MINC Classifier with Deep Learning Studio
In this article, we will be creating an AI APP module designed for MINC-2500-tiny dataset using DLS.
Deep Learning Studio(DLS) will used to train and test the network on the dataset provided. The software can be downloaded from deepcognition.ai by creating a free account.
For this example, Windows v3.0.1 will be used.
In this example, we will be use the MINC-2500-tiny dataset which is available on DLS. DLS provides MINC-2500-tiny dataset by default in public datasets.
MINC is short for Materials in Context Database, provided by Cornell.
MINC-2500is a resized subset of
MINCwith 23 classes, and 2500 images in each class. It is well labeled and has a moderate size thus is perfect to be our example.
We proceed to make our AI App Module. Click on the Projects tab. To create a new project, click on the Create Project button. A pop up asking for the project name, project type and description shows up. The project type for our model is AI App Module. You can set the name and description as per your preference. Click on the newly created project and you will see a screen with tab as show below:
New Project Creation
In the Task Specification tab (shown above), select the AI App Module tab as GluonCV Classifier by Deep Cognition that was provided by DLS.
Make sure you have installed AI Module plugin GluonCV Classifier by Deep Cognition
Then choose the pre-trained type, you will get these three options :
Then select Model type. After selecting the Model tab you will see the tabs,for edit AI module settings as per your requirements. Here is a screenshot of how it should look :
Go to the next Data tab, here you can select minc-2500-tiny dataset with a small drop-down button next to the Dataset. Load dataset in Memory one batch at a time or full dataset at the same time. Shuffle your data by clicking on it.
We will now train the model from the Training tab. Select the device using which you want to compute the model parameters and click on Start Training. An ETA will be shown in the top left function along with other statistics shown on the tab.
Once the model has completed its training, we now go to the Results tab to check our result. On the Graphs option, select the RunX from the left and you will see the graphs for our training run.
On the Configuration option, you can see all the layers and hyperparameters that were used for the given training run.