supervised airfoils with images

supervised-airfoils.ipynb

@@ -157,7 +157,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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 truncated
+      "image/png": "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 truncated
       "text/plain": [
        "<Figure size 1600x500 with 2 Axes>"
       ]
@@ -380,7 +380,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
@@ -400,7 +400,14 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "loss train: 0.02743, loss val: 0.03572:   7%|█▎                | 14/200 [00:23<05:01,  1.62s/it]"
+      "loss train: 0.01113, loss val: 0.01996: 100%|█████████████████| 200/200 [05:40<00:00,  1.61s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "training done, saved network weights\n"
      ]
     }
    ],
@@ -464,12 +471,12 @@
    "source": [
     "The NN is finally trained! The losses should have nicely gone down in terms of absolute values: With the standard settings from an initial value of around 0.2 for the validation  loss, to ca. 0.02 after training.\n",
     "\n",
-    "Let's look at the graphs to get some intuition for how the training progressed over time. This is typically important to identify longer-term trends in the training. In practice it's tricky to spot whether the overall trend of hundreds of noisy numbers in a command line log is going slightly up or down - this is much easier to spot in a visualization."
+    "Let's look at the graphs to get some intuition for how the training progressed over time. This is typically important to identify longer-term trends in the training. In practice it's tricky to spot whether the overall trend of 100 or so noisy numbers in a command line log is going slightly up or down - this is much easier to spot in a visualization."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -478,7 +485,18 @@
     "id": "Hlki3bU8JMTT",
     "outputId": "3a9fa5a9-6682-4857-d9e4-656b252bd78b"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "plt.plot(np.arange(loss_hist.shape[0]), loss_hist, \"b\", label=\"Training loss\")\n",
     "plt.plot(np.arange(loss_hist_val.shape[0]), loss_hist_val, \"g\", label=\"Validation loss\")\n",
@@ -508,7 +526,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -518,7 +536,18 @@
     "outputId": "1a473bd9-b3de-463a-cff9-3d886afeda93",
     "scrolled": true
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<Figure size 1600x500 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "net.eval()\n",
     "inputs, targets = next(iter(loader_val))\n",
@@ -559,7 +588,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -568,7 +597,54 @@
     "id": "dD5O58L9HLE-",
     "outputId": "25a66fab-38e3-438f-c2b7-71fbcbf2e3f6"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[93m\u001b[1mWarning:\u001b[22m `airfoils-test` is stored in single-file format. The download might take some time.\u001b[0m\n",
+      "\u001b[96m\u001b[1mSuccess:\u001b[22m Loaded airfoils-test with 10 simulations and 1 samples each.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<Figure size 1600x500 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<Figure size 1600x500 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<Figure size 1600x500 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Average relative test error: 0.026288176793605088\n"
+     ]
+    }
+   ],
    "source": [
     "loader_test = Dataloader( \"airfoils-test\", batch_size=1, normalize_data=None, shuffle=False )\n",
     "loss = nn.L1Loss()\n",
@@ -598,7 +674,7 @@
     "id": "By722sgwFbwG"
    },
    "source": [
-    "The average test error with the default settings should be below 0.025. As the inputs are normalized, this means the average relative error across all three fields is around 2.5% w.r.t. the maxima of each quantity. This is not too bad for new shapes, but clearly leaves room for improvement.\n",
+    "The average test error with the default settings should be close to 0.025. As the inputs are normalized, this means the average relative error across all three fields is around 2.5% w.r.t. the maxima of each quantity. This is not too bad for new shapes, but clearly leaves room for improvement.\n",
     "\n",
     "Looking at the visualizations, you'll notice that especially high-pressure peaks and pockets of larger y-velocities are missing in the outputs. This is primarily caused by the small network, which does not have enough resources to reconstruct details.\n",
     "\n",