Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

41results about How to "Shorten training time" patented technology

Video behavior recognition method, device and equipment based on multi-mode large model fine tuning

The embodiment of the invention relates to the technical field of video detection, in particular to a video behavior recognition method, device and equipment based on multi-mode large model fine tuning. A specific embodiment of the method comprises the steps of obtaining a video behavior recognition data set and an initial video behavior recognition model; for each piece of video behavior identification data, executing the following steps: determining a key frame image corresponding to a video frame sequence included in the video behavior identification data; storing the key frame image to a preset image storage position; based on the label text template, the key frame image, the image storage path and a behavior label included in the video behavior identification data, a training sample is generated, and the training sample comprises a sample image and sample label data; training the initial video behavior recognition model, and determining the initial video behavior recognition model as a video behavior recognition model; and inputting the target video data into the video behavior recognition model to obtain video behavior text information. According to the embodiment, the training duration of the video behavior recognition model can be prolonged.
Owner:HANGZHOU INNOVATION RES INST OF BEIJING UNIV OF AERONAUTICS & ASTRONAUTICS +1

Routing method of quantum key distribution network and related device

The invention discloses a routing method of a quantum key distribution network and a related device. The method comprises the steps that the state of a first QKD network is collected, the value of a corresponding reward function is calculated, the state is input into a preset actor network, and a corresponding action is output; the reward function is a linear combination of a plurality of topological state influence parameters; training the actor network by using a training architecture of the actor-commentator network in combination with the state, the action and the reward function value until a training termination condition is reached; taking the trained actor network as a strategy network; inputting the state of the link between the nodes in the second QKD network of which the route is to be determined into the strategy network, and outputting the weight value of the link between the nodes in the second QKD network through the strategy network; and calculating the optimal route of the second QKD network according to the weight value output by the strategy network. The invention provides a strategy network which is more intelligent and stronger in robustness so as to realize a routing strategy which is higher in distribution efficiency and more balanced in load.
Owner:SHENZHEN SPINQ TECHNOLOGY CO LTD +1

Polyethylene pipe sweat soldering defect detection system based on microwaves

The invention discloses a microwave-based polyethylene pipe hot-melt welding defect detection system, and relates to the technical field of polyethylene pipe hot-melt welding joint defect detection, and the method comprises the following steps: firstly, collecting microwave reflection signals of normal and defect-containing hot-melt welding joints, and carrying out normalization; the processed signals are sliced, sliced fragments are labeled, time domain and frequency domain features are extracted, and a defect sample data set is constructed; carrying out feature selection on the extracted features, and selecting 10 features with the highest contribution to the recognition accuracy; constructing a support vector classifier model, performing training by using the data set after feature selection, and performing hyper-parameter optimization on the model to obtain an optimal classification model; designing and realizing a polyethylene pipe hot-melt welding defect detection system, and detecting whether a welding position contains defects and defect positions or not; according to the invention, accurate detection of polyethylene pipe hot melting welding defects can be realized, defects and positions can be rapidly identified, and technical support is provided for quality safety detection of polyethylene pipes.
Owner:SOUTHWEST PETROLEUM UNIV

Malicious domain name generation method, domain name generation model training method and related equipment

The embodiment of the invention provides a malicious domain name generation method, a domain name generation model training method and related equipment, and belongs to the technical field of network security. The malicious domain name generation method comprises the following steps: extracting sequence features of an obtained sample domain name character sequence through an initial domain name generation model, and determining a sample generation domain name based on the sequence features; determining an initial parameter set of the current initial domain name generation model, and performing Bayesian optimization on model parameters of the initial domain name generation model based on the sample generation domain name and the initial parameter set to obtain a trained domain name generation model; obtaining a plurality of malicious domain names to be processed, and generating a domain name character sequence based on the plurality of malicious domain names; and inputting the domain name character sequence into the trained domain name generation model, and predicting to obtain a target generated domain name with the same feature as the malicious domain name sequence. The generation efficiency of the malicious domain name can be improved, and then the detection efficiency of the malicious domain name is improved.
Owner:PENG CHENG LAB

