diff --git a/scenarios/action_recognition/00_webcam.ipynb b/scenarios/action_recognition/00_webcam.ipynb index c6c548f4f..c57706305 100644 --- a/scenarios/action_recognition/00_webcam.ipynb +++ b/scenarios/action_recognition/00_webcam.ipynb @@ -54,15 +54,14 @@ "name": "stdout", "output_type": "stream", "text": [ - "3.7.6 (default, Jan 8 2020, 19:59:22) \n", - "[GCC 7.3.0] \n", + "3.8.5 (default, Sep 3 2020, 21:29:08) [MSC v.1916 64 bit (AMD64)] \n", "\n", - "PyTorch 1.2.0 \n", + "PyTorch 1.7.1+cu110 \n", "\n", - "Torch-vision 0.4.0a0 \n", + "Torch-vision 0.8.2+cu110 \n", "\n", "Available devices:\n", - "0: Tesla K80\n" + "0: NVIDIA GeForce GTX 1650\n" ] } ], @@ -72,22 +71,27 @@ "from collections import deque #\n", "import io\n", "import requests\n", + "import urllib.request\n", "import os\n", "from time import sleep, time\n", "from threading import Thread\n", "from IPython.display import Video\n", "\n", "# Third party tools\n", + "import cv2\n", "import decord #\n", "import IPython.display #\n", + "from IPython.display import display\n", "from ipywebrtc import CameraStream, ImageRecorder\n", "from ipywidgets import HBox, HTML, Layout, VBox, Widget, Label\n", + "import ipywidgets as widgets\n", "import numpy as np\n", "from PIL import Image\n", "import torch\n", "import torch.cuda as cuda\n", "import torch.nn as nn\n", "from torchvision.transforms import Compose\n", + "from matplotlib import cm\n", "\n", "# utils_cv\n", "sys.path.append(\"../../\")\n", @@ -187,7 +191,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Using cache found in /home/jiata/.cache/torch/hub/moabitcoin_ig65m-pytorch_master\n" + "Using cache found in C:\\Users\\mumin/.cache\\torch\\hub\\moabitcoin_ig65m-pytorch_master\n" ] } ], @@ -212,7 +216,7 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 5, "metadata": { "nbpresent": { "id": "eb1dfefe-dfe4-46e4-8482-9b2bc1d05b89" @@ -234,7 +238,7 @@ " 'auctioning']" ] }, - "execution_count": 20, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -252,7 +256,7 @@ } }, "source": [ - "Among them, we will use 50 classes that we are interested in (i.e. the actions make sense to demonstrate in front of the webcam) and ignore other classes by filtering out from the model outputs. This will help us reduce the noise during prediction." + "Among them, we will use 50 classes that we are interested in (i.e. the actions make sense to demonstrate in front of the webcam or ip camera) and ignore other classes by filtering out from the model outputs. This will help us reduce the noise during prediction." ] }, { @@ -352,15 +356,24 @@ "For this example, we'll use the following video:" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Download the video to our data folder" + ] + }, { "cell_type": "code", "execution_count": 7, - "metadata": {}, + "metadata": { + "scrolled": false + }, "outputs": [ { "data": { "text/html": [ - "