64results about How to "Reduce video memory usage" patented technology

The invention belongs to the technical field of model training, and particularly relates to a large model increment training method and system based on dynamic sparsification. The method comprises the following steps: S1, evaluating the parameter importance of a large model by adopting a multi-dimensional evaluation method, and reflecting the contribution of parameters to the performance of the large model; s2, performing dynamic sparsification control on the large model structure by adopting a self-adaptive structure adjustment method; s3, performing incremental training management on the large model by constructing a capacity-adjustable empirical playback buffer pool and proposing a multi-objective loss function; and S4, carrying out model compression optimization on the large model by adopting a mixed precision quantification strategy. The method has the characteristics that the network structure can be dynamically adjusted by evaluating the importance of model parameters in real time, so that the efficient training is realized while the model performance is ensured.

The present invention discloses a super-resolution reconstruction method for industrial CT images based on deep learning, and its application relates to the field of industrial CT image technology, in order to solve the problem of low image resolution caused by equipment limitations. The steps include data acquisition and preprocessing, data enhancement, edge enhancement module construction, convolution downsampling module construction, RRDB residual module construction, upsampling and reconstruction, model training and optimization, and splicing trace processing. By using the present invention, super-resolution reconstruction of multi-material CT images can be achieved, and the resolution and clarity of the images can be improved.

The invention discloses a big language model reasoning optimization method, system and device and a storage medium, which are corresponding schemes, in the scheme, a data clustering and quantification mechanism is introduced in a big language model reasoning process, when the size of a KV cache exceeds a preset threshold value, firstly, KV cache data is subjected to clustering division, and when the size of the KV cache exceeds the preset threshold value, the KV cache data is subjected to clustering division; and performing low-precision quantization processing on part of data, and replacing the other part of data with a clustering center, thereby achieving the purpose of reducing the KV cache size. Through the scheme of the invention, the video memory occupation in the reasoning process can be obviously reduced, the reasoning efficiency is improved, and the utilization rate of system resources is optimized.

The invention discloses an unmanned aerial vehicle low-altitude visual angle target detection method and device based on deep learning, and belongs to the technical field of computer vision. The method comprises the following steps: performing data enhancement on a collected target detection object image data set, and dividing the enhanced target detection object image data set into a training set, a verification set and a test set; an attention mechanism module is added in a backbone network of the YOLOV7-OBB model; the YOLOV7-OBB model is trained based on the training set, the YOLOV7-OBB model in the training process is evaluated based on the verification set, and the trained YOLOV7-OBB model is obtained; and inputting the test set into the trained YOLOV7-OBB model, and carrying out target detection to obtain a detection result. By enhancing a target detection object image data set and adding an attention mechanism module, the YOLOV7-OBB model fully learns key feature information of a target, and the detection precision and robustness are remarkably improved.

The invention discloses an information processing method, electronic equipment and a computer readable storage medium, and relates to the technical field of large model technology and data processing. The method comprises the steps that in the forward reasoning process of a target machine learning model, parameter information corresponding to a query request is obtained, and the parameter information is obtained after the query request is encoded; performing quantization compression on the parameter information according to a preset quantization mode to obtain quantization compression information; performing quantitative compression processing on the parameter information by adopting the quantitative compression information to obtain cache information; and reasoning based on the cache information to obtain a query result corresponding to the query request. According to the method and the device, the technical problems that offline compression key value caching and quantitative calibration steps are complicated, and the model precision is influenced by calibration data, so that the model precision is relatively low in the prior art are solved.

The invention discloses a texture resource loading method and device, computer equipment and a computer readable storage medium, and relates to the technical field of computers.The method comprises the steps that in response to reloading of texture resources, resource information of a texture array is obtained, and repositioning the byte address range of each texture in the texture array according to the resource information of the texture array, determining the memory layout of the texture array, and performing traversal memory allocation on each texture in the texture array by using the memory layout of the texture array so as to reload the texture array according to the byte address range pointed by the traversal memory allocation. According to the scheme, the byte address range of each texture in the texture array is repositioned through reloading of the texture resources, so that the texture resolution in the texture array is dynamically adjusted according to hardware configuration, and part of pixel information in the texture array is cut off under the condition that the equipment resources are limited; the memory and video memory occupation of the texture resources is reduced, and the loading time of the texture resources is shortened.

