348 results about "Inverse quantization" patented technology

The present disclosure provides a variable-bit-rate image compression method and system, an apparatus, a terminal, and a storage medium. The variable-bit-rate image compression method includes: obtaining an initial feature map from a to-be-encoded image; quantizing the initial feature map by a dead-zone quantizer; performing entropy encoding on the quantized feature map and hyper-prior information to obtain a compressed bit-stream; performing entropy decoding on the compressed bit-stream, and recovering quantized hyper-prior information and the quantized feature map; performing inverse quantization on the quantized feature map to obtain a reconstructed feature map; obtaining a reconstructed image from the reconstructed feature map; and adjusting quantization and inverse quantization parameters according to a target bit-rate or target distortion. The present disclosure provides a precise bit-rate control solution, makes the bit-rate of the compressed bit-stream better adapt to the dynamic change of a network bandwidth, and has an extremely high actual application value.

The invention relates to the technical field of voice processing, can be applied to service system platforms of medical health, financial science and technology, communication and the like, and discloses an audio compression and reconstruction method, device, equipment and medium. Residual vector quantization and inverse quantization are carried out to generate basic spectrum features; and compensating a high-frequency component by adopting a spectrum expansion network, predicting a time domain error in combination with a long-short-term memory network, generating a time domain residual compensation signal, and superposing the time domain residual compensation signal with the reconstructed time domain audio signal to obtain a target audio signal. Through residual vector quantization and neural network modeling, the audio reconstruction quality under low-bit-rate compression is improved, spectrum detail reservation and time domain error compensation are optimized, meanwhile, the calculation complexity is reduced, and the method is suitable for high-sampling-rate and resource-limited scenes.

Provided in the present invention is a parameter-efficient large-language fine-tuning federated learning framework, comprising the following steps: performing modeling on LoRA adapters of different edge clouds; since different weights exhibit different average performances on the LoRA adapters, using singular values to quantify the importance of the weights, and therefore, before each round of independent training of the LoRA adapters using N edge clouds, using a matrix singular value to decompose a BA matrix in the LoRA adapter for each trainable weight; configuring heterogeneous LoRA adapters on the basis of the importance of the weights; and using different numbers of quantization bits to quantize a pre-trained model, and performing high-precision inverse quantization on the pre-trained model only when matrix multiplication is executed, wherein the pre-trained model is quantized to the maximum number of quantization bits on the basis of the memory budget of the edge clouds. The present invention has the following beneficial effects: the present invention determines the optimal fine-tuning model structure, thereby improving the performance of LLM fine-tuning, and adapts to heterogeneous and resource-constrained edge clouds.

A device for decoding encoded dynamic mesh data determines a set of quantized integer coefficient values for displacement vectors of the encoded dynamic mesh data; determines a quantization parameter based on one or more syntax elements included in a displacement sub-bitstream of the encoded dynamic mesh data; inverse quantizes, based on the quantization parameter, the set of quantized integer coefficient values to determine a set of fixed-point dequantized coefficient values; determines a set of fixed-point transformed coefficient values based on the set of fixed-point dequantized coefficient values; converts the set of fixed-point transformed coefficient values to a set of floating-point transformed coefficient values; inverse transforms the set of floating-point transformed coefficient values to determine a set of reconstructed displacement vectors; and determines a reconstructed deformed mesh based on the set of reconstructed displacement vectors.

The invention relates to the technical field of voice processing, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a voice signal compression method, device, equipment and medium, which comprises the following steps: executing Fourier transform on an initial voice signal to extract an amplitude spectrum and a phase spectrum, respectively processing the amplitude spectrum and the phase spectrum to generate features, and splicing the features to obtain a compressed voice signal; the method comprises the following steps: carrying out quantization by adopting a residual vectorization mode to generate a compressed feature vector, executing entropy coding to obtain a compressed code stream, recovering the compressed feature vector at a decoding side, reconstructing a spliced feature through residual reverse quantization, enhancing feature expression through up-sampling operation, and restoring a voice signal through inverse Fourier transform. According to the method, a dual-path processing structure of amplitude features and phase features is constructed, feature compression is realized in combination with residual vectorization and entropy coding, inverse quantization and up-sampling enhancement are executed in a decoding stage, a spectrum energy structure and phase continuity are effectively reserved, and reconstruction precision and fidelity of voice signals are improved under the condition of low bit rate.

