Release Notes¶

Mech-DLK V2.3.0
Mech-DLK V2.2.1

Mech-DLK V2.3.0 ¶

Graphics card driver requirement¶

Before using Mech-DLK V2.3.0, please upgrade the graphics card driver to 472.50 or above.

Improved the training speed¶

Optimized the algorithms, and thus significantly improved the speed of model training. Only the optimal model is saved during training, and the training cannot be stopped halfway.

Added the Smart Labeling Tool¶

For modules including Defect Segmentation, Instance Segmentation, and Object Detection, you can do smart labeling by selecting the Smart Labeling Tool, clicking on the objects to label, right-clicking to undo the redundant selection, and pressing Enter to complete the labeling.

Added the function of adding/removing vertices for the Polygon Tool¶

For modules including Instance Segmentation and Object Detection, after labeling with the Polygon Tool, if the selection needs to be modified, you can left-click on the line segment between two vertices to add a vertice, or right-click on a vertice to remove it.

Added the Template Tool¶

For modules including Instance Segmentation and Object Detection, you can use the Template Tool to set the selection as a template. The template can be applied by simply clicking on the images. It is suitable for scenarios where there are multiple neatly-arranged objects of the same type in an image, and it improves labeling efficiency.

Added the function of preview by zooming¶

Support previewing full images and cropped cell images. Please see Resize and Preview.

Optimized the Grid Cutting Tool¶

Optimized the Grid Cutting Tool. After cutting the image by the grid, you can select a cell image by checking the box in the upper left corner of the cell image, and you can preview the image by clicking on the button in the upper right corner of the cell.

Optimized the data filtering mechanism¶

Added options for filtering results: “Correct results”, “Wrong results”, “False negative”, “False positive”.

Added options for filtering data types: “Labeled as OK”, “Labeled as NG”.

Built-in deep learning environment¶

The deep learning environment is built into the software Mech-DLK, and the models can be trained without a separately installed environment.

Mech-DLK V2.2.1 ¶

Added the Function of Showing the Class Activation Maps for Module Classification¶

After the model is trained, click Generate CAM. The class activation maps show the weights of the features in the form of heat maps; the model classifies an image into its class according to these features. Image regions with warmer colors have higher weights for classifying the image into its class.

Validation and export of CPU models¶

Classification, Object Detection: After training is complete, select the deployment device as CPU or GPU before exporting the model.
Instance segmentation: Before training the model, set the training parameters. When exporting a model, select the deployment device as CPU/GPU:
- CPU lightweight model : Before training the model, set the training parameter Model type to Lite (better with CPU deployment). When exporting the model for deployment, set Deployment device to CPU or GPU.
- GPU standard model : Before training the model, set the training parameter Model type to Normal (better with GPU deployment). When exporting the model for deployment, it is recommended to set Deployment device to GPU.