Information recommendation method and device and storage medium

The invention relates to an information recommendation method and device and a storage medium, and the method comprises the steps: obtaining user information of a target user, the user information comprising at least one of the following: user portrait information, commodity attribute information of a target commodity, and interaction information between the target user and the target commodity; constructing a user feature vector matrix corresponding to the user information; the user feature vector matrix is input into a pre-trained intention prediction model to obtain an intention prediction label of the target user, the intention prediction model is a multi-task model obtained based on teacher model end-to-end training, and the intention prediction label comprises a prediction label corresponding to each prediction task in the intention prediction model; the teacher model corresponds to a target prediction task in the intention prediction model; and according to the intention prediction tag, determining whether to send recommendation information corresponding to the target commodity to the target user. The prediction accuracy of the intention prediction model can be ensured, and the training time of the intention prediction model is effectively shortened.
Owner:BEIJING XIAOMI MOBILE SOFTWARE CO LTD +1

Abnormality processing method and device, electronic equipment and storage medium

The invention discloses an exception handling method and device, electronic equipment and a storage medium, and the method comprises the steps: detecting the computing power exception information of a heterogeneous computing equipment cluster in the training of a deep learning model; if so, interrupting the training of the deep learning model on the heterogeneous computing device cluster; searching a target task processing strategy matched with the abnormal computing power index from a current task processing strategy set; task processing strategies in the current task processing strategy set correspond to different computing power indexes, and each task processing strategy represents training resources needing to be loaded under the condition that the corresponding computing power index is abnormal; and if the abnormal heterogeneous computing device is found, restarting training of the deep learning model on a target heterogeneous computing device cluster based on the target task processing strategy, wherein the target heterogeneous computing device cluster comprises heterogeneous computing devices except the abnormal heterogeneous computing device. The method does not need manual follow-up to solve breakpoint continuous training of each time, shortens the training time, and improves the utilization rate of cluster resources.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD

A music recognition model training method, music recognition method and related equipment

The present application provides a training method for a music recognition model, a music recognition method and related equipment, which are used to solve the problem of low recognition accuracy of the trained music recognition model. The method at least includes: the music recognition model includes: a trained feature extraction sub-model and a text recognition sub-model, and a feature mapping sub-model to be trained; each round of iterative training of the music recognition model to be trained includes: using the feature mapping sub-model to map the spectral features extracted by the feature extraction sub-model to descriptive text features; describing the text features, which are used to describe a variety of training music attributes of sample audio clips; based on the difference between the training music description recognized based on the descriptive text features using the text recognition sub-model and the corresponding sample music description, the model parameters of the feature mapping module are adjusted. Training only on the feature mapping sub-model reduces the quantity requirement of sample data in the music field and improves the recognition accuracy of the music recognition model.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD

A lightweight image super-resolution method and system based on dynamic reparameterization

A lightweight image super-resolution method based on dynamic reparameterization includes: S1 inputting a preprocessed low-resolution original image into a CNN-based lightweight image super-resolution backbone network and image reconstruction module to obtain a super-resolution image; S2 calculating a loss function based on the super-resolution image and the corresponding high-resolution original image after preprocessing, and updating the network weights through backpropagation; S3 expanding the convolutional layer with the largest contribution score in the iteration cycle into an enhanced edge-oriented reparameterization branch module according to the iteration cycle and initialization conditions, and pruning all reparameterization branches with the smallest contribution score that have been expanded into reparameterization branch modules in the iteration cycle; repeating steps S1-S3 until the backbone network converges. This method improves reconstruction performance without changing the lightweight network parameters of the backbone network and maintaining fast inference speed. Compared to other reparameterization methods, it can significantly reduce training time and memory consumption.
Owner:BEIJING JIAOTONG UNIV

Wavefront aberration prediction method of optical-mechanical system under variable-temperature working condition

The invention discloses a wavefront aberration prediction method for an optical-mechanical system under a variable-temperature working condition. The wavefront aberration prediction method comprises the following steps: step 1, establishing a physical model and a simulation model of an optical system; 2, measuring and calibrating the simulation model by using the optical system physical model; 3, constructing a neural network data set by using the simulation model; 4, training a neural network model, wherein the convolutional neural network comprises an input layer, a convolutional layer, a pooling layer, a full connection layer and an output layer; the samples obtained in the step 3 are used for training the convolutional neural network, and when a loss function of the convolutional neural network is converged, the whole training process is completed; and 5, predicting the wavefront aberration of the system by using the convolutional neural network. The temperature sensor is used for monitoring the temperature of the key point in real time, the surface shape performance of the optical-mechanical system is predicted in real time by training the deep learning network, and the error compensation efficiency and precision of the system can be effectively improved.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Model training method and device

