Deploying to main from @ geometric-intelligence/TopoBench@0579351 🚀

Author: gbg141

topobenchmarkx/.doctrees/environment.pickle

@@ -22,7 +22,27 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Imports"
+    "### <font color='289C4E'>Table of contents<font><a class='anchor' id='top'></a>\n",
+    "&emsp;[1. Imports](##sec1)\n",
+    "\n",
+    "&emsp;[2. Configurations and utilities](##sec2)\n",
+    "\n",
+    "&emsp;[3. Defining the lifting](##sec2)\n",
+    "\n",
+    "&emsp;[4. Loading the data](##sec3)\n",
+    "\n",
+    "&emsp;[5. Model initialization](##sec4)\n",
+    "\n",
+    "&emsp;[6. Training](##sec5)\n",
+    "\n",
+    "&emsp;[7. Testing the model](##sec6)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 1. Imports <a class=\"anchor\" id=\"sec1\"></a>"
    ]
   },
   {
@@ -60,7 +80,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Configurations and utilities"
+    "## 2. Configurations and utilities <a class=\"anchor\" id=\"sec2\"></a>"
    ]
   },
   {
@@ -152,7 +172,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Defining the lifting"
+    "## 3. Defining the lifting  <a class=\"anchor\" id=\"sec3\"></a>"
    ]
   },
   {
@@ -206,7 +226,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Loading the data"
+    "## 4. Loading the data  <a class=\"anchor\" id=\"sec4\"></a>"
    ]
   },
   {
@@ -233,11 +253,10 @@
    "metadata": {},
    "outputs": [
     {
-     "name": "stderr",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Processing...\n",
-      "Done!\n"
+      "Transform parameters are the same, using existing data_dir: ./data/MUTAG/MUTAG/clique_lifting/458544608\n"
      ]
     }
    ],
@@ -255,7 +274,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Model initialization"
+    "## 5. Model initialization  <a class=\"anchor\" id=\"sec5\"></a>"
    ]
   },
   {
@@ -304,7 +323,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Training"
+    "## 6. Training  <a class=\"anchor\" id=\"sec6\"></a>"
    ]
   },
   {
@@ -316,14 +335,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "GPU available: True (mps), used: False\n",
+      "GPU available: True (cuda), used: False\n",
       "TPU available: False, using: 0 TPU cores\n",
       "IPU available: False, using: 0 IPUs\n",
       "HPU available: False, using: 0 HPUs\n",
@@ -344,6 +363,7 @@
     }
    ],
    "source": [
+    "%%capture\n",
     "# Increase the number of epochs to get better results\n",
     "trainer = pl.Trainer(max_epochs=50, accelerator=\"cpu\", enable_progress_bar=False)\n",
     "\n",
@@ -353,34 +373,37 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "train/accuracy :     0.7573964595794678\n",
-      "train/precision :     0.737596869468689\n",
-      "train/recall :     0.6920425891876221\n",
-      "val/loss :     0.6638099551200867\n",
-      "val/accuracy :     0.7894737124443054\n",
-      "val/precision :     0.7749999761581421\n",
-      "val/recall :     0.7115384340286255\n",
-      "train/loss :     0.5858408808708191\n"
+      "      Training metrics\n",
+      " --------------------------\n",
+      "train/accuracy:       0.7633\n",
+      "train/precision:      0.7352\n",
+      "train/recall:         0.7310\n",
+      "val/loss:             0.7276\n",
+      "val/accuracy:         0.7895\n",
+      "val/precision:        0.7750\n",
+      "val/recall:           0.7115\n",
+      "train/loss:           0.7212\n"
      ]
     }
    ],
    "source": [
+    "print('      Training metrics\\n', '-'*26)\n",
     "for key in train_metrics:\n",
-    "    print(key,\":    \", train_metrics[key].item())"
+    "    print('{:<21s} {:>5.4f}'.format(key+':', train_metrics[key].item()))"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Testing the model"
+    "## 7. Testing the model  <a class=\"anchor\" id=\"sec7\"></a>"
    ]
   },
   {
@@ -390,6 +413,17 @@
     "Finally, we can test the model and obtain the results."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%capture\n",
+    "trainer.test(model, datamodule)\n",
+    "test_metrics = trainer.callback_metrics"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 12,
@@ -399,55 +433,20 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/opt/miniconda3/envs/topox/lib/python3.11/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:441: The 'test_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=13` in the `DataLoader` to improve performance.\n"
+      "      Testing metrics\n",
+      " -------------------------\n",
+      "test/loss:           0.7276\n",
+      "test/accuracy:       0.7895\n",
+      "test/precision:      0.7750\n",
+      "test/recall:         0.7115\n"
      ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
-       "┃<span style=\"font-weight: bold\">        Test metric        </span>┃<span style=\"font-weight: bold\">       DataLoader 0        </span>┃\n",
-       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
-       "│<span style=\"color: #008080; text-decoration-color: #008080\">       test/accuracy       </span>│<span style=\"color: #800080; text-decoration-color: #800080\">    0.7894737124443054     </span>│\n",
-       "│<span style=\"color: #008080; text-decoration-color: #008080\">         test/loss         </span>│<span style=\"color: #800080; text-decoration-color: #800080\">    0.6638099551200867     </span>│\n",
-       "│<span style=\"color: #008080; text-decoration-color: #008080\">      test/precision       </span>│<span style=\"color: #800080; text-decoration-color: #800080\">    0.7749999761581421     </span>│\n",
-       "│<span style=\"color: #008080; text-decoration-color: #008080\">        test/recall        </span>│<span style=\"color: #800080; text-decoration-color: #800080\">    0.7115384340286255     </span>│\n",
-       "└───────────────────────────┴───────────────────────────┘\n",
-       "</pre>\n"
-      ],
-      "text/plain": [
-       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
-       "┃\u001b[1m \u001b[0m\u001b[1m       Test metric       \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      DataLoader 0       \u001b[0m\u001b[1m \u001b[0m┃\n",
-       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
-       "│\u001b[36m \u001b[0m\u001b[36m      test/accuracy      \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m   0.7894737124443054    \u001b[0m\u001b[35m \u001b[0m│\n",
-       "│\u001b[36m \u001b[0m\u001b[36m        test/loss        \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m   0.6638099551200867    \u001b[0m\u001b[35m \u001b[0m│\n",
-       "│\u001b[36m \u001b[0m\u001b[36m     test/precision      \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m   0.7749999761581421    \u001b[0m\u001b[35m \u001b[0m│\n",
-       "│\u001b[36m \u001b[0m\u001b[36m       test/recall       \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m   0.7115384340286255    \u001b[0m\u001b[35m \u001b[0m│\n",
-       "└───────────────────────────┴───────────────────────────┘\n"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
     }
    ],
    "source": [
-    "trainer.test(model, datamodule)\n",
-    "test_metrics = trainer.callback_metrics"
+    "print('      Testing metrics\\n', '-'*25)\n",
+    "for key in test_metrics:\n",
+    "    print('{:<20s} {:>5.4f}'.format(key+':', test_metrics[key].item()))"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {