# Types of file formats in TensorFlow and data handling

/ / درس 4

### توضیح مختصر

• زمان مطالعه 0 دقیقه
• سطح خیلی سخت

### دانلود اپلیکیشن «زوم»

این درس را می‌توانید به بهترین شکل و با امکانات عالی در اپلیکیشن «زوم» بخوانید

### فایل ویدیویی

برای دسترسی به این محتوا بایستی اپلیکیشن زبانشناس را نصب کنید.

### متن انگلیسی درس

Hi and welcome to this coding lecture.

Let’s import num pi and Matt.

Plot lib and of course the tensor flow library.

We will import tensor flow as TAF.

Next we will generate fake data.

Once again this code is virtually the same as the one we used before.

There is a single line of code difference.

Let’s look at it for each project you work on you’ll have a dataset.

Perhaps you are used to excel OSX or CSP files.

However tensor flow doesn’t work well with them.

It is tensor based so it likes tenses.

Therefore we want a format that can store the information in tenses.

One solution to this problem is NPC files.

That’s basically num PI’s file type.

It allows you to save n d arrays or end dimensional arrays thinking like computer scientists.

We can say tensor is can be represented as Multi-dimensional arrays.

When we read an MP Z file the data is already organized in the desired way.

Often this is an important part of Deep Learning pre processing.

You are given data in a specific file format.

Then you open it pre process it and finally save it into an NPC later.

You build your algorithm using the NPC instead of the original file.

OK back to the code.

As you can see we have named the inputs and targets we generated generated inputs and generated targets.

Next we can simply save them into a tensor friendly file the proper way to do that is to use the NPC

saves method.

It involves several arguments.

The first one is the file name it is written in quotation marks.

I’ll call it TAF underscore intro.

Then we must indicate the objects we want to save into the file.

The syntax is as follows the label we want to assign to the ending array equals the array we want to

save under that label.

For us the label is inputs and is equal to the generated inputs array similarly.

The targets are equal to the generated targets.

Note it is not required to call them inputs and targets if we would like to we could call them with