Target detection model training method and device, electronic equipment and storage medium

The invention provides a target detection model training method and device, electronic equipment and a storage medium, and the method comprises the steps: transmitting a to-be-trained target detection model to a plurality of training parties, enabling each training party to carry out the training through employing the own data, and obtaining a candidate target detection model; determining an aggregation node from the plurality of distributed processing nodes; and aggregating the parameters in each candidate target detection model through an aggregation node, and updating each candidate target detection model based on the aggregated parameters to obtain a target detection model. In each round of training of the target detection model, one processing node is not fixed to aggregate parameters of a plurality of trained target detection models, but one processing node is dynamically selected each time to aggregate the model parameters, so that the probability that the fault nodes are selected is also reduced, and