Update frames_from_video_file function in video tutorials

PiperOrigin-RevId: 485426940

Author: shilpakancharla

site/en/tutorials/load_data/video.ipynb

@@ -91,6 +91,18 @@
         "[remotezip](https://github.com/gtsystem/python-remotezip){:.external} to inspect the contents of a ZIP file, [tqdm](https://github.com/tqdm/tqdm){:.external} to use a progress bar, [OpenCV](https://opencv.org/){:.external} to process video files, and [`tensorflow_docs`](https://github.com/tensorflow/docs/tree/master/tools/tensorflow_docs){:.external} for embedding data in a Jupyter notebook."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "SjI3AaaO16bd"
+      },
+      "outputs": [],
+      "source": [
+        "# The way this tutorial uses the `TimeDistributed` layer requires TF>=2.10\n",
+        "!pip install -U tensorflow>=2.10.0"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -616,13 +628,15 @@
         "    start = random.randint(0, max_start + 1)\n",
         "\n",
         "  src.set(cv2.CAP_PROP_POS_FRAMES, start)\n",
+        "  # ret is a boolean indicating whether read was successful, frame is the image itself\n",
         "  ret, frame = src.read()\n",
         "  result.append(format_frames(frame, output_size))\n",
         "\n",
         "  for _ in range(n_frames - 1):\n",
+        "    for _ in range(frame_step):\n",
+        "      ret, frame = src.read()\n",
         "    if ret:\n",
-        "      frame = tf.image.convert_image_dtype(frame, tf.float32)\n",
-        "      frame = tf.image.resize_with_pad(frame, *output_size)\n",
+        "      frame = format_frames(frame, output_size)\n",
         "      result.append(frame)\n",
         "    else:\n",
         "      result.append(np.zeros_like(result[0]))\n",
@@ -936,6 +950,7 @@
         "net.trainable = False\n",
         "\n",
         "model = tf.keras.Sequential([\n",
+        "    tf.keras.layers.Rescaling(scale=255),\n",
         "    tf.keras.layers.TimeDistributed(net),\n",
         "    tf.keras.layers.Dense(10),\n",
         "    tf.keras.layers.GlobalAveragePooling3D()\n",
@@ -957,6 +972,8 @@
     "colab": {
       "collapsed_sections": [],
       "name": "video.ipynb",
+      "private_outputs": true,
+      "provenance": [],
       "toc_visible": true
     },
     "kernelspec": {

site/en/tutorials/video/video_classification.ipynb

@@ -133,7 +133,6 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "cellView": "form",
         "id": "nB2aOTU35r9_"
       },
       "outputs": [],
@@ -308,13 +307,15 @@
         "    start = random.randint(0, max_start + 1)\n",
         "\n",
         "  src.set(cv2.CAP_PROP_POS_FRAMES, start)\n",
+        "  # ret is a boolean indicating whether read was successful, frame is the image itself\n",
         "  ret, frame = src.read()\n",
         "  result.append(format_frames(frame, output_size))\n",
         "\n",
         "  for _ in range(n_frames - 1):\n",
+        "    for _ in range(frame_step):\n",
+        "      ret, frame = src.read()\n",
         "    if ret:\n",
-        "      frame = tf.image.convert_image_dtype(frame, tf.float32)\n",
-        "      frame = tf.image.resize_with_pad(frame, *output_size)\n",
+        "      frame = format_frames(frame, output_size)\n",
         "      result.append(frame)\n",
         "    else:\n",
         "      result.append(np.zeros_like(result[0]))\n",
@@ -1017,6 +1018,7 @@
     "colab": {
       "collapsed_sections": [],
       "name": "video_classification.ipynb",
+      "provenance": [],
       "toc_visible": true
     },
     "kernelspec": {