Original subtitles

In the previous video, we have done training and have tried to detect face masks using the trained

weights.

In this video, we will measure the accuracy of the trained weights using mean average precision, mean

average precision, or MFP is a metric for evaluating an object detection model.

But before calculating MP, I will explain some of the arguments that can be used.

First there is the weights argument.

This is the goal of these seven weights file that will be used to calculate the MP value.

This is an example of its application.

Next is the bed size argument.

This argument is the number of images processed at one time.

This is an example of its application.

Next is the device argument.

This argument is used to select which CPU to use by writing down the index.

The default value of this argument is zero, which means it selects the first available CPU with queue

to support on the computer.

If using CPU replace zero with CPU in this argument, the data argument comes next.

This argument is a data file that contains the number of classes, the dataset product and the class

name.

This is an example of its application.

Next is the IMT argument.

This argument is the size of the image to be processed.

The following is an example of its application.

The confidence argument comes next.

This is an object confidence threshold.

The following is an example of its application.

Next is the I.O.U. argument.

This is the IOU threshold.

I only use the ratio of the overlapping area between the predicted bounding box and the ground truth

bounding box.

The detection result is said to be correct if it has an IOU value greater than or equal to the threshold.

This is an example of its application.

Next is the name argument.

This argument is the name of the folder that stores the P calculation results.

This is an example of its application.

Next is the Tusk argument.

This argument specifies whether the calculations should be run on train validation or test data set.

The following is an example of its application.

In this video we will calculate upon validation and test of the face mask dataset.

The validation dataset is located in the folder listed below and the test dataset is in the folder below.

These are the images on the foundation dataset.

There are 80 images.

These are the images on the test dataset.

There are 81 images.

The first step to calculate MLP is to launch the Anaconda prompt.

Press the Windows button.

Then enter Anaconda.

Click the Anaconda prompt.

Then activate the all of seven CPU environment using the command.

Activate yolo.

v72 for you and for.

Press enter.

They never get to the goal of seven zips further.

First, we will calculate MLP and the validation dataset.

Use the command.

Python test the PI.

That's that's why it's we will use the train weights in this example in runs train.

YOLO v seven Face mask.

Waits.

That's not pretty.

In bedsides we write to.

On device write zero.

In the data.

Write down the data file that was previously created in the training section.

We use 640 pixels for the image size.

In conference, we use 0.01, which is the default value for measuring accuracy.

In IOU, we use 0.5.

We write to all of his seven face must well in the name argument.

In the last argument, right?

Well, because we will calculate MLP in validation dataset.

Chris enter.

Wait until the calculation is finished.

Here are the results.

The calculation results will display precision recall.

And LP.

MP 0.5 indicates that the MLP calculates and employs an IOU threshold of 0.5.

The detection result is said to be correct.

If it has an IOU value of at least 0.5.

In this example, the MLP value for all classes is 0.767.

There are also MFP values for each class.

This value can be used to determine whether the training results are suitable for all classes.

In this example, the training results are good for mosque and no mosque, but not good for bad mosques.

Next, we will calculate MLP on the test dataset.

Use the common python.

Test the python.

That's that's why it's.

We will use the train weights.

In bed size we write through.

On device write zero.

In the data.

Write down the data file that was previously created in the training section.

We use 640 pixels for the image size.

In contrast, we use 0.01.

You know, you use 0.5.

You write Your love is seven face must test in the name of human.

In the first argument right test because we will calculate MLP in test dataset.

Press enter.

Wait until the MP calculation is finished.

The following is the result of the map calculation on the test dataset.

That's all explanation for measuring accuracy using mean average precision.

Thank you.

And see you then.