MaskRCNN APP can be used in factory defect detection, medical image analysis, fish image analysis, biological image analysis, advanced driving assistance systems, autonomous vehicles, etc. As shown in the figure above, check whether the person is wearing a mask.
[Operation steps and instructions]
Before using MaskRCNN for training or object detection, please make sure that the dataset folder is selected correctly.
The "browse" button next to the "Select Dataset" field can open the data folder location to facilitate users to confirm and modify.
1.annotation pascal voc xml: Open the annotation webpage for image annotation.
2.delete log: Delete log folder.
After marking the images, you can start training.
There are several ways of inference:
4. inference: Inference of a single image, you can set the image path you want to infer in the inference image path of Parameter (under the folder selected in the data folder).
5.evaluation mAP: Calculate the mAP of the valid folder.
6.inference api: Use web pages for image inference. After pressing the "6.inference api" button, press the "7.inference api browser" button to open the web page.