Target detection method and device, equipment and medium

The embodiment of the invention provides a target detection method and device, equipment and a medium, and the method comprises the steps: segmenting a to-be-detected image into a preset number of cut images according to a preset shape before inputting each cut image into a pre-trained first feature extraction network model for feature extraction, the problem that in the target detection process, the feature extraction layer and the spatial pyramid pooling layer lose detail information of the image in the zooming process is effectively avoided, in the subsequent target detection process, the full connection layer determines the weight matrix of the image to be detected based on the attention mechanism, and the image detection accuracy is improved. According to the weight matrix and the first image feature vector, more weights are distributed to the region containing the target, and the accuracy and recall rate of small target detection are improved. 本申请一些实施例提供了一种目标检测方法、装置、设备及介质，该方法中在将每个裁剪图像输入到预先训练完成的第一特征提取网络模