - 0s - loss: 0.0069 - 25ms/epoch - 8ms/step\n",
"Epoch 99/300\n",
"3/3 - 0s - loss: 0.0075 - 21ms/epoch - 7ms/step\n",
"Epoch 100/300\n",
"3/3 - 0s - loss: 0.0057 - 25ms/epoch - 8ms/step\n",
"Epoch 101/300\n",
"3/3 - 0s - loss: 0.0032 - 24ms/epoch - 8ms/step\n",
"Epoch 102/300\n",
"3/3 - 0s - loss: 0.0039 - 26ms/epoch - 9ms/step\n",
"Epoch 103/300\n",
"3/3 - 0s - loss: 0.0029 - 24ms/epoch - 8ms/step\n",
"Epoch 104/300\n",
"3/3 - 0s - loss: 0.0031 - 25ms/epoch - 8ms/step\n",
"Epoch 105/300\n",
"3/3 - 0s - loss: 0.0021 - 24ms/epoch - 8ms/step\n",
"Epoch 106/300\n",
"3/3 - 0s - loss: 0.0015 - 24ms/epoch - 8ms/step\n",
"Epoch 107/300\n",
"3/3 - 0s - loss: 0.0014 - 26ms/epoch - 9ms/step\n",
"Epoch 108/300\n",
"3/3 - 0s - loss: 0.0013 - 25ms/epoch - 8ms/step\n",
"Epoch 109/300\n",
"3/3 - 0s - loss: 0.0022 - 29ms/epoch - 10ms/step\n",
"Epoch 110/300\n",
"3/3 - 0s - loss: 0.0019 - 26ms/epoch - 9ms/step\n",
"Epoch 111/300\n",
"3/3 - 0s - loss: 0.0020 - 23ms/epoch - 8ms/step\n",
"Epoch 112/300\n",
"3/3 - 0s - loss: 6.9314e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 113/300\n",
"3/3 - 0s - loss: 9.3566e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 114/300\n",
"3/3 - 0s - loss: 0.0015 - 25ms/epoch - 8ms/step\n",
"Epoch 115/300\n",
"3/3 - 0s - loss: 0.0017 - 25ms/epoch - 8ms/step\n",
"Epoch 116/300\n",
"3/3 - 0s - loss: 0.0020 - 26ms/epoch - 9ms/step\n",
"Epoch 117/300\n",
"3/3 - 0s - loss: 0.0018 - 23ms/epoch - 8ms/step\n",
"Epoch 118/300\n",
"3/3 - 0s - loss: 0.0010 - 28ms/epoch - 9ms/step\n",
"Epoch 119/300\n",
"3/3 - 0s - loss: 8.8028e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 120/300\n",
"3/3 - 0s - loss: 7.2462e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 121/300\n",
"3/3 - 0s - loss: 8.0890e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 122/300\n",
"3/3 - 0s - loss: 9.8991e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 123/300\n",
"3/3 - 0s - loss: 7.1008e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 124/300\n",
"3/3 - 0s - loss: 4.9597e-04 - 22ms/epoch - 7ms/step\n",
"Epoch 125/300\n",
"3/3 - 0s - loss: 4.7966e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 126/300\n",
"3/3 - 0s - loss: 3.0518e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 127/300\n",
"3/3 - 0s - loss: 2.7030e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 128/300\n",
"3/3 - 0s - loss: 3.4302e-04 - 22ms/epoch - 7ms/step\n",
"Epoch 129/300\n",
"3/3 - 0s - loss: 3.2476e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 130/300\n",
"3/3 - 0s - loss: 1.6305e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 131/300\n",
"3/3 - 0s - loss: 1.8642e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 132/300\n",
"3/3 - 0s - loss: 8.2074e-05 - 29ms/epoch - 10ms/step\n",
"Epoch 133/300\n",
"3/3 - 0s - loss: 6.5955e-05 - 29ms/epoch - 10ms/step\n",
"Epoch 134/300\n",
"3/3 - 0s - loss: 6.8692e-05 - 29ms/epoch - 10ms/step\n",
"Epoch 135/300\n",
"3/3 - 0s - loss: 1.1016e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 136/300\n",
"3/3 - 0s - loss: 1.4056e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 137/300\n",
"3/3 - 0s - loss: 1.0764e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 138/300\n",