A method and an apparatus are disclosed for patch-based mesh coding. In the disclosed embodiments, a mesh decoding device decodes a bitstream to reconstruct patch information and a patch-based base mesh. The mesh decoding device reconstructs base mesh vertices and connectivity by using the patch information and the patch-based base mesh. The mesh decoding device generates predicted vertices and connectivity based on the reconstructed base mesh vertices and connectivity. The mesh decoding device decodes a bitstream to reconstruct a transform-coefficient image, and reconstructs vector differences of vertices by unpacking, inverse quantizing and inverse transforming the transform-coefficient image. The mesh decoding device adds the predicted vertices and the vector differences to reconstruct mesh vertices and connectivity.

The invention relates to the technical field of integrated circuit design and artificial intelligence hardware acceleration, and particularly discloses a quantization precision adaptive switching hardware acceleration architecture. Hardware is divided into a static area and a dynamic area, wherein the static area comprises a pre-processing module, a post-processing module, a control module and a reconfigurable logic loading control block which run all the time; the dynamic region bears a quantization and inverse quantization module composed of a plurality of reconfigurable logic units. The method is characterized in that a model precision instruction is analyzed through a control module, and a reconfigurable logic file with corresponding precision is dynamically loaded to a dynamic area from external starting equipment by a loading control block according to an internal address mapping table, so that seamless switching of different quantization precision is realized on the hardware level, and the whole chip does not need to be burnt again. According to the design, through a modularized and reconfigurable hardware structure, the limitation of fixed-precision hardware in coping with diversified AI models is effectively solved, and the deployment flexibility and energy efficiency are remarkably improved.

The invention discloses a code rate adaptive image compression method and system, and the method comprises the steps: obtaining an input image, and calculating the local information entropy of the input image to generate a spatial adaptive mask; obtaining target code rate and actual code rate information to generate a code rate control signal; and dynamically selecting a calculation path by using a mask through a dynamic reversible neural network, and executing reversible quantization transformation according to the control signal to obtain a compressed bit stream and actual code rate information for closed-loop feedback. According to the method, a symmetric reversible framework with shared parameters is constructed, so that the model storage requirement is reduced; the calculation depth of the network is dynamically adjusted through entropy sensing gating, and the overall calculation amount is reduced; and a composite control and PID optimization mechanism is adopted, so that continuous and smooth code rate control is realized. The deployment and application efficiency of the compression system in a resource limited scene can be effectively improved.

The invention provides a hyperspectral remote sensing image compression method based on attention and quantization coding optimization, and the method comprises the steps: carrying out a network model training process: carrying out the processing, cutting and enhancement of hyperspectral remote sensing image data, and constructing a sample set for training; extracting low-dimensional feature representation of the sample data by using a lightweight encoder, wherein the encoder integrates a convolutional layer and a spectrum multi-head self-attention module; a decoder fusing a space-spectrum attention mechanism is adopted to gradually reconstruct a hyperspectral remote sensing image from low-dimensional features; optimizing coding and decoding model parameters through a combined loss function; a quantization coding two-stage compression process: performing adaptive quantization on the features, and mapping the floating point type features into discrete integers based on a logarithm mapping strategy; performing two-stage coding compression on the quantized features; and recovering feature representation through decoding and inverse quantization, and inputting a trained decoder network to reconstruct a hyperspectral remote sensing image.

The invention relates to the technical field of steel coil detection, and discloses a multi-mode-based steel coil surface defect detection method, device and equipment and a medium, and the method comprises the following steps: obtaining an input image containing a steel coil surface and a task description corresponding to the input image; performing code conversion on the input image and the task description, and determining a discrete sequence; inputting the discrete sequence into an encoder and decoder model to obtain a task output sequence; and performing inverse quantization reasoning according to the task output sequence, and determining a detection frame, a mask and defect description information of an input image so as to complete surface defect detection of the steel coil. According to the method, samples of different defect types can be rapidly obtained through the sample pair formed by the input image and the task description, rapid iteration of model training is facilitated, and meanwhile, through the multi-modal image set, the detection frame, the mask and the defect description information are directly output, the steel coil surface defect detection precision is improved, and the detection application range is widened.

A quantum computing device is formed using a first chip (302) and a second chip (306). The first chip has a first substrate (303), a first set of pads (312A, B), and a set of Josephson junctions (304) disposed on the first substrate. The second chip has a second substrate (307), a second set of pads (308) disposed on the second substrate opposite the first set of pads, and a second layer (310) formed on a subset of the second set of pads. The second layer is configured to bond the first chip and the second chip. The subset of the second set of pads corresponds to a subset of the set of Josephson junctions selected to avoid frequency conflicts between qubits in a set of qubits. Qubits are formed using Josephson junctions in the subset of Josephson junctions and another Josephson junction not in the subset that is caused to be unavailable for forming qubits.