The invention discloses an underwater target detection method based on differential attention. The method comprises the following steps: acquiring an underwater image to be detected; based on the underwater image data set, constructing a lightweight underwater target detection network model based on a differential attention mechanism; constructing a joint loss function, and performing end-to-end training on the lightweight underwater target detection network model to obtain a trained lightweight underwater target detection network model; performing mathematical equivalence fusion on the lightweight underwater target detection network model to generate a lightweight reasoning model; and inputting the obtained underwater image to be detected into the lightweight reasoning model to realize target detection of the underwater image. According to the method, a differential attention feature interaction mechanism is introduced, common-mode noise is stripped through differential calculation, and the detection precision and real-time performance of an underwater fuzzy scene and a tiny target are remarkably improved in combination with a feature pyramid network integrating dynamic scale perception and semantic gating.

The invention relates to an image denoising method, a model training method and device, electronic equipment and a computer program product, relates to the technical field of image processing, and can be applied to a scene for denoising an image containing noise. The method comprises the steps of obtaining a to-be-processed image, and performing decomposition transformation processing on the to-be-processed image to obtain a plurality of frequency sub-graphs; performing feature extraction processing based on the plurality of frequency sub-images to obtain intermediate image features; performing up-sampling processing on the intermediate image features to obtain recovered image features, the up-sampling processing being an inverse process of decomposition transformation processing; and generating a de-noised image according to the restored image features and the to-be-processed image. According to the method, video memory occupation in the image processing process is effectively reduced, the calculation efficiency of the model is improved, and meanwhile, detail and texture information of the image is reserved; moreover, the image denoising effect is optimized, and the information loss in the denoising process is reduced.

This invention relates to a segmented hybrid inference method for large language models based on uncertainty-driven approaches. The method includes acquiring current text data and historical state features to estimate the uncertainty index of the current segment; minimizing a unified scheduling objective function based on the uncertainty index to obtain a target inference pattern; performing inference calculations based on the target inference pattern to generate information contribution values ​​corresponding to key-value pairs; calculating the corresponding dynamic merging control probabilities based on the uncertainty index and information contribution values, and performing weighted merging or pruning on the key-value pairs to be merged to obtain compressed key-value pairs; defining a deviation metric and limiting the deviation metric to not exceed a preset upper bound determined by the dynamic merging control probability set and the uncertainty index; triggering a rollback process when the deviation exceeds this limit; otherwise, feeding back the compressed key-value pair state to the next segment for iterative iteration until the inference of all segments is completed; thereby reducing memory usage and inference latency while ensuring accuracy.

The present application relates to the field of digital image processing and information security, and discloses a document tampering detection method and system based on image data processing, comprising the following steps: first, extracting the noise residual and microscopic penetration characteristics of the document image, and constructing a physical potential energy field and a virtual viscous resistance field; then, using a Darcy law variant model for dynamic evolution, generating a virtual flow velocity vector field to simulate the sliding behavior of fluid in heterogeneous media; subsequently, constructing a heterogeneous graph based on the flow field divergence singular point and streamline trajectory, using a graph neural network to aggregate the node dynamics characteristics for deep reasoning, and finally generating a tampering positioning mask. The present application innovatively introduces fluid mechanics field theory, converts hidden static texture differences into significant dynamic flow field anomalies, solves the problem that the prior art is difficult to capture microscopic tampering traces, and significantly improves the detection accuracy and generalization ability in complex document scenarios.

