Files
PINA/tutorials/tutorial1/tutorial.ipynb
2023-11-17 09:51:29 +01:00

398 lines
14 KiB
Plaintext
Vendored

{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "6f71ca5c",
"metadata": {},
"source": [
"# Tutorial 1: Physics Informed Neural Networks on PINA"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "ef4949c9",
"metadata": {},
"source": [
"In this tutorial, we will demonstrate a typical use case of PINA on a toy problem. Specifically, the tutorial aims to introduce the following topics:\n",
"\n",
"* Defining a PINA Problem,\n",
"* Building a `pinn` object,\n",
"* Sampling points in a domain\n",
"\n",
"These are the three main steps needed **before** training a Physics Informed Neural Network (PINN). We will show each step in detail, and at the end, we will solve the problem."
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "1bd1904d",
"metadata": {},
"source": [
"## PINA Problem"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "cf9c96e3",
"metadata": {},
"source": [
"### Initialize the `Problem` class"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "8a819659",
"metadata": {},
"source": [
"Problem definition in the PINA framework is done by building a python `class`, which inherits from one or more problem classes (`SpatialProblem`, `TimeDependentProblem`, `ParametricProblem`) depending on the nature of the problem. Below is an example:\n",
"#### Simple Ordinary Differential Equation\n",
"Consider the following:\n",
"\n",
"$$\n",
"\\begin{equation}\n",
"\\begin{cases}\n",
"\\frac{d}{dx}u(x) &= u(x) \\quad x\\in(0,1)\\\\\n",
"u(x=0) &= 1 \\\\\n",
"\\end{cases}\n",
"\\end{equation}\n",
"$$\n",
"\n",
"with the analytical solution $u(x) = e^x$. In this case, our ODE depends only on the spatial variable $x\\in(0,1)$ , meaning that our `Problem` class is going to be inherited from the `SpatialProblem` class:\n",
"\n",
"```python\n",
"from pina.problem import SpatialProblem\n",
"from pina import CartesianProblem\n",
"\n",
"class SimpleODE(SpatialProblem):\n",
" \n",
" output_variables = ['u']\n",
" spatial_domain = CartesianProblem({'x': [0, 1]})\n",
"\n",
" # other stuff ...\n",
"```\n",
"\n",
"Notice that we define `output_variables` as a list of symbols, indicating the output variables of our equation (in this case only $u$). The `spatial_domain` variable indicates where the sample points are going to be sampled in the domain, in this case $x\\in[0,1]$."
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "4e0a22bc",
"metadata": {},
"source": [
"What about if our equation is also time dependent? In this case, our `class` will inherit from both `SpatialProblem` and `TimeDependentProblem`:\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "2373a925",
"metadata": {},
"outputs": [],
"source": [
"from pina.problem import SpatialProblem, TimeDependentProblem\n",
"from pina import CartesianDomain\n",
"\n",
"class TimeSpaceODE(SpatialProblem, TimeDependentProblem):\n",
" \n",
" output_variables = ['u']\n",
" spatial_domain = CartesianDomain({'x': [0, 1]})\n",
" temporal_domain = CartesianDomain({'t': [0, 1]})\n",
"\n",
" # other stuff ..."
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "ad8566b8",
"metadata": {},
"source": [
"where we have included the `temporal_domain` variable, indicating the time domain wanted for the solution.\n",
"\n",
"In summary, using PINA, we can initialize a problem with a class which inherits from three base classes: `SpatialProblem`, `TimeDependentProblem`, `ParametricProblem`, depending on the type of problem we are considering. For reference:\n",
"* `SpatialProblem` $\\rightarrow$ a differential equation with spatial variable(s)\n",
"* `TimeDependentProblem` $\\rightarrow$ a time-dependent differential equation\n",
"* `ParametricProblem` $\\rightarrow$ a parametrized differential equation"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "592a4c43",
"metadata": {},
"source": [
"### Write the `Problem` class\n",
"\n",
"Once the `Problem` class is initialized, we need to represent the differential equation in PINA. In order to do this, we need to load the PINA operators from `pina.operators` module. Again, we'll consider Equation (1) and represent it in PINA:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "f2608e2e",
"metadata": {},
"outputs": [],
"source": [
"from pina.problem import SpatialProblem\n",
"from pina.operators import grad\n",
"from pina import Condition, CartesianDomain\n",
"from pina.equation.equation import Equation\n",
"\n",
"import torch\n",
"\n",
"\n",
"class SimpleODE(SpatialProblem):\n",
"\n",
" output_variables = ['u']\n",
" spatial_domain = CartesianDomain({'x': [0, 1]})\n",
"\n",
" # defining the ode equation\n",
" def ode_equation(input_, output_):\n",
"\n",
" # computing the derivative\n",
" u_x = grad(output_, input_, components=['u'], d=['x'])\n",
"\n",
" # extracting the u input variable\n",
" u = output_.extract(['u'])\n",
"\n",
" # calculate the residual and return it\n",
" return u_x - u\n",
"\n",
" # defining the initial condition\n",
" def initial_condition(input_, output_):\n",
" \n",
" # setting the initial value\n",
" value = 1.0\n",
"\n",
" # extracting the u input variable\n",
" u = output_.extract(['u'])\n",
"\n",
" # calculate the residual and return it\n",
" return u - value\n",
"\n",
" # conditions to hold\n",
" conditions = {\n",
" 'x0': Condition(location=CartesianDomain({'x': 0.}), equation=Equation(initial_condition)),\n",
" 'D': Condition(location=CartesianDomain({'x': [0, 1]}), equation=Equation(ode_equation)),\n",
" }\n",
"\n",
" # sampled points (see below)\n",
" input_pts = None\n",
"\n",
" # defining the true solution\n",
" def truth_solution(self, pts):\n",
" return torch.exp(pts.extract(['x']))"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "7cf64d01",
"metadata": {},
"source": [
