Name: TensorFlow高級API。第3部分 - 構建和完善你的模型 (TensorFlow high-level APIs: Part 3 - Building and refining your models)
Uploaded: 2021-01-14T10:38:09.000Z
Duration: 7 min 26 s
Description: 【看影片學英語】數萬部 YouTube 影片，搭配英漢字典即點即查，輕鬆掌握單字發音與用法，長久累積看電影不必再看字幕。

KARMEL ALLISON: Hi and welcome to Coding TensorFlow.

I'm Karmel Allison, and I'm here to guide you

through a scenario using TensorFlow's high-level APIs.

and how to prepare your data for machine learning.

We then moved on to optimizing your data for machine learning

We will start with a simple sequential model, which

and then we go through some standard densely connected

Our final layer here will output the class predictions

Notice here that we are just establishing the architecture

Once we have the layer architecture established,

we can compile the model, which adds the optimizer, loss,

TensorFlow provides a number of optimizers and lost choices,

We pass our data set into our model, and we train.

Now in a real world situation with large data sets,

we would likely want to leverage hardware accelerators

And we may even want to distribute training

You can find out more about using distribution strategies

for this in the links included in the description below.

So for now I will just point out that the same code will

work in the distributed settings and when

For now, we will just assume that we will wait

Once it's done training, you can test it.

we first need to load in our validation data.

It's important here that we use the same processing procedure

for our test data that we did for our training data.

So maybe we'll define a function that we can use in both cases

with the validation data, which returns the loss and accuracy

Note here that because we took care of our data

we know that the transformation of our input validation data

will happen in the same way as it did for our training

data, which is critical to ensuring repeatable results.

So now we validated our model on independent

held out data that was processed in the same way as our training

There is a lot of tooling that is required

for real world deployment, which the library TFX makes possible.

I put a link to this in the description below.

TensorFlow provides a model saving format

that works with the suite of TensorFlow products,

including TensorFlow Serving and TensorFlow.js.

The TensorFlow saved model includes a checkpoint with all

of the weights and variables, and it also includes the graph

that we built for training, evaluating, and predicting.

This saved model is a fully contained serialization

of your model, so you can load it back into Python later

if you want to retrain or reuse your model.

And now we've gone through all of the critical stages

to build a model for our data in TensorFlow.

It could be that this is the perfect model, and we're happy.

But then we'd all have to go and find new jobs,

so let's assume that we want to improve the accuracy

There are lots of places we might decide to make changes.

We could change the way we process and parse the data.

We could change the optimizer or the loss.

We could try different hyper parameters and so on.

to use the same data and features to try out

one of TensorFlow's canned estimators, which

are built in implementations of some more

complex models including those that don't fit nicely

字幕列表影片播放

TensorFlow高級API。第3部分 - 構建和完善你的模型 (TensorFlow high-level APIs: Part 3 - Building and refining your models)

assume

process

critical

grab