We’ll use this as the basis for the auto rotoscoping. Make sure your virtual environment is activated (see above) and type: conda install torchvision -c pytorchĬonda install -c anaconda pillow Step 3: Download the sample codeĬlick here to download the code that we modified from. To use the code, we need to install some of the third party libraries required for it to run. You can treat things like “black boxes” and just reap the benefits.
The great thing about modern programming is that you don’t need to fully understand how something works to use the code. We’ll be working with code provided by, an amazing website for learning about computer vision and machine learning. To exit out of a virtual environment, just type: conda deactivate Step 2: Install the libraries we need Once you have Anaconda installed on your system, open the Anaconda prompt (or the regular Terminal on OS X) and execute the following commands to create and activate a custom virtual environment (which we’ll call ‘autoroto’-you can choose any name you like): conda create -name autoroto (Click here to download Anaconda for your platform) It also makes virtual environments easy: virtual environments are development ‘sandboxes’ you can experiment in without messing up any other software installed on your computer. Step 1: Install AnacondaĪnaconda is an amazing installer package for Python that allows you to install third party software without having to search the web for it. Half the battle is getting everything installed right, so I’ve made sure to clearly lay out all the details in the video. In this ‘Impossible Shot’ video you’ll get a good intro to programming in Python and come out the other side with an amazing rotoscoping tool that you can put into use in production today. Most beginner programming tutorials start with some lame text-based guessing game.
What’s better, you can start to learn a little Python in the process. And with just a couple of lines of code you-the unskilled, non-programmer-can have that machine learning goodness at your command. We’re still a few years away from where machine learning AI can produce rotoscoping that rivals what human artists can achieve (though only a very few), but even today machine learning offers results that are more than adequate for color correction, camera tracking garbage mattes, or temp roto for slap comps while waiting on final outsourced roto.
0 kommentar(er)