"After we define the `Problem` class, we need to write different class methods, where each method is a function returning a residual. These functions are the ones minimized during PINN optimization, given the initial conditions. For example, in the domain $[0,1]$, the ODE equation (`ode_equation`) must be satisfied. We represent this by returning the difference between subtracting the variable `u` from its gradient (the residual), which we hope to minimize to 0. This is done for all conditions (`ode_equation`, `initial_condition`). \n",
"\n",
"Once we have defined the function, we need to tell the neural network where these methods are to be applied. To do so, we use the `Condition` class. In the `Condition` class, we pass the location points and the function we want minimized on those points (other possibilities are allowed, see the documentation for reference) as parameters.\n",
"\n",
"Finally, it's possible to define a `truth_solution` function, which can be useful if we want to plot the results and see how the real solution compares to the expected (true) solution. Notice that the `truth_solution` function is a method of the `PINN` class, but is not mandatory for problem definition.\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "22e502dd",
"metadata": {},
"source": [
"## Build the `PINN` object"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "075f43f5",
"metadata": {},
"source": [
"The basic requirements for building a `PINN` model are a `Problem` and a model. We have just covered the `Problem` definition. For the model parameter, one can use either the default models provided in PINA or a custom model. We will not go into the details of model definition (see Tutorial2 and Tutorial3 for more details on model definition)."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "3bb4dc9b",
"metadata": {},
"outputs": [],
"source": [
"from pina.model import FeedForward\n",
"from pina import PINN\n",
"\n",
"# initialize the problem\n",
"problem = SimpleODE()\n",
"\n",
"# build the model\n",
"model = FeedForward(\n",
" layers=[10, 10],\n",
" func=torch.nn.Tanh,\n",
" output_dimensions=len(problem.output_variables),\n",
" input_dimensions=len(problem.input_variables)\n",
")\n",
"\n",
"# create the PINN object\n",
"pinn = PINN(problem, model)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "8d2cb313",
"metadata": {},
"source": [
"Creating the `PINN` object is fairly simple. Different optional parameters include: optimizer, batch size, ... (see [documentation](https://mathlab.github.io/PINA/) for reference)."
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "78b30f95",
"metadata": {},
"source": [
"## Sample points in the domain "
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "53c783e8",
"metadata": {},
"source": [
"Once the `PINN` object is created, we need to generate the points for starting the optimization. To do so, we use the `sample` method of the `CartesianDomain` class. Below are three examples of sampling methods on the $[0,1]$ domain:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "09ce5c3a",
"metadata": {},
"outputs": [],
"source": [
"# sampling 20 points in [0, 1] through discretization\n",
"pinn.problem.discretise_domain(n=20, mode='grid', variables=['x'])\n",
"\n",
"# sampling 20 points in (0, 1) through latin hypercube samping\n",
"pinn.problem.discretise_domain(n=20, mode='latin', variables=['x'])\n",
"\n",
"# sampling 20 points in (0, 1) randomly\n",
"pinn.problem.discretise_domain(n=20, mode='random', variables=['x'])"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "27a287db",
"metadata": {},
"source": [
"### Very simple training and plotting\n",
"\n",
"Once we have defined the PINA model, created a network, and sampled points in the domain, we have everything necessary for training a PINN. To do so, we make use of the `Trainer` class."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "f8b4f496",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/u/n/ndemo/.local/lib/python3.9/site-packages/torch/cuda/__init__.py:546: UserWarning: Can't initialize NVML\n",
" warnings.warn(\"Can't initialize NVML\")\n",
"GPU available: True (cuda), used: True\n",
"TPU available: False, using: 0 TPU cores\n",
"IPU available: False, using: 0 IPUs\n",
"HPU available: False, using: 0 HPUs\n",
"/u/n/ndemo/.local/lib/python3.9/site-packages/lightning/pytorch/loops/utilities.py:72: PossibleUserWarning: `max_epochs` was not set. Setting it to 1000 epochs. To train without an epoch limit, set `max_epochs=-1`.\n",
" rank_zero_warn(\n",
"2023-10-17 10:02:21.318700: I tensorflow/core/util/port.cc:110] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
"2023-10-17 10:02:21.345355: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
"To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
"2023-10-17 10:02:23.572602: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
"/opt/sissa/apps/intelpython/2022.0.2/intelpython/latest/lib/python3.9/site-packages/scipy/__init__.py:138: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.26.0)\n",
" warnings.warn(f\"A NumPy version >={np_minversion} and <{np_maxversion} is required for this version of \"\n",
"LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n",
"\n",
" | Name | Type | Params\n",
"----------------------------------------\n",
"0 | _loss | MSELoss | 0 \n",
"1 | _neural_net | Network | 141 \n",
"----------------------------------------\n",
"141 Trainable params\n",
"0 Non-trainable params\n",
"141 Total params\n",
"0.001 Total estimated model params size (MB)\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "5e99075a1776436eb94b80f7dfbbc794",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Training: 0it [00:00, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"`Trainer.fit` stopped: `max_epochs=1000` reached.\n"
]
}
],
"source": [
"from pina import Trainer\n",
"\n",
"# initialize trainer\n",
"trainer = Trainer(pinn)\n",
"\n",
"# train the model\n",
"trainer.train()"
]
}
],
"metadata": {
"interpreter": {
"hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
},
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}