The invention discloses a model training method and device, and belongs to the technical field of artificial intelligence, and the method comprises the steps: obtaining a first calculation graph corresponding to a first model, the first calculation graph being used for describing a calculation sequence among N first calculation nodes of the first model, and N being a positive integer; determining M first computing nodes from the N first computing nodes, wherein M is a positive integer smaller than or equal to N; and calculating M gradients in one-to-one correspondence with the M first computing nodes, and respectively updating the weight parameters of the corresponding first computing nodes based on each gradient to obtain a trained first model.
Owner:VIVO MOBILE COMM CO LTD

A wall-penetrating target behavior recognition method based on channel state information and a device thereof

The application provides a wall-penetrating target behavior recognition method based on channel state information, which comprises the following steps: preprocessing the collected CSI signals; performing PCA data dimension reduction on the preprocessed CSI signals, removing redundant signals and irrelevant information, and extracting optimal subcarriers; performing first-order difference processing on the signals extracted after PCA dimension reduction, and then using a method based on a buffer sliding window to segment effective feature signal segments; converting the effective feature signal segments into feature images with time-frequency domain features through STFT, and inputting the feature images into a pre-trained SE-ResNet18 convolutional neural network for behavior recognition classification. The method can penetrate the wall to realize the behavior recognition of the human target behind the wall. Compared with the traditional deep learning network, the method adopts a small sample transfer learning method combined with a pre-trained model, and the recognition accuracy can reach 91.67% under the conditions of fewer training times, fewer iteration times and shorter training time, so that the behavior recognition classification task can be effectively completed.
Owner:XIAMEN UNIV

Chinese geographic entity prediction method and system based on multilayer deep learning framework

The invention discloses a Chinese geographic entity prediction method and system based on a multilayer deep learning framework, and belongs to the technical field of named entity recognition, and the method comprises the following steps: 1, obtaining a geographic entity data set in the field of Chinese geographic entity recognition, the geographic entity data set comprising a training sample; 2, training and predicting a Chinese geographic entity recognition model through the training sample; 3, adjusting and optimizing model parameters according to the prediction performance of the Chinese geographic entity recognition model; wherein ERNIE-Gram is used as a language preprocessing model in the training and prediction of the Chinese geographic entity recognition model, a tagged corpus is preprocessed, a corresponding dynamic word vector is obtained, a BiLSTM output result is decoded through IDCNN and BiLSTM training, emission score output and CRF, a tagged sequence with the maximum probability is predicted, and the Chinese geographic entity recognition model is obtained. And then classifying each entity in the tag sequence so as to complete the whole process of Chinese geographic entity identification. According to the invention, the accuracy of geographic entity identification is improved from a multi-dimensional perspective.
Owner:HUNAN UNIV OF SCI & TECH

A non-cooperative unmanned aerial vehicle burst frequency point detection method and device based on a Seg-Yolo model

The present application relates to the field of signal detection, and particularly to a non-cooperative unmanned aerial vehicle burst frequency point detection method and device based on a Seg-Yolo model. The Seg-Yolo model proposed by the present application does not require prior sequences of non-cooperative unmanned aerial vehicle signals at all, and does not require prediction of specific sequences, and can directly realize continuous, discontinuous, overlapping and non-overlapping signal frequency point detection in a time-frequency graph. Through preprocessing, image noise reduction and the Seg-Yolo model, the present application reduces the image volume that needs to be processed and simplifies the size of the deep learning network, can accurately lock the center frequency of each frequency point on the basis of reducing the training time and improving the training efficiency, and improves the accuracy and reliability of signal extraction based on complex frequency hopping signals.
Owner:CHENGDU IND VOCATIONAL TECHN COLLEGE

Voice data processing method, electronic equipment, vehicle and storage medium

The embodiment of the invention provides a voice data processing method, electronic equipment, a vehicle and a storage medium, and the method comprises the steps: obtaining multiple segments of voice data, and generating text data corresponding to the voice data; cutting each segment of voice data based on a preset duration range to obtain at least one segment of sub-voice data corresponding to each segment of voice data and text data corresponding to each segment of sub-voice data; extracting acoustic features and semantic features of each segment of sub-voice data, and extracting a text vector of text data corresponding to each segment of sub-voice data; and storing the acoustic features, the semantic features and the text vectors of each segment of sub-voice data into a feature database. According to the embodiment of the invention, the voice data can be cut based on the preset duration range, the duration difference of different voice data is reduced, the time consumption of the voice feature extraction process is avoided, the effective voice features can be extracted, the quality of the voice data is effectively improved, and the training efficiency of the large voice model is improved.
Owner:ZHEJIANG GEELY HLDG GRP CO LTD +1

