Original subtitles

In this video, we'll show you how to use YOLO v seven to detect eight different object classes in an

image.

However, in this video we will perform the detection on Google collect.

Make sure you have YOLO v seven installed on Google collect before starting the detection to begin once

a web browser, then go to the Google color view URL.

After that opened the all of seven notebook.

Continue to scroll down.

Navigate to the the text and section.

This circle is used to mount Google Drive.

Here's the explanation.

In fourth.

Try from Google Color with this command.

Then this command is used to one Google drive.

When the sale by pressing the following button.

Click Connect to Google Drive.

Exclusive Google Drive account.

Scroll down and click the allow button.

Continue to the next cell.

This cell is used to enter my drive.

Here's the explanation.

This command is used to import OS.

This command is to create a constant containing the string drive.

My drive.

To access my drive.

Use this command.

When the sale by pressing the following button.

Continue to the next cell.

This cell is used to enter the root folder of your office.

Seven.

We used the command city YOLO v seven.

To view the contents of a folder used to command.

When the sale by pressing the following button.

After that, this code cell is used for detection.

We will detect objects in the image here, but the source is a folder containing several images, not

a single file.

The folder is called inference images.

Because color cannot directly display the detection results.

It cannot use the view image argument.

Use the following command to perform detection.

Python detect the p.

That's.

That's why it's YOLO v seven.

We use 0.5.

In contrast, in the image size, we use 640.

Insults, inference images.

Run the sale by pressing the following button.

Went for the detection process to fitness.

Here are the results.

There have been several images detected.

The detection results are saved in the folder below.

Then in the following cell, we read a function to display the image.

Kite blood from Epworth is used to display the immense.

Image from map of the bees used to read the image.

Following that, we create a self image function.

With one parameter, the image path.

The function contains several lines of program code.

The image is read using this code.

This code is used to specify the size of the displayed image.

The access is hidden using this code.

The image is displayed using the skull.

When the sale by pressing the following button.

Proceed to the next cell.

The cell image function will be called in this cell to display the image.

In this example, we will display the detection results on the horses dot jpg image.

Blocking its path.

Then copy by pressing control.

See?

Delete previous parameters.

Face the image by pressing control of the.

Then run the sale by pressing the following button.

It will then look like this.

The next video will explain how to detect objects on video.

See you in the next video.