Enter the URL of the YouTube video to download subtitles in many different formats and languages.
JASON MAYES: When you're\nworking with a library
like TensorFlow.js\nthat you just saw
there are three key ways\nyou can use or create
The first and easiest\nway to get started
These are [INAUDIBLE] models\nthat someone else has already
trained that you can reuse\nfor the same use case.
More often than not, you'll\nfind that a model exists
that already does what you need\nto do that a company may have
made publicly available\nlike recognizing
the pose of a human\nbody, for example
State-of-the-art models like\nthis exist that have been
trained on huge amounts of data\nand are typically very robust
Even better, they are\nusually well tested
in real-world situations,\nmeaning they're probably
Some state-of-the-art models\neven have associated model
cards as shown on this slide,\nwhich you can check to see how
it performs, for data it is used\nto train on, and if there are
any known issues to be\naware of when using it.
In this course, you will learn\nhow to use pre-made models
and while some are easy\nto use than others
all can save you a huge amount\nof time gathering training
data and, of course, the\ncosts of development, too.
In fact, some state-of-the-art\nmodels can take weeks to train
a working model using very\nexpensive hardware before
Next up, you have\ntransfer learning.
This allows you to take\ncertain pre-trained models
and retrain them to learn\na new, similar task using
If you have a model that's\ngreat at image recognition--
maybe it can already recognize\ndogs, tables, and chairs--
you can easily\nretrain that model
to recognize, say, cats, as\nit already has the building
blocks to find a\nvariety of objects
in an image, which it can then\nuse to find other objects, too.
You actually saw this in\naction earlier in the course
when you learned to\nuse Teachable Machine.
Here, you gave the\nmodel some new imagery
from which it builds upon\nits previous understanding
of the world in order to\nsolve the new task in a very
Finally, you can choose to\ncreate your own models starting
with a completely blank\ncanvas using the TensorFlow.js
This is useful when there's\nno existing model type that's
suitable for your task at\nhand, or maybe the ones that
do exist are not fast enough\nor take up too much memory.
In this case, you can try\nto write and then train
your own model architectures\nthat can solve these problems.
More often than\nnot, few people will
need to work at this\nlevel, but we'll
touch on this later in\nthe course to give you
In fact, most people\nwill do just fine
by building on top\nof pre-made models
or use transfer learning\nfor their custom data
enabling them to work\nfaster and, of course
leveraging cutting-edge\nresearch that
is known to be battle hardened\nand known to work well
So in summary here,\nwith TensorFlow.js
you can run existing\npre-made models
retrain models by\na transfer learning
to work on your own data, or\nwrite your own custom models
completely from scratch,\njust like some of you
might already be doing in Python\nbut in JavaScript or Node.js.
Now, TensorFlow.js is\nalso able to support
the execution of other\nforms of TensorFlow models
either directly or through our\ncommand line converter, which
might be useful if the\nresearch you want to use
is initially in\na different form.
You'll learn more about\ndealing with conversion
Now with that, it's time to\ndive deeper into pre-made models
to see what exists and to\nstart writing some code
So let's head on to\nthe next chapter.