Cluster-based parallel segmentation learning method, device, equipment and storage medium

The application belongs to the technical field of computers and discloses a parallel segmentation learning method and device based on clusters, equipment and a storage medium. The method comprises the following steps: obtaining a plurality of to-be-learned user terminals and user communication information of each to-be-learned user terminal; performing cluster division on each to-be-learned user terminal according to each to-be-learned user terminal and the user communication information of each to-be-learned user terminal, and determining a plurality of target user clusters; and performing cluster serial segmentation learning according to an aggregated user terminal model and each target user cluster to obtain a target user terminal model, wherein the aggregated user terminal model is obtained by performing parallel segmentation learning on each target user cluster according to the target spectrum resources of each to-be-learned user terminal. Through the above method, the overall training time delay in the segmentation learning process is effectively reduced, the efficiency of segmentation learning is improved, the negative effects caused by network heterogeneity and dynamics are inhibited, and the convergence and accuracy of existing segmentation learning technology are ensured.
Owner:PENG CHENG LAB

Aircraft health reliability analysis method and system

The present invention discloses a health reliability analysis method and system for an aircraft. The present invention decomposes an original image, performs noise identification on the decomposed signal, then denoises the noise signal, and then reconstructs the image using the denoised signal and the non-noise signal, thereby obtaining a denoised original image; then, the denoised original image is input into an aircraft blade damage recognition model to obtain a damage recognition result, and finally, based on the damage recognition result, a health reliability analysis result can be obtained; in this way, through the above-mentioned design, noises of different frequency bands and frequencies can be removed to the greatest extent, thereby reducing the influence of mixed noise on damage recognition, thereby improving the accuracy of model recognition; at the same time, when performing damage recognition, the optimal parameters of the model are determined by an improved genetic algorithm, and multiple sets of model parameters can be evaluated in one iteration process, thereby reducing the model training time and improving the recognition efficiency.
Owner:AVIC LITTON (BEIJING) AVIATION TECH CO LTD

Lightweight electric tower identification algorithm based on improved MobileNetV3

The invention provides an improved MobileNetV3 lightweight electric tower identification algorithm, and belongs to the technical field of electric tower identification algorithms, and the algorithm comprises the steps: firstly, introducing an expansion convolution method into MobileNetV3 to expand the receptive field range of a convolution kernel, so as to reduce the loss of electric tower characteristics; then, a channel attention mechanism SENet in the network is replaced with a two-dimensional attention mechanism SimAM introduced without parameters, and the parameters of the network are reduced; and finally, in normalization operation, batch data normalization of the backbone network is replaced with group data normalization of which the accuracy is stable under various batch sizes, so that errors caused by small-batch data processing are reduced. Experiments on a self-made electric tower database prove that compared with a baseline algorithm, the network keeps a high recognition rate of 95.1%, the parameter quantity of the network is reduced, and rapid convergence and accurate recognition of the network on an electric tower image are realized.
Owner:STATE GRID HENAN ELECTRIC POWER ELECTRIC POWER SCI RES INST

Optical receiver construction method and device, equipment, communication system and storage medium

The invention discloses an optical receiver construction method, device and equipment, a communication system and a storage medium, and relates to the field of network communication, and the method comprises the steps: constructing a first neural network equalizer of a first communication link based on a neural network; configuring a model parameter of a second neural network equalizer as an initial model parameter of the first neural network equalizer; based on the initial model parameter, performing fine tuning training on the first neural network equalizer by using training data of the first communication link to obtain a target neural network equalizer; the target neural network equalizer is suitable for the optical receiver of the first communication link; the first communication link is different from the second communication link. Through migration and multiplexing of knowledge, the construction process of the optical receiver is converted from repetitive low-efficiency labor to efficient adaptive learning, so that the deployment efficiency and expandability of an optical fiber communication system are greatly improved.
Owner:PENG CHENG LAB