"3/3 - 0s - loss: 9.8001e-05 - 26ms/epoch - 9ms/step\n",
"Epoch 139/300\n",
"3/3 - 0s - loss: 2.1907e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 140/300\n",
"3/3 - 0s - loss: 2.4921e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 141/300\n",
"3/3 - 0s - loss: 4.0704e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 142/300\n",
"3/3 - 0s - loss: 5.5095e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 143/300\n",
"3/3 - 0s - loss: 8.7078e-04 - 22ms/epoch - 7ms/step\n",
"Epoch 144/300\n",
"3/3 - 0s - loss: 9.0852e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 145/300\n",
"3/3 - 0s - loss: 0.0014 - 27ms/epoch - 9ms/step\n",
"Epoch 146/300\n",
"3/3 - 0s - loss: 0.0021 - 26ms/epoch - 9ms/step\n",
"Epoch 147/300\n",
"3/3 - 0s - loss: 0.0012 - 29ms/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 - 27ms/epoch - 9ms/step\n",
"Epoch 150/300\n",
"3/3 - 0s - loss: 0.0013 - 31ms/epoch - 10ms/step\n",
"Epoch 151/300\n",
"3/3 - 0s - loss: 0.0012 - 26ms/epoch - 9ms/step\n",
"Epoch 152/300\n",
"3/3 - 0s - loss: 0.0011 - 23ms/epoch - 8ms/step\n",
"Epoch 153/300\n",
"3/3 - 0s - loss: 8.8283e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 154/300\n",
"3/3 - 0s - loss: 5.0875e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 155/300\n",
"3/3 - 0s - loss: 4.6452e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 156/300\n",
"3/3 - 0s - loss: 4.4445e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 157/300\n",
"3/3 - 0s - loss: 4.5507e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 158/300\n",
"3/3 - 0s - loss: 5.0221e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 159/300\n",
"3/3 - 0s - loss: 7.1127e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 160/300\n",
"3/3 - 0s - loss: 5.3585e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 161/300\n",
"3/3 - 0s - loss: 3.0625e-04 - 25ms/epoch - 8ms/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 - 25ms/epoch - 8ms/step\n",
"Epoch 164/300\n",
"3/3 - 0s - loss: 1.7076e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 165/300\n",
"3/3 - 0s - loss: 2.1320e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 166/300\n",
"3/3 - 0s - loss: 2.7991e-04 - 23ms/epoch - 8ms/step\n",
"Epoch 167/300\n",
"3/3 - 0s - loss: 3.3069e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 168/300\n",
"3/3 - 0s - loss: 2.9444e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 169/300\n",
"3/3 - 0s - loss: 4.0663e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 170/300\n",
"3/3 - 0s - loss: 3.3016e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 171/300\n",
"3/3 - 0s - loss: 2.0864e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 172/300\n",
"3/3 - 0s - loss: 3.1231e-04 - 31ms/epoch - 10ms/step\n",
"Epoch 173/300\n",
"3/3 - 0s - loss: 2.9278e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 174/300\n",
"3/3 - 0s - loss: 3.0427e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 175/300\n",
"3/3 - 0s - loss: 4.5326e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 176/300\n",
"3/3 - 0s - loss: 3.3629e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 177/300\n",
"3/3 - 0s - loss: 2.4525e-04 - 23ms/epoch - 8ms/step\n",
"Epoch 178/300\n",
