2results about How to "Reduce marking costs" patented technology

The utility model provides a sleeve film marking device for an aluminum electrolytic capacitor. The sleeve film marking device comprises a rack; the sleeve film conveying device is arranged on the rack, the sleeve film conveying device comprises an unwinding roller and a winding roller, and the winding roller is rotatably arranged; the ink marking device is arranged in a conveying path of the sleeve film conveying device; and the air drying device is arranged in the conveying path of the sleeve film conveying device, and the air drying device comprises an airflow multiplier and outputs blown air through the airflow multiplier. According to the sleeve film marking device for the aluminum electrolytic capacitor provided by the invention, the air drying device is arranged in the sleeve film conveying path, and the air drying device outputs and blows air to the ink mark through the airflow multiplier, so that the ink mark printed on the sleeve film can be blow-dried online, the sleeve film marking operation time is shortened, the operation site requirement is reduced, and the production efficiency is improved. And meanwhile, the air-dried sleeve film can be automatically wound on line through the winding roller, and the marking cost of the sleeve film is reduced.

The present application provides a kind of training method, device, electronic equipment and storage medium of pedestrian search model based on twin network, wherein the method comprises: determining training image;According to the lower branch of twin network, the feature of training image is extracted, and the feature vector of each pedestrian in training image is obtained;The training image is processed to obtain multi-scale pedestrian image, and the feature of multi-scale pedestrian image is extracted according to the upper branch of twin network, and the multi-scale feature vector of each pedestrian in training image is obtained;According to the feature vector and multi-scale feature vector, training is carried out, and the trained pedestrian search model is obtained when training is completed. When pedestrian search is carried out, the pedestrian at different scales is accurately searched.