Replace unicode escaped characters in ipynb files

PiperOrigin-RevId: 854213767

Author: AleksMat

jax3d/projects/nesf/nerfstatic/NeSF_Visualization_Demo.ipynb

@@ -322,7 +322,7 @@
       },
       "outputs": [],
       "source": [
-        "# Initialize \u0026 load per-scene NeRF models.\n",
+        "# Initialize & load per-scene NeRF models.\n",
         "\n",
         "recovered_nerf_state = semantic_utils.load_all_nerf_variables(\n",
         "    save_dir=params.train.nerf_model_ckpt,\n",
@@ -401,7 +401,7 @@
       },
       "outputs": [],
       "source": [
-        "# Plot XYZ values where density \u003e min_density for various values of min_density.\n",
+        "# Plot XYZ values where density > min_density for various values of min_density.\n",
         "\n",
         "def plot_density_coordinates(kept_points, color=None, ax=None):\n",
         "  ii, jj, kk = kept_points[:, 0], kept_points[:, 1], kept_points[:, 2]\n",
@@ -440,7 +440,7 @@
       },
       "outputs": [],
       "source": [
-        "# Plot XYZ values where density \u003e 0, interactively.\n",
+        "# Plot XYZ values where density > 0, interactively.\n",
         "\n",
         "def plot_density_coordinates_interactive(kept_points, color=None):\n",
         "  assert len(kept_points)\n",
@@ -592,7 +592,7 @@
         "fig = plt.figure(figsize=(len(min_density_values) * 4, 4))\n",
         "axs = []\n",
         "for i, min_density in enumerate(min_density_values):\n",
-        "  mask = sigma_values \u003e min_density\n",
+        "  mask = sigma_values > min_density\n",
         "  kept_points = positions[0][mask[0, :, 0]]\n",
         "  kept_points_color = color_values[0][mask[0, :, 0]]\n",
         "  ax = fig.add_subplot(1, len(min_density_values), i+1, projection='3d')\n",
@@ -673,7 +673,7 @@
         "    *,\n",
         "    semantic_variables: Tree[jnp.ndarray],\n",
         "    semantic_model: volumetric_semantic_model.VolumetricSemanticModel,\n",
-        ") -\u003e f32[\"D n k\"]:\n",
+        ") -> f32[\"D n k\"]:\n",
         "  \"\"\"Predict semantic logits for a set of 3D points.\n",
         "\n",
         "  Args:\n",
@@ -854,7 +854,7 @@
         "# Visualize semantic model predictions across 3D lattice of points.\n",
         "\n",
         "MIN_DENSITY = 16\n",
-        "mask = sigma_values \u003e MIN_DENSITY\n",
+        "mask = sigma_values > MIN_DENSITY\n",
         "kept_points = positions[0][mask[0, :, 0]]\n",
         "kept_points_color = semantic_predictions[0][mask[0, :, 0]]\n",
         "print(kept_points.shape)\n",
@@ -913,7 +913,7 @@
         "\n",
         "  points = ray_o + depth * ray_d\n",
         "\n",
-        "  mask = np.all((points \u003e= -1) \u0026 (points \u003c= 1), axis=-1)\n",
+        "  mask = np.all((points >= -1) & (points <= 1), axis=-1)\n",
         "\n",
         "  select_points = points[mask]\n",
         "  select_semantics = semantics[mask]\n",
@@ -929,7 +929,7 @@
       },
       "outputs": [],
       "source": [
-        "# Construct labeled semantic point cloud from ground truth dataset (i.e. using semantic masks, ray origins \u0026 directions from known cameras, and depth)\n",
+        "# Construct labeled semantic point cloud from ground truth dataset (i.e. using semantic masks, ray origins & directions from known cameras, and depth)\n",
         "\n",
         "labeled_point_cloud = construct_labeled_point_cloud(examples)"
       ]