This is based on the deep learning Caffe framework. The SSD (Single Shot MultiBox Detector) algorithm is used to train the model. Then the trained model is used to detect the capacitance on the PCB. The training image size is 300 × 300. Unlike other SSD, this solution uses the MobileNetV1 network.
First, we need to prepare the image that we want to learn from the model, select the target frame in the image, and mark the selected box as the category. The purpose is to let the model know what the object in the image belongs to things.
Then, through a series of py files, generate two txt manifest files, so that the model knows which files are to be tested for training, and which categories are divided into these files, and then execute py files for two txt manifest files. Training, after the training is completed, select different py files according to the test image you want to test.