The invention relates to the technical field of computer vision and coal mine intelligent mining, and discloses a lightweight working face three-dimensional reconstruction method and device fusing geometric prior constraints, and the method comprises the steps: firstly screening a dynamic effective region based on a projection relation and texture features, and removing static redundant scenes; performing sparse visual reasoning and depth regression only for the effective area to generate an initial depth map; carrying out physical structure correction on the depth map by utilizing geometric priori such as vertical upright posts and parallel top plates of the hydraulic support; and finally, constructing an optimization objective function containing deviation constraints of the vertical column perpendicularity and the top plate parallelism, and completing high-precision fusion of the incremental point cloud. According to the method, inference delay is reduced by reducing invalid calculation, structural distortion and registration drift caused by an underground severe environment are effectively inhibited by using a geometric law, and real-time and high-fidelity reconstruction of a working face scene is realized.

The invention discloses an edge terminal-oriented memory efficient model fine tuning method and system, which realize decoupling of a backbone network and a fine tuning process by constructing a parallel side network module, and avoid video memory occupation caused by backbone gradient return. A double-adapter module is arranged, modeling is carried out on same-layer features and cross-layer context information, and the feature expression precision is improved. And constructing a feature fusion module, and performing adaptive weighting on different path outputs through learnable gating. A backbone grouping module is integrated, dynamic grouping is carried out on a backbone network based on interlayer similarity, and redundant modules and calculation overhead are reduced. And through the fine tuning execution module, only back propagation and parameter updating are carried out on the side network, and a trunk freezing state is kept, so that the memory and training cost is reduced. According to the method, the memory efficiency and the training speed of the edge fine adjustment process are improved, high-precision model self-adaption is achieved with extremely low calculation burden, and application in the fields of cloud edge collaborative intelligence and the like of unmanned aerial vehicles, robots, vehicle-mounted terminals and the like is effectively supported.

The application provides a method and device for quantifying elastic KV cache through computing power of an intelligent computing cloud platform, and relates to the technical fields of intelligent computing centers, intelligent computing centers, computing power infrastructure and intelligent computing cloud technology.The method comprises the following steps: S1, dividing historical tokens into multiple cache blocks, quantifying KV data and writing the data into corresponding cache blocks, and selecting multiple candidate anchor points; S2, calculating block-level summary data; S3, in response to a new target token, scoring the cache blocks to generate cache block scores and screening out candidate cache blocks; S4, calculating uncertainty index data and determining a target cache block with to-be-restored precision according to the uncertainty index data; and S5, locating an upstream target anchor point and locally playing back the historical tokens based on the upstream target anchor point to generate target high-precision KV data of the target cache block.The application can greatly improve the quantification effect of KV cache of the intelligent computing cloud platform.

The invention discloses an unmanned aerial vehicle visual angle dense small target detection method and device based on deep learning, and belongs to the technical field of target detection. Aiming at the problem that a YOLOv7 network is insufficient in dense small target feature extraction capability in the prior art, the method comprises the following steps: acquiring an unmanned aerial vehicle image data set, acquiring a dense small target image from the unmanned aerial vehicle image data set, and preprocessing the dense small target image; constructing a dense small target detection model based on YOLOv7, wherein the dense small target detection model comprises a backbone network, a neck network and a head network; wherein a small target detection head is added in the dense small target detection model, and a dense detection module is introduced in the head network; and detecting the dense small target image through the dense small target detection model to obtain a detection result. Therefore, by improving a YOLOv7 detection head and introducing a dense detection module, secondary reasoning on a dense small target area is increased, and the dense small target detection effect is remarkably improved.

This invention provides a rapid landslide area segmentation method based on high-resolution satellite remote sensing data and deep learning algorithms, belonging to the field of ground scene technology. The invention downsamples the original satellite remote sensing image to obtain a first image, extracts reflectance data from the red and near-infrared channels, calculates the reflectance difference and sum of reflectance values, and normalizes them to obtain a vegetation index to construct a vegetation layer. The first image and the vegetation layer are superimposed and stitched together, and feature enhancement is performed to obtain a vegetation feature map. This map is input into a convolutional neural network to output a landslide probability map. A two-dimensional coordinate set is constructed and cropped to obtain high-resolution test patches. The spatial gradient magnitude of the local vegetation index is calculated and weighted by a preset enhancement coefficient to generate edge-enhanced patches. The edge-enhanced patches are input into a semantic segmentation network to output a local landslide map, which is then backfilled into the initial image to obtain a landslide area segmentation map. This invention constructs a cascaded segmentation system to achieve efficient and accurate segmentation of landslide areas.

