Medical glass bottle appearance defect detection model training method and device and terminal device

The invention is suitable for the technical field of defect detection, and provides a medical glass bottle appearance defect detection model training method and a device and a terminal device. The method comprises the following steps: acquiring a medical glass bottle image, and generating a normal image and a defect marking image based on the medical glass bottle image; inputting the defect mark image into a preset mapping network to generate a defect code; inputting the normal image and the defect code into a preset generator to generate a synthetic defect sample; training a generative adversarial network model based on the synthetic defect sample and the defect marking image; and generating a defect sample training set based on the generative adversarial network model, and training a deep learning image recognition model based on the defect sample training set. According to the medical glass bottle appearance defect detection model training method provided by the invention, a sufficient defect sample traini