"3/3 - 0s - loss: 2.5538e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 179/300\n",
"3/3 - 0s - loss: 3.3784e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 180/300\n",
"3/3 - 0s - loss: 1.9497e-04 - 23ms/epoch - 8ms/step\n",
"Epoch 181/300\n",
"3/3 - 0s - loss: 1.9737e-04 - 23ms/epoch - 8ms/step\n",
"Epoch 182/300\n",
"3/3 - 0s - loss: 2.2758e-04 - 22ms/epoch - 7ms/step\n",
"Epoch 183/300\n",
"3/3 - 0s - loss: 2.9136e-04 - 23ms/epoch - 8ms/step\n",
"Epoch 184/300\n",
"3/3 - 0s - loss: 1.1060e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 185/300\n",
"3/3 - 0s - loss: 5.0481e-05 - 24ms/epoch - 8ms/step\n",
"Epoch 186/300\n",
"3/3 - 0s - loss: 4.0821e-05 - 29ms/epoch - 10ms/step\n",
"Epoch 187/300\n",
"3/3 - 0s - loss: 5.7687e-05 - 24ms/epoch - 8ms/step\n",
"Epoch 188/300\n",
"3/3 - 0s - loss: 5.1819e-05 - 26ms/epoch - 9ms/step\n",
"Epoch 189/300\n",
"3/3 - 0s - loss: 4.4923e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 190/300\n",
"3/3 - 0s - loss: 5.0681e-05 - 21ms/epoch - 7ms/step\n",
"Epoch 191/300\n",
"3/3 - 0s - loss: 3.9062e-05 - 29ms/epoch - 10ms/step\n",
"Epoch 192/300\n",
"3/3 - 0s - loss: 3.1511e-05 - 22ms/epoch - 7ms/step\n",
"Epoch 193/300\n",
"3/3 - 0s - loss: 3.9896e-05 - 24ms/epoch - 8ms/step\n",
"Epoch 194/300\n",
"3/3 - 0s - loss: 3.6009e-05 - 24ms/epoch - 8ms/step\n",
"Epoch 195/300\n",
"3/3 - 0s - loss: 3.8435e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 196/300\n",
"3/3 - 0s - loss: 6.6916e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 197/300\n",
"3/3 - 0s - loss: 1.2784e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 198/300\n",
"3/3 - 0s - loss: 8.5005e-05 - 23ms/epoch - 8ms/step\n",
"Epoch 199/300\n",
"3/3 - 0s - loss: 6.0588e-05 - 28ms/epoch - 9ms/step\n",
"Epoch 200/300\n",
"3/3 - 0s - loss: 6.8180e-05 - 28ms/epoch - 9ms/step\n",
"Epoch 201/300\n",
"3/3 - 0s - loss: 4.7230e-05 - 27ms/epoch - 9ms/step\n",
"Epoch 202/300\n",
"3/3 - 0s - loss: 3.8133e-05 - 24ms/epoch - 8ms/step\n",
"Epoch 203/300\n",
"3/3 - 0s - loss: 7.4671e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 204/300\n",
"3/3 - 0s - loss: 8.1094e-05 - 23ms/epoch - 8ms/step\n",
"Epoch 205/300\n",
"3/3 - 0s - loss: 7.8872e-05 - 24ms/epoch - 8ms/step\n",
"Epoch 206/300\n",
"3/3 - 0s - loss: 8.7357e-05 - 28ms/epoch - 9ms/step\n",
"Epoch 207/300\n",
"3/3 - 0s - loss: 4.8380e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 208/300\n",
"3/3 - 0s - loss: 7.0697e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 209/300\n",
"3/3 - 0s - loss: 5.2098e-05 - 23ms/epoch - 8ms/step\n",
"Epoch 210/300\n",
"3/3 - 0s - loss: 5.4029e-05 - 24ms/epoch - 8ms/step\n",
"Epoch 211/300\n",
"3/3 - 0s - loss: 2.8489e-05 - 27ms/epoch - 9ms/step\n",
"Epoch 212/300\n",
"3/3 - 0s - loss: 3.3961e-05 - 23ms/epoch - 8ms/step\n",
"Epoch 213/300\n",
"3/3 - 0s - loss: 4.1667e-05 - 24ms/epoch - 8ms/step\n",
"Epoch 214/300\n",
"3/3 - 0s - loss: 3.7597e-05 - 26ms/epoch - 9ms/step\n",
"Epoch 215/300\n",
"3/3 - 0s - loss: 2.7004e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 216/300\n",
"3/3 - 0s - loss: 2.9110e-05 - 23ms/epoch - 8ms/step\n",
"Epoch 217/300\n",
"3/3 - 0s - loss: 3.6687e-05 - 26ms/epoch - 9ms/step\n",
"Epoch 218/300\n",