The invention provides a model reasoning method, device and equipment and a storage medium, and relates to the technical field of computers, in particular to the artificial intelligence fields of neural networks, model reasoning, model quantification and the like. According to the specific implementation scheme, a to-be-processed quantization weight matrix of a model is read into a register of a processor from a cache of the processor; performing inverse quantization fusion calculation based on elements of the quantization weight matrix to be processed in the register and an activation matrix of the model to obtain a reasoning result of a current operator of the model; and writing the reasoning result of the current operator into a memory of the processor for operators after the current operator to use. The calculation amount in the reasoning process can be reduced, and the calculation speed and efficiency of reasoning can be improved.

A data processing method, applied to the field of artificial intelligence, and comprising: acquiring first data, wherein the first data is obtained by means of a machine learning model on the basis of first input data; performing non-uniform quantization processing on the first data to obtain first compressed data, and storing the first compressed data in a memory; and reading the first compressed data from the memory, and performing inverse quantization processing corresponding to the non-uniform quantization processing on the first compressed data to obtain second data, wherein the second data and second input data are used for being input into the machine learning model, and the second input data is data input into the machine learning model after the first input data. According to the present application, non-uniform quantization is performed on data on the basis of non-uniform distribution characteristics of the data, so that the distribution characteristics of the data can be better met, and a quantization result having a smaller overall error or average error can be obtained, thereby improving the processing precision of models.

The invention provides a floating-point number quantization method and device, a floating-point number inverse quantization method and device, equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises: based on a compression rule, determining quantization information corresponding to an index of each floating-point number in floating-point numbers to be quantized, the quantization information corresponding to the index of each floating-point number comprising a first quantization value and / or a second quantization value, the compression rule comprises a rule that an index which indicates that quantization information with a low compression degree belongs to is greater than an index which indicates that quantization information with a high compression degree belongs to, and for each floating-point number in the floating-point numbers to be quantized, based on a first quantization value corresponding to the floating-point number, performing quantization processing on a mantissa of the floating-point number, and / or performing quantization processing on the mantissa of the floating-point number based on a second quantization value corresponding to the floating-point number. And quantizing the index of the floating-point number based on the second quantized value corresponding to the floating-point number. By adopting the method and the device, the required average error can be met during quantization.

The invention discloses a quantization method, a medium, computer equipment and a program product. The method comprises the following steps: acquiring a difference matrix between a current parameter matrix and a pseudo quantization parameter matrix of a neural network; the pseudo quantization parameter matrix is obtained by sequentially performing quantization processing and inverse quantization processing on the current parameter matrix; projecting the difference matrix to a plurality of target feature spaces to obtain a plurality of projection difference matrixes of the difference matrix; wherein any target feature space is a feature space composed of at least one feature dimension with the importance from high to low in the original feature space, and the number of the at least one feature dimension is smaller than the total number of the feature dimensions in the original feature space; determining a target projection difference value matrix from the plurality of projection difference value matrixes through grid search, and compensating the pseudo quantization parameter matrix based on the target projection difference value matrix to obtain a compensation parameter matrix; and performing quantization processing on the compensation parameter matrix.

The data processing method is applied to the field of artificial intelligence and comprises the steps that first data are obtained, and the first data are obtained through a machine learning model according to first input data; performing non-uniform quantization processing on the first data to obtain first compressed data, and storing the first compressed data to a memory; and reading the first compressed data from the memory, and performing inverse quantization processing corresponding to the non-uniform quantization processing on the first compressed data to obtain second data, the second data and second input data being used for being input into the machine learning model, the second input data is data input into the machine learning model after the first input data. According to the method, non-uniform quantization is carried out on the data based on the non-uniform distribution characteristics of the data, the distribution characteristics of the data can be better met, the quantization result with smaller overall error or average error is obtained, and thus the processing precision of the model is improved.

The present application provides an enhanced layer encoding and decoding method and apparatus. The method includes: the encoder obtains a reconstructed block of the base layer of the image block to be encoded. The difference is calculated between the corresponding pixel points of the image block to be encoded and the reconstructed block of the base layer to obtain a residual block of the enhanced layer of the image block to be encoded. The transformation block partitioning method of the residual block of the enhanced layer is determined. The residual block of the enhanced layer is transformed according to the transformation block partitioning method. The decoder obtains the bitstream of the residual block of the enhanced layer of the image block to be decoded. Entropy decoding, inverse quantization, and inverse transformation are performed on the bitstream of the residual block of the enhanced layer to obtain a reconstructed residual block of the enhanced layer. The reconstructed block of the base layer of the image block to be decoded is obtained. The corresponding pixel points of the reconstructed residual block of the enhanced layer and the reconstructed block of the base layer are summed to obtain a reconstructed block of the enhanced layer. The present application can reduce the processing flow of the encoder and improve the encoding efficiency of the encoder. By adopting an adaptive TU partitioning method, the compression efficiency of the residual block can be more effectively improved.