Method and device for imaging moving targets in extremely weak light environment based on deep learning

The application discloses a kind of based on deep learning's extremely weak light environment under moving target scattering imaging method and device, it is related to extremely weak light environment under moving target imaging field, for the speckle image obtained by detector, establish neural network to obtain position information and original image recovery information.The accurate position information of target is obtained using prior information and recovered speckle to carry out trajectory recovery.N fixed positions in the detection range are placed target, and the sampling graph of fixed position for training is obtained.N fixed positions of sample speckle are used to train neural network, and after training, fixed parameter becomes the neural network for low-light imaging position classification.Each fixed position of sample speckle is used to train neural network respectively, and after training, fixed parameter becomes the neural network for low-light imaging reconstruction in fixed position.The application uses multiple position neural networks to recover speckle together, obtains more environmental information, and is conducive to generating the accuracy of detection imaging under the complex motion state of target.
Owner:SHANGHAI JIAOTONG UNIV

Work system S3-S5 motor temperature rise test method and device capable of shortening intermittent period

The invention discloses a working system S3-S5 motor temperature rise test method and device capable of shortening the interruption period, and relates to the technical field of motor test. A long-term problem is split into a plurality of independent short-term problems by the PPINN model, and the short-term problems are supervised by a rapid coarse-grained (CG) solver, so that the high calculation efficiency of training the neural network by using small data sets can be utilized to the maximum extent, the training time can be shortened, a big data set can be decomposed into a plurality of small data sets for training by the PPINN model, and the training efficiency is improved. Therefore, under the condition of not enough GPU resources, the PINN can still be trained by using a big data set on the CPU resources, data acquired by the equivalent temperature rise test is used for prediction model training and prediction of equivalent motor temperature rise test time and a temperature rise value, only one time of measurement is needed for one time of temperature rise test, and compared with a traditional method, the experiment time can be greatly shortened, and the test efficiency is improved. The test efficiency is improved, and the labor intensity and cost are reduced.
Owner:CHONGQING UNIV OF TECH

Data processing method and device, federal learning system and electronic equipment

The embodiment of the invention discloses a data processing method and device, a federal learning system and electronic equipment. A specific embodiment of the data processing method comprises the steps of determining a prediction result of a model according to inner product data in response to the received inner product data sent by a follow-up participant in a federated learning system; determining a data residual error according to the prediction result and the corresponding label data; performing encryption processing on the data residual, and sending encrypted residual data to participants except the main participant in the federated learning system; wherein the federal learning system is a system in which at least three parties participate. The implementation mode is related to a model training technology, and the follow-up participant can directly send the inner product data to the main participant. Therefore, the training efficiency of the combined learning model can be improved. And the main participant sends the encrypted residual data to other participants, so that the data security can be ensured while the weight update of each participant is realized.
Owner:BEIJING WODONG TIANJUN INFORMATION TECH CO LTD +1

Robot autonomous navigation method and device based on local information, and storage medium

The application relates to a robot autonomous navigation method based on local information, which comprises the following steps: step 1, a virtual navigation platform is built, an autonomous navigation model is designed, and training data of a virtual navigation process are collected; step 2, based on the training data, a deep reinforcement learning algorithm is used to train the autonomous navigation model; step 3, the trained autonomous navigation model is derived and encapsulated; and step 4, the encapsulated autonomous navigation model is applied to an actual navigation task. Compared with the prior art, the application has the advantages of high scene applicability and low calculation complexity.
Owner:SHANGHAI JIAOTONG UNIV

Multi-agent reinforcement learning system

The invention discloses a multi-agent reinforcement learning system which comprises a local coordination control subsystem and a global coordination control subsystem. The local coordination control subsystem comprises a biological enlightenment behavior module, a cluster behavior control module and a local agent strategy pool, the biological enlightenment behavior module is used for realizing obstacle avoidance and navigation of an agent and coordination control of multiple operations in the agent, and the cluster behavior control module is used for realizing cluster behavior control of the agent; the local agent strategy pool is used for storing agent processing strategies; the global coordination control subsystem comprises a global data updating module, a global arbitration module and a global agent strategy pool, the global data updating module is used for pushing global strategies to agents in a global state and obtaining strategies accumulated by the agents, and the global arbitration module is used for determining an optimal strategy; and the global agent strategy pool is used for storing the optimal strategy. According to the scheme, a bionic intelligent reinforcement learning framework is provided, and the learning rate and performance of the system can be improved.
Owner:ZHUOYI ZHINENG

