The article is devoted to the study of object detection in images using neural networks. The structure of convolutional neural networks used for image processing is considered. The formation of the convolutional layer (Fig. 1), the sub-sampling layer (Fig. 2) and the fully connected layer (Fig. 3) are described in detail. An overview of popular high-performance convolutional neural network architectures used to detect R-FCN, Yolo, Faster R-CNN, SSD, DetectNet objects has been made. The basic stages of image processing by the DetectNet neural network, which is designed to detect objects in images, are discussed. NVIDIA DIGITS was used to create and train models, and several DetectNet models were trained using this environment. The parameters of experiments (Table 1) and the comparison of the quality of the trained models (Table 2) are presented. As training and validation data, we used an image of the KITTI database, which was created to improve self-driving systems that do not go without built-in devices, one of which could be the Jetson TX2. KITTI’s images feature several object classes, including cars and pedestrians. Model training and testing was performed using a Jetson TX2 supercomputer. Five models were trained that differed in the Base learning rate parameter. The results obtained make it possible to find a compromise value for the Base learning rate parameter to quickly obtain a model with a high mAP value. The quality of the best model obtained on the KITTI validation dataset is mAP = 57.8%.