The invention relates to a task-oriented semantic communication-oriented adaptive source channel coding system, which belongs to the field of wireless communication, and comprises a sending end for extracting a semantic feature map for evaluation from input data through a feature extractor initialized based on a pre-training large model, executing nested quantization and arithmetic coding based on a calculated importance score, and sending the semantic feature map to a task-oriented semantic communication-oriented adaptive source channel coding system; generating a scalable semantic bit stream with importance levels; the physical layer is used for carrying out reordering and grouping according to importance levels of bit streams, a channel encoder is combined with an interleaver to realize unequal error protection of semantic matching, and encoded bits are mapped to sign bits with different fault-tolerant capabilities in a constellation diagram through division modulation; and a receiving end: recovering the semantic feature map through arithmetic decoding and nested inverse quantization. According to the invention, on the premise of keeping compatibility with a digital communication protocol stack, through distortion-driven joint rate self-adaption, the transmission effectiveness for machine tasks and human vision is obviously improved under a limited bandwidth.

The embodiment of the invention discloses an image decoding method, an image coding method, electronic equipment and a readable storage medium. The decoding method comprises the following steps: during image decoding, performing first decoding sub-stage processing on a to-be-decoded image code stream to obtain pixel residual information; wherein the first decoding sub-stage comprises the steps of code stream acquisition and entropy decoding of an image to be decoded; caching the pixel residual error information to a shared macro block information buffer; when an image is decoded, acquiring residual information of pixels to be processed in the macro block information buffer by adopting an asynchronous independent clock; performing second decoding sub-stage processing on the to-be-processed pixel residual information to obtain image decoding information; wherein the second decoding sub-stage comprises inverse quantization, inverse discrete cosine transform and pixel code stream write-back. By decoupling the decoding process, asynchronous parallel processing of the decoding process can be realized, the image decoding efficiency is improved, and the memory utilization rate of equipment is improved.

This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for portrait video relighting on device using AI-generated HDR maps. A processor obtains an indication of a panoramic view, and generates, based on the indication, a first HDR image. The processor generates a composited relit image based on image data comprising an image frame and an adjusted light level associated with the first HDR image, and outputs another indication of the composited relit image. A processor obtains a first HDR image at a first bit depth, and generates, based on an inverse quantization function and the first HDR image, a second HDR image at a different, second bit depth. The processor determines an adjusted light level of the second HDR image based on the second HDR image and brightness of an HDR panoramic dataset, and outputs an indication of the adjusted light level.

The embodiment of the invention discloses a processor, a chip product, computer equipment and a data processing method. The processor comprises a block matrix calculation unit, a storage unit and a target register, wherein the storage unit is used for storing an input matrix to be processed and inverse quantization data corresponding to the input matrix; the block matrix calculation unit is used for reading the block matrix from the storage unit and reading the last target operation result from the target register; performing accumulation operation on the last target operation result and the block matrix to obtain a candidate operation result; and according to the inverse quantization parameter corresponding to the block matrix read from the storage unit, performing data precision adjustment on each element in the candidate operation result to obtain a current target operation result, and updating and storing the current target operation result in a target register.

FIELD: video signal encoding and decoding.SUBSTANCE: residual coefficient of the residual block is extracted. The quantization parameter for the residual block is calculated. Inverse quantization on the residual coefficient using the calculated quantization parameter is performed. A residual sample of the residual block is formed by performing an inverse transform on the inversely quantized residual coefficient. The encoded residual coefficient for the partial region in the residual block is not transmitted from the encoding device. The residual sample of the partial region in the residual block is set to the default value preset in the decoder, which is 0. The default value is set based on at least one of the size or shape of the residual block. A partial region is a region excluding at least one of the N columns on the left side of the residual block or M rows on the top side of the residual block.EFFECT: increased efficiency of video signal coding.9 cl, 16 dwg

The invention provides a task execution method which comprises the steps that according to a first query feature and a first key feature, a computing unit is used for executing a first multiplication task of a target attention task queue, a first multiplication result feature is obtained, the first key feature is obtained by converting a second key feature of a fixed point type into a floating point type, and the second key feature is obtained by converting a second key feature of a floating point type; the numerical precision of the first key feature is greater than that of the second key feature, and the numerical precision of the first query feature is less than that of the second query feature; according to the first multiplication result feature and the first value feature, executing a plurality of target tasks of the target attention task queue by using a computing unit to obtain attention features; the first query feature is obtained through the second query feature and an inverse quantization scaling parameter for the second key feature, so that the hardware resource overhead of executing the target attention task queue by the computing unit is smaller than a preset hardware resource overhead value. The invention further provides a task execution device and equipment, a medium and a program product.

