Fix broken notebook - n_frames and label_frames in Video Classification tutorial

PiperOrigin-RevId: 493099684

Author: 8bitmp3

site/en/tutorials/video/video_classification.ipynb

@@ -59,14 +59,14 @@
         "id": "L2MHy42s5wl6"
       },
       "source": [
-        "# Video classification with a 3D convolutional neural network (CNN)\n",
+        "# Video classification with a 3D convolutional neural network\n",
         "\n",
-        "This tutorial demonstrates training a 3D convolutional neural network for video classification using the [UCF101](https://www.crcv.ucf.edu/data/UCF101.php) action recognition dataset. A 3D CNN uses a three dimensional filter to perform convolutions. The kernel is able to slide in three directions, whereas in a 2D CNN it can slide in two dimensions. The model is based on the work published in [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://arxiv.org/abs/1711.11248v3) by D. Tran et al. (2017).  In this tutorial, you will: \n",
+        "This tutorial demonstrates training a 3D convolutional neural network (CNN) for video classification using the [UCF101](https://www.crcv.ucf.edu/data/UCF101.php) action recognition dataset. A 3D CNN uses a three-dimensional filter to perform convolutions. The kernel is able to slide in three directions, whereas in a 2D CNN it can slide in two dimensions. The model is based on the work published in [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://arxiv.org/abs/1711.11248v3) by D. Tran et al. (2017).  In this tutorial, you will:\n",
         "\n",
         "* Build an input pipeline\n",
         "* Build a 3D convolutional neural network model with residual connections using Keras functional API\n",
         "* Train the model\n",
-        "* Evaluate and test the model \n",
+        "* Evaluate and test the model\n",
         "\n",
         "This video classification tutorial is the second part in a series of TensorFlow video tutorials. Here are the other three tutorials:\n",
         "\n",
@@ -378,7 +378,7 @@
         "download_dir = pathlib.Path('./UCF101_subset/')\n",
         "subset_paths = download_ufc_101_subset(URL, \n",
         "                        num_classes = 10, \n",
-        "                        splits = {\"train\": 30, \"val\": 10, \"test\": 10}, \n",
+        "                        splits = {\"train\": 30, \"val\": 10, \"test\": 10},\n",
         "                        download_dir = download_dir)"
       ]
     },
@@ -400,22 +400,27 @@
       },
       "outputs": [],
       "source": [
+        "n_frames = 10\n",
+        "batch_size = 8\n",
+        "\n",
         "output_signature = (tf.TensorSpec(shape = (None, None, None, 3), dtype = tf.float32),\n",
         "                    tf.TensorSpec(shape = (), dtype = tf.int16))\n",
-        "train_ds = tf.data.Dataset.from_generator(FrameGenerator(subset_paths['train'], 10, training = True),\n",
+        "\n",
+        "train_ds = tf.data.Dataset.from_generator(FrameGenerator(subset_paths['train'], n_frames, training=True),\n",
         "                                          output_signature = output_signature)\n",
         "\n",
+        "\n",
         "# Batch the data\n",
-        "train_ds = train_ds.batch(8)\n",
+        "train_ds = train_ds.batch(batch_size)\n",
         "\n",
-        "val_ds = tf.data.Dataset.from_generator(FrameGenerator(subset_paths['val'], 10),\n",
+        "val_ds = tf.data.Dataset.from_generator(FrameGenerator(subset_paths['val'], n_frames),\n",
         "                                        output_signature = output_signature)\n",
-        "val_ds = val_ds.batch(8)\n",
+        "val_ds = val_ds.batch(batch_size)\n",
         "\n",
-        "test_ds = tf.data.Dataset.from_generator(FrameGenerator(subset_paths['test'], 10),\n",
+        "test_ds = tf.data.Dataset.from_generator(FrameGenerator(subset_paths['test'], n_frames),\n",
         "                                         output_signature = output_signature)\n",
         "\n",
-        "test_ds = test_ds.batch(8)"
+        "test_ds = test_ds.batch(batch_size)"
       ]
     },
     {
@@ -898,7 +903,7 @@
         "  ax.set_xlabel('Predicted Action')\n",
         "  ax.set_ylabel('Actual Action')\n",
         "  plt.xticks(rotation=90)\n",
-        "  plt.yticks(rotation=0) \n",
+        "  plt.yticks(rotation=0)\n",
         "  ax.xaxis.set_ticklabels(labels)\n",
         "  ax.yaxis.set_ticklabels(labels)"
       ]
@@ -911,8 +916,8 @@
       },
       "outputs": [],
       "source": [
-        "fg = FrameGenerator(subset_paths['train'], num_frames, training = True)\n",
-        "label_names = list(fg.class_ids_for_name.keys())"
+        "fg = FrameGenerator(subset_paths['train'], n_frames, training=True)\n",
+        "labels = list(fg.class_ids_for_name.keys())"
       ]
     },
     {
@@ -945,7 +950,7 @@
         "id": "FefzeIZz-9aI"
       },
       "source": [
-        "The precision and recall values for each class can also be calculated using a confusion matrix. "
+        "The precision and recall values for each class can also be calculated using a confusion matrix."
       ]
     },
     {
@@ -1026,7 +1031,7 @@
         "id": "d4WsP4Z2HZ6L"
       },
       "source": [
-        "## Next Steps\n",
+        "## Next steps\n",
         "\n",
         "To learn more about working with video data in TensorFlow, check out the following tutorials:\n",
         "\n",