"3/3 - 0s - loss: 7.2615e-05 - 28ms/epoch - 9ms/step\n",
"Epoch 219/300\n",
"3/3 - 0s - loss: 1.0681e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 220/300\n",
"3/3 - 0s - loss: 1.9565e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 221/300\n",
"3/3 - 0s - loss: 1.9595e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 222/300\n",
"3/3 - 0s - loss: 1.7055e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 223/300\n",
"3/3 - 0s - loss: 1.4371e-04 - 28ms/epoch - 9ms/step\n",
"Epoch 224/300\n",
"3/3 - 0s - loss: 1.0054e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 225/300\n",
"3/3 - 0s - loss: 7.8233e-05 - 26ms/epoch - 9ms/step\n",
"Epoch 226/300\n",
"3/3 - 0s - loss: 2.0859e-04 - 30ms/epoch - 10ms/step\n",
"Epoch 227/300\n",
"3/3 - 0s - loss: 2.3248e-04 - 22ms/epoch - 7ms/step\n",
"Epoch 228/300\n",
"3/3 - 0s - loss: 3.5742e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 229/300\n",
"3/3 - 0s - loss: 3.2267e-04 - 22ms/epoch - 7ms/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 - 29ms/epoch - 10ms/step\n",
"Epoch 232/300\n",
"3/3 - 0s - loss: 2.2141e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 233/300\n",
"3/3 - 0s - loss: 1.3816e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 234/300\n",
"3/3 - 0s - loss: 1.2997e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 235/300\n",
"3/3 - 0s - loss: 1.2696e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 236/300\n",
"3/3 - 0s - loss: 7.3166e-05 - 22ms/epoch - 7ms/step\n",
"Epoch 237/300\n",
"3/3 - 0s - loss: 4.9531e-05 - 25ms/epoch - 8ms/step\n",
"Epoch 238/300\n",
"3/3 - 0s - loss: 5.9576e-05 - 29ms/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 - 30ms/epoch - 10ms/step\n",
"Epoch 241/300\n",
"3/3 - 0s - loss: 1.0165e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 242/300\n",
"3/3 - 0s - loss: 1.1189e-04 - 26ms/epoch - 9ms/step\n",
"Epoch 243/300\n",
"3/3 - 0s - loss: 1.2715e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 244/300\n",
"3/3 - 0s - loss: 2.3746e-04 - 29ms/epoch - 10ms/step\n",
"Epoch 245/300\n",
"3/3 - 0s - loss: 7.2393e-04 - 22ms/epoch - 7ms/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 - 28ms/epoch - 9ms/step\n",
"Epoch 248/300\n",
"3/3 - 0s - loss: 6.1267e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 249/300\n",
"3/3 - 0s - loss: 5.4795e-04 - 23ms/epoch - 8ms/step\n",
"Epoch 250/300\n",
"3/3 - 0s - loss: 8.4581e-04 - 25ms/epoch - 8ms/step\n",
"Epoch 251/300\n",
"3/3 - 0s - loss: 4.3189e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 252/300\n",
"3/3 - 0s - loss: 6.3720e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 253/300\n",
"3/3 - 0s - loss: 8.4664e-04 - 24ms/epoch - 8ms/step\n",
"Epoch 254/300\n",
"3/3 - 0s - loss: 0.0025 - 23ms/epoch - 8ms/step\n",
"Epoch 255/300\n",
"3/3 - 0s - loss: 0.0032 - 23ms/epoch - 8ms/step\n",
"Epoch 256/300\n",
"3/3 - 0s - loss: 0.0040 - 24ms/epoch - 8ms/step\n",
"Epoch 257/300\n",
"3/3 - 0s - loss: 0.0021 - 28ms/epoch - 9ms/step\n",
"Epoch 258/300\n",
"3/3 - 0s - loss: 0.0023 - 28ms/epoch - 9ms/step\n",
"Epoch 259/300\n",
"3/3 - 0s - loss: 0.0034 - 26ms/epoch - 9ms/step\n",
"Epoch 260/300\n",
"3/3 - 0s - loss: 0.0045 - 30ms/epoch - 10ms/step\n",
"Epoch 261/300\n",