A video coding system for a machine employs adaptive quantization of a frequency response based on a machine model of received data. The encoder receives a machine model of the machine-based system and generates a frequency importance map from the machine model. An adjustment matrix is then generated based on the frequency importance map and used to adjust the coefficients of the default quantization matrix. Video data is quantized using the adjusted quantization matrix and encoded in a bitstream for transmission to a decoder site. At the decoder site, the decoder may extract parameters of the adjusted quantization matrix from the bitstream, or calculate the adjusted quantization matrix using a machine model to inverse quantize the received data for machine consumption.

The present invention discloses a rate-adaptive image compression method and system, which includes: obtaining an input image, calculating its local information entropy to generate a spatially adaptive mask; obtaining target bit rate and actual bit rate information to generate a bit rate control signal; using a dynamic reversible neural network, dynamically selecting a calculation path using a mask, and performing a reversible quantization transformation based on the control signal to obtain a compressed bit stream and actual bit rate information for closed-loop feedback. The present invention reduces model storage requirements by constructing a symmetric reversible architecture with parameter sharing; dynamically adjusts the network calculation depth using entropy-aware gating to reduce the overall computational complexity; and adopts a composite control and PID optimization mechanism to achieve continuous and smooth bit rate control. It can effectively improve the deployment and application efficiency of compression systems in resource-constrained scenarios.

A displacement decoding unit (205) of a mesh decoding device (200) according to the present invention includes: a bypass arithmetic decoding unit (205A) configured to generate a coefficient level value by performing bypass arithmetic decoding on a displacement bit stream; an inverse quantization unit (205B) configured to generate a first transformed coefficient by performing inverse quantization on the coefficient level value; an adder (205D) configured to generate a second transformed coefficient by adding a prediction transformed coefficient and a prediction residual; an inter prediction unit (205F) configured to generate the prediction transformed coefficient by performing inter prediction by using the second transformed coefficient of a reference frame read from the frame buffer; and a second inverse transform unit (205G) configured to generate a decoded displacement by performing second inverse transform on the second transformed coefficient.

Disclosed are an image encoding / decoding method and a computer-readable recording medium. The method for decoding an image includes: receiving a bitstream in which an image is encoded; acquiring a plurality of lower blocks from the upper block in the current image by using block division based on a tree structure; generating a predicted image of the current image by referring to syntax information acquired from the bitstream; and acquiring a decoded image by combining the generated prediction image with a residual image acquired by inverse-quantizing and inverse-transforming the quantized transform coefficient from the bitstream.

The application provides a method for detecting synchronous JPEG recompression of BMP format concealed images, and a method for effectively estimating a JPEG quantization table is provided; by using the particularity of JPEG 100 quality factor compression, the minimum error caused by JPEG compression when the quality factor is 100 is extracted to construct an expected-minimum error feature; by using the convergence characteristics of inverse quantization JPEG coefficients, a first-order relative error feature is proposed, and finally synchronous JPEG recompression images saved in BMP format are effectively detected, and synchronous JPEG recompression at any quality factor can also be detected. The application can effectively distinguish single compressed images from recompressed images, and has higher accuracy compared with corresponding traditional JPEG recompression detection methods.

Disclosed are an image encoding / decoding method and a computer-readable recording medium. The image decoding method includes: dividing a first block into a plurality of second blocks; generating a prediction block of the second block based on intra prediction; generating a residual block of the second block by performing inverse quantization on residual information obtained from the bitstream; and adding the prediction block and the residual block to reconstruct a second block, where generating the prediction block of the second block comprises determining a mode candidate group of the second block from a plurality of mode candidate groups, where the mode candidate group is a set of intra prediction modes that can be used for intra prediction of the second block, and where the mode candidate group is a set of intra prediction modes that can be used for intra prediction of the second block. The plurality of mode candidate groups includes an MPM candidate group consisting of A intra prediction modes, a first non-MPM candidate group consisting of B intra prediction modes, and a second non-MPM candidate group consisting of C intra prediction modes.