documentation, arxiv v0.2.15

Author: bartzbeielstein

docs/bart23e.html

@@ -13916,7 +13916,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.10.11"
+      "version": "3.10.10"
     }
   },
   "nbformat": 4,

docs/bart23e.pdf

@@ -407,7 +407,14 @@
         "        x = self.fc3(x)\n",
         "        return x\n",
         "\n",
-        "```\n",
+        "```\n"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
         "\n",
         "#### The `Net_Core` class\n",
         "\n",
@@ -438,7 +445,13 @@
         "        self.sgd_momentum = sgd_momentum\n",
         "```\n",
         "\n",
-        ":::{.callout-note}\n",
+        ":::{.callout-note}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
         "\n",
         "\n",
         "We see that the class `Net_lin_reg` has additional attributes and does not inherit from `nn` directly. It adds an additional class, `Net_core`, that takes care of additional attributes that are common to all neural network models, e.g., the learning rate multiplier `lr_mult` or the batch size `batch_size`.\n",
@@ -63168,12 +63181,12 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {},
       "source": [
         "\n",
-        "## Tensorboard {#sec-tensorboard}\n",
-        "\n"
+        "## Tensorboard {#sec-tensorboard}"
       ]
     },
     {
@@ -63389,13 +63402,14 @@
         "\n",
         "\n",
         "```{raw}\n",
-        "Net_CIFAR10(\n",
-        "  (conv1): Conv2d(3, 6, kernel_size=(5, 5), stride=(1, 1))\n",
-        "  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
-        "  (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))\n",
-        "  (fc1): Linear(in_features=400, out_features=64, bias=True)\n",
+        "Net_lin_reg(\n",
+        "  (fc1): Linear(in_features=10, out_features=64, bias=True)\n",
         "  (fc2): Linear(in_features=64, out_features=32, bias=True)\n",
-        "  (fc3): Linear(in_features=32, out_features=10, bias=True)\n",
+        "  (fc3): Linear(in_features=32, out_features=1, bias=True)\n",
+        "  (relu): ReLU()\n",
+        "  (softmax): Softmax(dim=1)\n",
+        "  (dropout1): Dropout(p=0.0, inplace=False)\n",
+        "  (dropout2): Dropout(p=0.0, inplace=False)\n",
         ")\n",
         "```\n",
         "\n"
@@ -84464,9 +84478,12 @@
       "metadata": {},
       "source": [
         "```{raw}\n",
-        "Loss on hold-out set: 1.2267619131326675\n",
-        "Accuracy on hold-out set: 0.58955\n",
-        "Early stopping at epoch 13\n",
+        "Epoch: 1\n",
+        "Loss on hold-out set: 0.17853929138431945\n",
+        "MeanAbsoluteError value on hold-out data: 0.3907899856567383\n",
+        "Epoch: 2\n",
+        "Loss on hold-out set: 0.17439044278115035\n",
+        "MeanAbsoluteError value on hold-out data: 0.38570401072502136\n",
         "```\n",
         "\n",
         "If `path` is set to a filename, e.g., `path = \"model_spot_trained.pt\"`, the weights of the trained model will be loaded from this file."
@@ -84509,6 +84526,18 @@
         "            task=fun_control[\"task\"],)"
       ]
     },
+    {
+      "cell_type": "raw",
+      "metadata": {},
+      "source": [
+        "Loss on hold-out set: 1.85966069472272e-05\n",
+        "MeanAbsoluteError value on hold-out data: 0.0021022311411798\n",
+        "Final evaluation: Validation loss: 1.85966069472272e-05\n",
+        "Final evaluation: Validation metric: 0.0021022311411798\n",
+        "----------------------------------------------\n",
+        "(1.85966069472272e-05, nan, tensor(0.0021))"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -220752,7 +220781,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.10.11"
+      "version": "3.10.10"
     }
   },
   "nbformat": 4,