Hangzhou Xishang Technology Co., Ltd.AI · Software · Data · Simulation
Contact Us
← Back to tutorial library

NEUROBLOCKS STUDIO · Examples & Tutorials

Visual CNN Builder

Drag and connect convolution, activation, pooling and classifier-head blocks to build a CNN visually.

Learn how to use NeuroBlocks Studio for Visual CNN Builder with real, manually matched screenshots. This tutorial covers setup, execution, result interpretation and practical checks.

What this tutorial covers

Drag and connect convolution, activation, pooling and classifier-head blocks to build a CNN visually.

Before you start：You need access to the product and should ideally follow the tutorial using your own real parameters or data. The screenshots below were manually rematched to avoid the image/topic mismatches seen in the previous version.
Visual CNN Builder - Open the relevant module and confirm the starting state.
Open the relevant module and confirm the starting state.
Visual CNN Builder - Configure the key inputs that match the topic.
Configure the key inputs that match the topic.
Visual CNN Builder - Run the workflow and inspect the result/status.
Run the workflow and inspect the result/status.

Step-by-step workflow

1Open the module

Start connecting blocks on the model canvas. Confirm that the visible page really matches the tutorial topic before changing any settings.

2Configure the input

Prepare and check convolution, activation, pooling and classifier-head blocks.

3Run and watch the status

Adjust the network structure and inspect the visual connections. Watch the visible status, plot or log area while the workflow is running.

4Inspect the result

Pay special attention to a runnable CNN architecture graph.

5Verify and iterate

This page focuses on structure-building, so keep the module order and connections logically valid. Change one meaningful parameter and rerun so you can verify whether the output changes in the expected direction.

How to read the result

  • The main output of this workflow is a runnable CNN architecture graph.
  • Read the result together with the exact inputs used for the run; a screenshot alone rarely tells the whole story.
  • This page focuses on structure-building, so keep the module order and connections logically valid.

Troubleshooting & practical tips

  • If nothing changes, first confirm that the correct module is open.
  • If the output looks unrealistic, check units, field mapping and input scale first.
  • For comparisons, change one key parameter at a time whenever possible.
Previous tutorialLayer Library & TemplatesNext tutorialDataset Import & Train/Validation/Test Split