Update usage example - add print to torch_model

Author: Neumann, Jan

USAGE_EXAMPLE.ipynb

@@ -13,19 +13,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "32e5812a-31f3-4f49-bee7-7edb3c52b60f",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/janeumann/dev/tools/mambaforge/envs/neuralogic-torch3/lib/python3.11/site-packages/neuralogic/core/builder/builder.py:4: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from tqdm.autonotebook import tqdm\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import compute_graph_vectorize.engines.torch as torch_engine\n",
     "from compute_graph_vectorize.engines.torch.settings import TorchModuleSettings\n",
@@ -515,14 +506,70 @@
    "execution_count": 18,
    "id": "cd9ee387-f2d5-451c-8b90-f69f99a06428",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "NetworkModule(\n",
+       "  (params_module): NetworkParams(\n",
+       "    (params): ParameterDict(\n",
+       "        (f_node_feature__f__0): Parameter containing: [torch.FloatTensor of size 7x7x1]\n",
+       "        (w_000): Parameter containing: [torch.FloatTensor of size 1x10x7]\n",
+       "        (w_001): Parameter containing: [torch.FloatTensor of size 1x10x10]\n",
+       "        (w_002): Parameter containing: [torch.FloatTensor of size 1x1x10]\n",
+       "    )\n",
+       "  )\n",
+       "  (batch_modules): ModuleList(\n",
+       "    (0): Sequential(\n",
+       "      (0): LayerModule(\n",
+       "        out_key: l_predict__wa,\n",
+       "        expected_count: 188,\n",
+       "        (the_modules): ModuleList(\n",
+       "          (0): RetrieveRefModule(f_node_feature__f__0)\n",
+       "          (1): LinearModule(\n",
+       "            (retrieve_weights): Sequential(\n",
+       "              (0): RetrieveRefModule(w_000)\n",
+       "            )\n",
+       "          )\n",
+       "          (2): GenericGatherModule([0, 0, 0, ... (size: 75)])\n",
+       "          (3): SegmentCSR(reduce=sum, count=28)\n",
+       "          (4): ReLU()\n",
+       "          (5): LinearModule(\n",
+       "            (retrieve_weights): Sequential(\n",
+       "              (0): RetrieveRefModule(w_001)\n",
+       "            )\n",
+       "          )\n",
+       "          (6): GenericGatherModule([0, 1, 0, ... (size: 556)])\n",
+       "          (7): SegmentCSR(reduce=sum, count=223)\n",
+       "          (8): GenericGatherModule([0, 1, 0, ... (size: 3371)])\n",
+       "          (9): SegmentCSR(reduce=mean, count=188)\n",
+       "          (10): LinearModule(\n",
+       "            (retrieve_weights): Sequential(\n",
+       "              (0): RetrieveRefModule(w_002)\n",
+       "            )\n",
+       "          )\n",
+       "          (11): Sigmoid()\n",
+       "        )\n",
+       "      )\n",
+       "      (1): RetrieveRefModule(l_predict__wa)\n",
+       "    )\n",
+       "  )\n",
+       ")"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "torch_model = torch_engine.build_torch_model(\n",
     "        vectorized_network,\n",
     "        t_settings,\n",
     "        debug=debug,\n",
     "        final_layer_only=final_layer_only\n",
-    ")"
+    ")\n",
+    "torch_model"
    ]
   },
   {