Model Convert

Model Convert is used to convert YOLOv5 TorchModel to TensorRT format, which can greatly improve the detection performance.

Function Entry: Toolbox-> Machine Learning-> Video Analysis-> Model Convert.

Training data path: Select the folder where the training data generated by Manage Picture Sample is located.
Model: Select the model to be converted.
Training Picture Size: Set the Picture Size for Model Training, which should be consistent with the Picture Size of Model Training.
Video width: Set the width of the video. The video width must be the width of the video to be detected after conversion.
Video height: set the height of the video. The video height must be the height of the video to be detected after conversion.

Note: The

converted model can only be used to detect the video with the set aspect ratio. If the aspect ratio is set to 1920 * 1080, the model can only be used for videos such as 1920 * 1080 and 1280 * 720.