Data distribution method, device and equipment and computer readable storage medium

The invention provides a data distribution method, device and equipment and a computer readable storage medium. The method comprises the following steps: acquiring a plurality of resource clusters and the unit computing power of an arithmetic unit included in each resource cluster; according to the unit computing power of each computing unit, combining each computing unit to obtain a plurality of combined clusters, and determining the cluster computing power of each combined cluster; obtaining multiple pieces of training data; and based on the cluster computing power of each combined cluster, performing grouping processing on the plurality of pieces of training data to obtain a training data set corresponding to each combined cluster, and distributing the training data set to the corresponding combined cluster so as to train a model by using each combined cluster through the corresponding training data set. According to the method and the device, the computing power of different computing units in a plurality of resource clusters can be activated to support the training of the model, so that the training time can be shortened, and the training efficiency can be improved.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD

Computational graph processing method, device, readable medium and electronic device

The present disclosure relates to a method, device, readable medium and electronic device for processing a computational graph. The method for processing a computational graph obtains a target computational graph corresponding to a machine learning model to be trained, performs node fusion processing on the target computational graph to obtain a fused computational graph including multiple subgraphs; according to multiple preset segmentation methods of each operator node, effectively segments the operator nodes in the fused computational graph to obtain multiple segmentation data flow graphs corresponding to the fused computational graph, and the segmentation data flow graph is a target computational graph with an effective segmentation method; then, a parallel configuration strategy corresponding to the target computational graph is searched according to the segmentation data flow graph, so that a model training strategy that is a hybrid of pipeline parallelism, data parallelism and model parallelism can be automatically and efficiently generated, which can effectively improve the model training efficiency of the machine learning model and shorten the model training time.
Owner:DOUYIN VISION CO LTD +1

Multi-feature charging load prediction method and system

The invention discloses a multi-feature charging load prediction method and system, and the method comprises the steps: obtaining a historical load sample data set, and carrying out the preprocessing of the historical load sample data set, and obtaining a complete data set; optimizing the complete data set by using a first optimization algorithm and a second optimization algorithm to obtain training parameters; and constructing a prediction model by using the training parameters, predicting the load according to the prediction model to obtain a prediction result, and performing data analysis on the prediction result, thereby improving the prediction accuracy and stability, and providing technical support for accurate prediction of the charging load.
Owner:NARI NANJING CONTROL SYSTEM CO LTD

Point cloud data sparse convolution training method and system

The invention provides a point cloud data sparse convolution training method and system. The method comprises the steps of obtaining to-be-trained point cloud data; performing preprocessing operation on the point cloud data to obtain a target convolutional layer; disassembling the target convolutional layer into a convolutional layer group; the convolutional layer group comprises a plurality of convolutional layers of which the size is smaller than that of the target convolutional layer; extracting features of the convolutional layer group; performing normalization processing on the features to obtain numerical values and threshold values corresponding to the features; screening the numerical values by using the threshold value to obtain a target numerical value; and obtaining a target feature based on the target numerical value, so as to solve the problems that when feature extraction is performed on the point cloud data at present, sparsity of the point cloud data disappears, so that the calculation amount of the point cloud data is very huge, the training duration and size of a model are greatly increased, and the risk of overfitting is improved.
Owner:NANJING UNIV

A grayscale image colorization method based on generative adversarial network

The present invention discloses a grayscale image colorization method based on a generative adversarial network. The method first selects a quantitative color picture group in the COCO image data set, decolorizes it and makes it into a training set. Secondly, a generative adversarial network architecture is constructed so that the generator model completes pre-training therein, and then the discriminant model and the pre-trained generative model are alternately trained, and the parameters are adjusted to obtain a trained model. After the test data is input into the model, the grayscale image colorization can be realized. The present invention has a great improvement in the optimization of the training method and the data set through the pre-training method and process of the generator, and can greatly shorten the training time on the basis of ensuring the generalization quality of the training quality and the final generated image, and is flexible; and the idea of ​​U-Net is used to train and test on the COCO data set, which can greatly reduce the disadvantages of the traditional method that manual intervention is required and it is difficult to perform fine coloring work at the pixel level of large-size images.
Owner:NANJING UNIV OF POSTS & TELECOMM