The invention discloses a face recognition model optimization method, device and equipment. The method comprises the following steps: acquiring a pre-trained convolutional neural network model; selecting a key layer in the pre-trained convolutional neural network model; adding a parallel Conv-LoRA layer at the position of a key layer of the pre-trained convolutional neural network model so as to finely adjust the output of the key layer; and acquiring a face image data set in an actual application scene, and training the Conv-LoRA layer by taking the face image data set as training data. According to the method, training parameters and video memory occupation can be reduced, efficient model fine tuning is realized, the performance is better in an actually used data scene, and meanwhile, migration and application on use scenes under different data distributions can be conveniently realized.

This invention discloses an intelligence generation method and system based on feature fingerprint storage and spatiotemporal geometric correction, belonging to the field of intelligent remote sensing image processing technology. The method involves: accessing heterogeneous data streams generated from multi-source remote sensing images in a synchronized time sequence; inputting a shared backbone network and a modality adaptation layer to generate a current feature stream in a unified semantic space; asynchronously retrieving historical baseline features from an in-memory feature fingerprint database based on geographic coordinates; fusing satellite imaging parameters with the current feature stream and inputting it into a spatial transformation network, resampling historical baseline features using a regression transformation matrix to achieve spatiotemporal geometric correction in the feature domain; weighted fusing of the current feature streams from each modality to generate a fused feature stream; and parallel interpretation and semantic encapsulation of the fused feature stream to generate a natural language intelligence report. This invention reduces memory usage and data throughput, shortens the intelligence generation cycle, reduces the false alarm rate, and achieves synergistic optimization of timeliness, accuracy, and automation.

The invention relates to a large language model segmentation hybrid reasoning method based on uncertainty driving, which comprises the following steps of: acquiring current text data and historical state characteristics to pre-estimate an uncertainty index of a current segment; according to the uncertainty index, minimizing the unified scheduling target function to obtain a target reasoning mode; performing reasoning calculation according to the target reasoning mode, and generating information contribution degrees corresponding to the key values; according to the uncertainty index and the information contribution degree, calculating a corresponding dynamic merging control probability, and performing weighted merging or pruning on the to-be-merged key value pairs to obtain compressed key value pairs; defining a deviation metric, and limiting the deviation metric not to exceed a preset upper bound determined by the dynamic merging control probability set and the uncertainty index; if so, triggering fallback processing; otherwise, the compressed key value pair state is fed back to the next segment for loop iteration until reasoning of all segments is completed; therefore, the video memory occupation and the reasoning delay are reduced on the premise of ensuring the precision.

This invention discloses a cloud-based multi-pretrained language model management and inference method and electronic device, including receiving model management requests and inference requests issued by tenants through a dispatcher; wherein, the model management request is specifically a tenant initiating a model management request to change the content and structure of the vBert model instance tree; a shallow feature lookup table is constructed and maintained through a manager to update the vBert model instance tree; and the model management requests and inference requests are scheduled and processed in a pipeline manner through a scheduler.

The application discloses a speech recognition fine-tuning method based on subspace decomposition and reorganization. The low-rank space of the LoRA module is equivalently decomposed into multiple subspaces, and learnable weights are added to different subspaces, so that the reorganization of all subspaces is realized. The reorganized subspaces can be transformed into an efficient calculation mode during training and an inference mode during inference, which significantly improves the inference and storage efficiency, and solves the problem of high inference cost during high concurrency request while ensuring efficient fine-tuning of parameters.