"3/3 - 0s - loss: 0.0064 - 22ms/epoch - 7ms/step\n",
"Epoch 262/300\n",
"3/3 - 0s - loss: 0.0050 - 27ms/epoch - 9ms/step\n",
"Epoch 263/300\n",
"3/3 - 0s - loss: 0.0068 - 23ms/epoch - 8ms/step\n",
"Epoch 264/300\n",
"3/3 - 0s - loss: 0.0042 - 26ms/epoch - 9ms/step\n",
"Epoch 265/300\n",
"3/3 - 0s - loss: 0.0047 - 30ms/epoch - 10ms/step\n",
"Epoch 266/300\n",
"3/3 - 0s - loss: 0.0045 - 25ms/epoch - 8ms/step\n",
"Epoch 267/300\n",
"3/3 - 0s - loss: 0.0046 - 25ms/epoch - 8ms/step\n",
"Epoch 268/300\n",
"3/3 - 0s - loss: 0.0032 - 25ms/epoch - 8ms/step\n",
"Epoch 269/300\n",
"3/3 - 0s - loss: 0.0031 - 25ms/epoch - 8ms/step\n",
"Epoch 270/300\n",
"3/3 - 0s - loss: 0.0041 - 23ms/epoch - 8ms/step\n",
"Epoch 271/300\n",
"3/3 - 0s - loss: 0.0034 - 25ms/epoch - 8ms/step\n",
"Epoch 272/300\n",
"3/3 - 0s - loss: 0.0043 - 28ms/epoch - 9ms/step\n",
"Epoch 273/300\n",
"3/3 - 0s - loss: 0.0034 - 25ms/epoch - 8ms/step\n",
"Epoch 274/300\n",
"3/3 - 0s - loss: 0.0036 - 29ms/epoch - 10ms/step\n",
"Epoch 275/300\n",
"3/3 - 0s - loss: 0.0030 - 26ms/epoch - 9ms/step\n",
"Epoch 276/300\n",
"3/3 - 0s - loss: 0.0027 - 26ms/epoch - 9ms/step\n",
"Epoch 277/300\n",
"3/3 - 0s - loss: 0.0033 - 25ms/epoch - 8ms/step\n",
"Epoch 278/300\n",
"3/3 - 0s - loss: 0.0024 - 25ms/epoch - 8ms/step\n",
"Epoch 279/300\n",
"3/3 - 0s - loss: 0.0017 - 24ms/epoch - 8ms/step\n",
"Epoch 280/300\n",
"3/3 - 0s - loss: 0.0017 - 27ms/epoch - 9ms/step\n",
"Epoch 281/300\n",
"3/3 - 0s - loss: 0.0015 - 28ms/epoch - 9ms/step\n",
"Epoch 282/300\n",
"3/3 - 0s - loss: 0.0015 - 27ms/epoch - 9ms/step\n",
"Epoch 283/300\n",
"3/3 - 0s - loss: 0.0019 - 26ms/epoch - 9ms/step\n",
"Epoch 284/300\n",
"3/3 - 0s - loss: 0.0042 - 26ms/epoch - 9ms/step\n",
"Epoch 285/300\n",
"3/3 - 0s - loss: 0.0026 - 25ms/epoch - 8ms/step\n",
"Epoch 286/300\n",
"3/3 - 0s - loss: 0.0035 - 27ms/epoch - 9ms/step\n",
"Epoch 287/300\n",
"3/3 - 0s - loss: 0.0033 - 28ms/epoch - 9ms/step\n",
"Epoch 288/300\n",
"3/3 - 0s - loss: 0.0059 - 28ms/epoch - 9ms/step\n",
"Epoch 289/300\n",
"3/3 - 0s - loss: 0.0073 - 25ms/epoch - 8ms/step\n",
"Epoch 290/300\n",
"3/3 - 0s - loss: 0.0060 - 30ms/epoch - 10ms/step\n",
"Epoch 291/300\n",
"3/3 - 0s - loss: 0.0032 - 25ms/epoch - 8ms/step\n",
"Epoch 292/300\n",
"3/3 - 0s - loss: 0.0022 - 25ms/epoch - 8ms/step\n",
"Epoch 293/300\n",
"3/3 - 0s - loss: 0.0021 - 23ms/epoch - 8ms/step\n",
"Epoch 294/300\n",
"3/3 - 0s - loss: 0.0025 - 25ms/epoch - 8ms/step\n",
"Epoch 295/300\n",
"3/3 - 0s - loss: 0.0011 - 26ms/epoch - 9ms/step\n",
"Epoch 296/300\n",
"3/3 - 0s - loss: 6.3007e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 297/300\n",
"3/3 - 0s - loss: 4.8764e-04 - 27ms/epoch - 9ms/step\n",
"Epoch 298/300\n",
"3/3 - 0s - loss: 5.1926e-04 - 27ms/epoch - 9ms/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 - 26ms/epoch - 9ms/step\n",
"14/14 [==============================] - 0s 3ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7ded3360b700>"
]
},
"metadata": {},
"execution_count": 48
},
{
"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": "aa47eccd-0042-46a6-e0a8-4d70cec90d12"
},
"execution_count": 49,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1710189563.0161803\n",
"Mon Mar 11 20:39:23 2024\n"
]
}
]
}
]
}