Abstract: A probe card for testing power devices under high temperature and high voltage. The probe card includes air inlet system, PCB board, switching layer, guide plate and probe from top to bottom; the bottom of air inlet system includes plurality of lower air outlets and side air outlets, the PCB board includes a first through-hole with same position, shape and quantity as the lower air outlet, the switching layer includes a second through-hole with same position, shape and quantity as the lower air outlet, the guide plate includes a third through-hole with same position, shape and quantity as the lower air outlet. The lower air outlet, the first through-hole, the second through-hole and the third through-hole are coaxially arranged. The high-temperature and high-pressure gas ejected from the lower air outlet is blown between the guide plate and the tested wafer after successively passing through the first, second, and third through-holes.

Abstract: This application relates to a target object detection method and apparatus, a non-transitory computer-readable storage medium, and a computer device. The method includes: obtaining a to-be-detected image; inputting the to-be-detected image into a target object detection model; generating, by the target object detection model, a prediction diagram corresponding to the to-be-detected image, the prediction diagram describing a relation degree to which pixels of the to-be-detected image belong to a target detection object; and performing region segmentation on the prediction diagram to obtain a target detection object region. In addition, a method and an apparatus for training an object detection model into the target object detection model, a non-transitory computer-readable storage medium, and a computer device are also provided.

Abstract: This application relates to a target object detection method and apparatus, a non-transitory computer-readable storage medium, and a computer device. The method includes: obtaining a to-be-detected image; inputting the to-be-detected image into a target object detection model; generating, by the target object detection model, a prediction diagram corresponding to the to-be-detected image, the prediction diagram describing a relation degree to which pixels of the to-be-detected image belong to a target detection object; and performing region segmentation on the prediction diagram to obtain a target detection object region. In addition, a method and an apparatus for training an object detection model into the target object detection model, a non-transitory computer-readable storage medium, and a computer device are also provided.