This invention discloses a cross-modal data processing system for the safe operation of hydrogen refueling stations, including a raw data acquisition and processing module, a full-variable safety scanning module, a physical relationship coupling diagnosis module, an adaptive operating condition clustering module, a question-answer pair construction module, a hydrogen refueling station time-series command data acquisition module, and a fault type identification module. By constructing a three-layer semantic enhancement logic and model adaptation strategy, this invention effectively solves the technical problems in the prior art, such as the lack of supervision signals in the raw data of hydrogen refueling stations, the difficulty in identifying hidden faults under complex operating conditions, and the difficulty in adapting heterogeneous feature space models.

The application relates to the technical field of intelligent manufacturing and computer vision, and discloses a robot welding action generation method and system and electronic equipment. The application realizes adaptive elimination of visual redundancy in the time sequence dimension through global time sequence merging, guarantees complete reservation of key visual detail features in a complex welding scene through diversity perception pruning, realizes collaborative simplification of text and visual features through attention weight screening pruning, and completes dynamic adaptive optimization of bimodal features through semantic perception pruning. The application solves the defect that the prior art cannot adaptively process visual features, removes redundant features layer by layer, reduces the calculation load, greatly improves the real-time performance of welding work, accurately reserves the core visual and text semantic features required for welding action generation, fully guarantees the control accuracy of the welding action, and significantly improves the adaptive perception capability and work reliability of the robot welding system in a complex scene.

The application discloses a Mongolian-Chinese multi-expert neural machine translation method and system based on decision layer relative strategy optimization, and the method comprises the following steps: acquiring Mongolian-Chinese bilingual parallel corpus and preprocessing to obtain Mongolian-Chinese translation training data; training a basic translation model based on the Mongolian-Chinese translation training data to obtain a Mongolian-Chinese task adaptation model; performing sensitivity analysis on the Mongolian-Chinese task adaptation model to obtain hierarchical sensitivity results of each network layer; according to the hierarchical sensitivity results and the complexity of an input sentence, different network layers of the Mongolian-Chinese task adaptation model are allocated with different quantization precisions to obtain a light-weight translation model; a course type training sequence is constructed, and an optimized Mongolian-Chinese translation model is obtained based on a composite reward function; a Mongolian sentence to be translated is input into the optimized Mongolian-Chinese translation model to generate a corresponding Chinese initial translation; and a final Chinese translation is determined according to the Mongolian sentence to be translated and the Chinese initial translation.

This invention discloses a decoder-free multi-branch attention table large-scale model and its reinforcement learning training method. Addressing the problems of redundant decoder structures, high computational overhead, and mismatch between training objectives and evaluation metrics in traditional supervised learning models, this invention proposes a multi-branch attention network based on an encoder-only architecture. This method removes the decoder portion from the traditional Transformer architecture, directly extracting feature interaction information using a multi-branch encoder. During the training phase, the Group Relative Policy Optimization (GRPO) algorithm is introduced for reinforcement learning training, abandoning the Critic network in traditional RL and directly calculating the relative advantage by sampling a set of outputs from the same input. This invention significantly reduces the number of model parameters and memory usage, while improving the accuracy and inference speed of table data processing by directly optimizing sequence-level rewards.

The invention provides a high-efficiency hyperspectral remote sensing image generation method based on spatial spectrum information self-selection. The method mainly comprises the following three core steps: 1, multi-level self-selection spatial feature coding; 2, multi-scale semantic fusion based on mixed pooling; and 3, spatial prior guidance and waveband relevance modeling. Starting from the characteristics of a hyperspectral remote sensing image generation task, a generation framework guided from spatial characteristics to spectral information driving is constructed, and a spatial-spectral information self-selection mechanism and a lightweight calculation strategy are introduced, so that the model can adaptively and dynamically pay attention to important spatial regions and spectral bands. The problems of insufficient physical consistency, redundant feature information, high video memory occupation and the like of a current hyperspectral remote sensing image generation method are effectively relieved, and the method has the advantages of high reconstruction precision, low calculation complexity, high training reasoning speed and the like; and high-quality hyperspectral remote sensing image data support can be provided for remote sensing downstream tasks such as image classification and change detection.

