This Image-Object-Detection-MobileNetV1-SSD512-Caffe 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 512 × 512. Unlike other SSD, this solution uses the MobileNetV1 network.
First, we need to prepare the image we want the model to learn, label the target in the image, and label the selected box as a 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 to train and test. Continue to execute the py file for training. After the training is complete, select a different py file based on the test image you are testing.