# Train

Now we get to the fun part -  Training a custom model! 

In this example we will be training a custom women's handbag model.  

{% hint style="info" %}
You can of course train any custom model you like after this workshop, but for this example we will take a look at retail and women's fashion! 
{% endhint %}

### Step 1: 

To Train a custom model the first thing we need is some data. 

Download the following files : 

{% file src="<https://1442039566-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-LvqHK7ivKIfEf7AUw48%2F-LvwSgxwXiGOgNGwoX2n%2F-LvwWrjauNtcN3XMz-rZ%2Fchanel.zip?alt=media&token=b7f00624-cf2b-4937-9c00-acab805dc65c>" %}

{% file src="<https://1442039566-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-LvqHK7ivKIfEf7AUw48%2F-LvwSgxwXiGOgNGwoX2n%2F-LvwTh35GJu0IHV_lE_u%2Fdior.zip?alt=media&token=812617cc-0271-4a1b-bb6f-27adbebebf41>" %}
dior.zip
{% endfile %}

{% file src="<https://1442039566-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-LvqHK7ivKIfEf7AUw48%2F-LvwSgxwXiGOgNGwoX2n%2F-LvwTocCYvkPwRCMtvnC%2Flouis-vitton.zip?alt=media&token=dd727990-fa2c-4c02-9d53-e1b7f8d3b7cb>" %}
louis-vitton.zip
{% endfile %}

Finally the Test file to test our model&#x20;

{% file src="<https://1442039566-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-LvqHK7ivKIfEf7AUw48%2F-LvwSgxwXiGOgNGwoX2n%2F-LvwTzTrX4AU5EeMqZiN%2Ftest.zip?alt=media&token=3e8eb70d-7246-41cc-a972-2544ac07098e>" %}
test.zip
{% endfile %}

{% hint style="info" %}
When you go off and create your own custom model you will need to find the data and create zip files to train.&#x20;
{% endhint %}

### Step 2 :&#x20;

Go ahead and re name your classifier . I named mine `Hand-Bag Classifier`  . Feel free to name your model anything you like depending on the type of classifier you are building . Also click browse to upload the `chanel.zip` , `louis-viton.zip` , and the `dior.zip` files into the project.&#x20;

![](https://1442039566-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-LvqHK7ivKIfEf7AUw48%2F-LvwSgxwXiGOgNGwoX2n%2F-LvwVsQvPaAX5p3D7XP5%2FScreen%20Shot%202019-12-12%20at%206.42.04%20PM.png?alt=media\&token=3466519c-39ae-447c-a59a-4efa1493cd04)

### Step 3:&#x20;

Once your files are uploaded you can click on the blue squares next to each zip file and click on **Add to model**&#x20;

![](https://1442039566-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-LvqHK7ivKIfEf7AUw48%2F-LvwSgxwXiGOgNGwoX2n%2F-LvwXevfzR1qR6lDymH_%2FScreen%20Shot%202019-12-12%20at%206.51.18%20PM.png?alt=media\&token=c74f639b-15dd-4a73-b760-3fcdcc657b53)

&#x20;You should see something like this :&#x20;

![](https://1442039566-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-LvqHK7ivKIfEf7AUw48%2F-LvwSgxwXiGOgNGwoX2n%2F-LvwXm9HgaOed7_Lmwec%2FScreen%20Shot%202019-12-12%20at%204.22.59%20PM.png?alt=media\&token=6ab8c226-f8bd-40af-a263-1e801734e9ce)

{% hint style="info" %}
You might get a flag on the class name. Make sure to chage it so includes correct characters.&#x20;
{% endhint %}

Doing this step ensures that you have three different classes of images in place.&#x20;

### Step 4 :&#x20;

Click on Train in the upper right hand corner to train the model . Training can take 10 - 15 mins depending on model size.&#x20;

![](https://1442039566-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-LvqHK7ivKIfEf7AUw48%2F-LvwSgxwXiGOgNGwoX2n%2F-LvwYi0VPJL8TSTybxXL%2FScreen%20Shot%202019-12-12%20at%206.59.03%20PM.png?alt=media\&token=69065e82-09bc-4b1b-9e3c-6cd2fb06b6e6)

![You should see this message when you start training](https://1442039566-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-LvqHK7ivKIfEf7AUw48%2F-LvwSgxwXiGOgNGwoX2n%2F-LvwYlih2x-FWuJfEPZz%2FScreen%20Shot%202019-12-12%20at%206.59.30%20PM.png?alt=media\&token=3d5929e6-7a1f-4b83-9725-66c6c5b91b3a)

Now all you have to do is wait for training to be done and then you can go ahead and test!&#x20;