This invention discloses a three-dimensional breast ABUS image classification method, electronic device, and computer-readable storage medium based on a tokenized bi-branch selective state-space model. The method preprocesses the three-dimensional ABUS volume data and inputs it into a hierarchical pyramidal classification network. The network constructs local convolutional branches and a global state-space branch in its basic modules: the local branch uses lightweight three-dimensional grouped convolution to extract texture and boundary morphology; the global branch aggregates features into a token map through voxel token generation, then performs multi-axis bi-directional selective state-space scanning and adaptive fusion using routing weights. After detoxing, the core features are injected through a gating mechanism. Finally, the classification result is output through three-dimensional global average pooling and a fully connected layer, enhancing the ability to model long-range dependencies across slices with near-linear complexity.

The application discloses a large language model inference acceleration method for real-time voice interaction and electronic equipment, and relates to the technical field of artificial intelligence. The method comprises the following steps: obtaining optimal recognition text output by an automatic speech recognition engine as a draft sequence; inputting input data containing the draft sequence into a target large language model, and calculating posterior probability distribution of all token positions in the draft sequence through single forward propagation parallel calculation; determining a model output candidate sequence according to the posterior probability distribution of each position, comparing the model output candidate sequence with the draft sequence, and completing inference output based on the comparison result. The application does not need to additionally train, deploy and maintain an independent draft model, effectively reducing system engineering complexity and memory occupation. Meanwhile, the application scheme is executed based on the original architecture of the target large language model throughout the whole process, without the need to modify the model network structure, and without the need to carry out retraining or fine-tuning, so that the original generality and recognition accuracy of the pre-trained large language model are completely retained.

The present application relates to the field of artificial intelligence technology, and specifically provides a method, device, electronic device and storage medium for training a large model in a wide area network. A method for training a large model in a wide area network, comprising performing the following steps for each target GPU in each GPU: performing forward and backward propagation processing on batch data, obtaining the first gradient value of the locally generated target gradient slice and the second gradient value of each first GPU in other wide area network nodes that is assigned the same gradient slice; performing parameter update according to the first gradient value and each second gradient value corresponding to the target gradient slice, and obtaining the parameter value of the first parameter slice corresponding to the corresponding optimizer slice; receiving the parameter value of the respective second parameter slice sent by each first GPU; receiving the parameter value of the respective third parameter slice sent by each second GPU in the same wide area network node. In this way, both the reduction of the video memory usage of each GPU and the improvement of the model training performance can be taken into account.

This invention relates to a three-dimensional defect segmentation method, system, and storage medium, belonging to the interdisciplinary fields of computer vision, deep learning, and nondestructive testing. The three-dimensional defect segmentation result is obtained by inputting the industrial CT volume data of the object to be inspected into a 2.5D segmentation network composed of an encoder, a spatial feature displacement module, and a decoder. This invention achieves efficient three-dimensional context awareness, significantly improving defect segmentation accuracy and three-dimensional morphological integrity. The segmentation result has topological connectivity and smooth boundaries, and its computational complexity and memory usage are far lower than those of a full 3D network. It can meet the real-time requirements of industrial online inspection and has broad application prospects in high-end manufacturing.

The invention provides a GPU storage and calculation integrated pre-filling decoding separation large model reasoning acceleration method and system, and the method comprises the steps: obtaining an original text, carrying out the operation of the original text through a GPU, and generating a corresponding key value cache and a query vector; based on a storage and calculation integrated memory, respectively reading the key vector, the numerical vector and the query vector from the key value cache for calculation, and generating a context vector; the method comprises the following steps: acquiring a plurality of request sequences, performing dynamic scheduling based on a preset time window or a request quantity threshold value, and sorting according to sequence lengths; carrying out zero-filling packaging on the input sequence by utilizing a GPU (Graphic Processing Unit) and executing pre-filling calculation to obtain an initial key value cache and a query vector; and respectively conveying the key value cache and the query vector to a storage area and a ready queue.