The invention belongs to the computer image processing technology field and particularly relates to an image grain size classification method based on the jumpable double-branch neural network. The method comprises steps that a data set is collected, and image data and corresponding coarse and fine category labels are included; the jumpable double-branch neural network is constructed, and a hierarchical gate control module is added to the densely-connected convolutional neural network; data enhancement of a training sample is performed, and the jumpable double-branch neural network is trained;an end-to-end neural network is trained, and the classification result is outputted. Coarse-grained and fine-grained classification tasks of images can be simultaneously solved through the constructed jumpable double-branch neural network. The method is advantaged in that the gate control module is added to the densely-connected convolutional layer, execution of the convolutional layer can be dynamically selected based on the input, the inference depth of the network is variable depending on complexity of the sample and the granularity of the classification tasks, and the flexible convolutional neural network is beneficial for improving model capacity and computational efficiency.

Image grain size classification method based on jumpable double-branch neural network

The invention relates to a target detection model based on deep learning and a training method thereof. According to the model, the structural advantages of dense connection are fully utilized, the training starts from zero, and an end-to-end detection effect can be achieved. According to the model, in the back-end feature extraction, a dense connection module is used to establish more associations between adjacent convolutional layers, model performance is improved and weight parameters are reduced. In front-end feature map merge, a dense connection mode is used to carry out feature reuse, the feature of a previous feature map is introduced into the feature map of each scale, a connection mode with a shorter path with a top layer is established, and thus an error signal is transmitted deeper along the network in the reverse propagation. The model has fewer parameters and stronger performance, and the disadvantage that a traditional model relies heavily on pre-training is made up. Themodel and the training method are also applicable to a target detection task of special domain images, and the problem of no convergence or serious over-fitting in training starting from zero is improved.

Target detection model based on deep learning and training method thereof

The invention provides an image classification model design method and apparatus The method comprises the steps of according to a labeled image database, performing training to obtain an initial network model of image classification; according to a prediction result of the initial network model and a prediction result of a final network model, building a loss function corresponding to the final network model; and according to the loss function, optimizing the final network model According to the image classification model design method and apparatus provided by the invention, the requirementon a training sample quantity is relatively low; the design difficulty and cost are lowered; and the problem of labeling ambiguity is effectively solved

Image classification model design method and apparatus

The invention relates to a Mobile Nets-based method for optimizing a multi-scale learning network. According to the invention, the multi-scale learning network comprises four parts. The front three parts of the four parts are composed of identical separable convolution layers, wherein the rear par of each separable convolution layer is connected with bachnorm and ReLU, then connected with a pooling layer, and finally connected with the full-connection layer and the output layer of the fourth part. The separable convolution layer comprises three groups of convolution operations. The specific network structures of the three groups of convolution operations are as follows: the first group is subjected to convolution operation according to the depth convolution of 3 * 3; the second group is subjected to convolution operation according to two continuous depth convolutions of 3 * 3; the outputs of the first and second groups are first subjected to adding operation and then subjected to convolution operation according to the point convolution of 1*1; the third group is subjected to convolution operation directly according to the point convolution of 1*1; the outputs of the first, second and third groups are subjected to combining operation. The experiment comparison shows that, the network structure constructed by the method and disclosed by the invention is few in experimental parameters and high in precision. The three groups of separable convolution layers are stable in structure and the experiment effect is most ideal.

Mobile Nets-based method for optimizing multi-scale learning network

An image retrieval method based on deep Hash learning optimization comprises the following steps of 1, constructing a multi-layer full connection network firstly, connecting a panh function behind each layer of full connection, and finally conducting the sign operation on the network output; 2, constructing a semantic retention loss function obtained by a classification loss function and a weighted semantic similarity matrix, and a target function with discrete orthogonal constraint obtained by a quantitative loss function and a regular item; 3, optimizing an objective function; 4, dividing the obtained feature data set into a query set Q and a to-be-searched set D, taking a part of data in the to-be-searched set D to form a training data set P, inputting depth characteristics and label information of the training data set P, initializing a weight coefficient and a binary code, performing iterative optimization on the step 3 in sequence to obtain an optimal network weight coefficient,and obtaining a depth hash function by the step 2; and step 4, carrying out the image retrieval and precision testing. The method is relatively higher in precision and relatively higher in retrieval efficiency.

An image retrieval method based on deep Hash learning optimization

The invention discloses a quick image classification method based on deep learning, and the method comprises the following steps: 1, network building; 2, data set preprocessing; 3, network training; 4, image classification, wherein the image classification comprises the following substeps: 4.1, inputting a testing data set into the trained network model after preprocessing, and extracting the multi-scale features of a testing image; 4.2, inputting the extracted multi-scale features into a Softmax classifier, and outputting the probability that the testing image belongs to one class; 4.3, inputting probability that the testing image belongs to one class and a label corresponding to the image into an Accuracy network layer, and outputting the probability that the image is classified correctly. Through the above steps, the method can achieve the quick classification of the testing image. The method is short in training time, is convenient in training, and is high in classification precision.

Quick image classification method based on deep learning

The invention relates to a method for optimizing a deep convolutional neural network for image classification, which comprises the steps of first, building an image classification convolutional neural network; second, training the image classification convolutional neural network; third, testing the image classification convolutional neural network. The process of testing the image classification convolutional neural network comprises the steps that a preprocessed test data set is fed into a trained network model, and an Accuracy layer of the network outputs an accuracy value according to a probability value outputted by a Softmax layer and a label value of an input layer, wherein the accuracy value is the probability that a test image is correctly classified. According to operations performed in the steps, optimization for the deep convolutional neural network for image classification can be realized. The method provided by the invention for optimizing the deep convolutional neural network for image classification can effectively reduce the semantic gap and is high in classification accuracy.

Method for optimizing deep convolutional neural network for image classification

The invention discloses a large-scale image retrieval method based on a deep residual network and hash coding. The method includes the following steps: step 1, deep-residual-network construction; step2, hash-network construction, which includes the following processes: step 2.1, forming a hash network by three fully connected layers, step 2.2, connecting a tanh activation function after each fully connected layer, and step 2.3, calculating gradient response according to a loss function to propagate and feed back the same into the network; step 3, deep-residual-network training, which includesthe following processes: step 3.1, dividing data into a training data set T and a test data set V, step 3.2, training the deep residual network, and step 3.3, training the hash network; and step 4, picture retrieval and precision tests. Retrieval for a picture can be realized simply through operations of the above-mentioned steps. According to the large-scale image retrieval method based on the deep residual network and hash coding provided by the invention, precision is higher, and retrieval efficiency is higher.

Pan Xiang

Papers

Quick image classification method based on deep learning

Method for optimizing deep convolutional neural network for image classification

Large-scale image retrieval method based on deep residual network and hash coding