Add FNO, show loss again in trainer and fix some small bugs

.github/workflows/pytest.yml

@@ -29,7 +29,7 @@ jobs:
         python -m pip install --upgrade pip
         pip install -U setuptools setuptools_scm wheel
         python -m pip install flake8 pytest pytest-cov
-        python -m pip install -e .
+        python -m pip install -e .[all]
         if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
     - name: Lint with flake8
       run: |

examples/deeponet/inverse_ode.ipynb

@@ -5,7 +5,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Inverse DeepONet\n",
+    "### Inverse DeepONet\n",
     "In this notebook, we present the learning of the inverse operator, that maps solution data to some input data. \n",
     "To keep things simple we again consider the ODE:\n",
     "\\begin{align*}\n",
@@ -28,8 +28,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os\n",
-    "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"1\"\n",
     "import torch\n",
     "import numpy as np\n",
     "import torchphysics as tp\n",

examples/deeponet/ode.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Physics-informed DeepONet: Solving a ODE for different right hand sides\n",
+    "### Physics-informed DeepONet: Solving a ODE for different right hand sides\n",
     "In this notebook, we present an introduction to the physics-informed DeepONet [(paper)](https://arxiv.org/abs/2103.10974) utilities of TorchPhysics. \n",
     "As an example, we try to learn the integral operator of the ODE:\n",
     "\\begin{align*}\n",
@@ -27,8 +27,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os\n",
-    "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"2\"\n",
     "import torch\n",
     "import torchphysics as tp\n",
     "import pytorch_lightning as pl"

examples/deeponet/oscillator.ipynb

@@ -6,8 +6,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os\n",
-    "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"3\"\n",
     "import torchphysics as tp\n",
     "import torch\n",
     "import pytorch_lightning as pl"

examples/deepritz/corner_pde.ipynb

@@ -22,8 +22,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os\n",
-    "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"1\"\n",
     "import torchphysics as tp \n",
     "import torch\n",
     "X = tp.spaces.R1('x') \n",

examples/deepritz/poisson-equation.ipynb

@@ -14,8 +14,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os\n",
-    "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\"\n",
     "import torch\n",
     "import torchphysics as tp\n",
     "import pytorch_lightning as pl"