15results about How to "Reduce precision loss" patented technology

The application provides a hardware perception-based model quantization method, system, medium, product and terminal, a hybrid execution mechanism is constructed between a high-level software framework and a bottom layer hardware behavior model, only core calculation operators in a quantization calculation graph of an initial quantization model which need to be executed on target hardware are handed over to a hardware behavior model for bit precision simulation, real calculation characteristics of the target hardware are simulated in a quantization process, and other auxiliary, non-computation-intensive operators are reserved in the high-level software framework for execution, so that the simulation verification efficiency is improved, the simulation precision and the execution efficiency are considered, and the goal that the quantized model runs more efficiently and has lower precision loss on the target hardware is achieved.

This invention provides an approximate 4-bit lookup table multiplier, relating to the field of integrated circuits, comprising: a conversion module, a first-stage multiplication module, and a second-stage multiplication module. During the multiplication process, for two compressed partial products with the same input, a 6-input, 2-output lookup table (LUT6_2) is used for simultaneous calculation. For three compressed partial products with the same input, the precision loss of each compressed partial product is calculated, and a 6-input, 2-output lookup table (LUT6_2) is used to simultaneously calculate the two compressed partial products with the smallest precision loss. The compressed partial product with the largest precision loss is calculated separately using a 6-input lookup table (LUT6). For compressed partial products with an input number exceeding the lookup table's input limit, and for unprocessed partial products, a partial carry-truncation method is used to calculate the product result. This invention can improve multiplier performance while reducing multiplier precision loss.

The invention provides a key value caching method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a plurality of text segments corresponding to a current text and a segment attention score corresponding to each text segment; based on the fragment attention score, screening at least one target text fragment from the plurality of text fragments; performing attention analysis on the plurality of candidate lexical elements in the at least one target text fragment to obtain first attention scores corresponding to the plurality of candidate lexical elements; based on the first attention score, screening out at least one target lexical element from the plurality of candidate lexical elements; and updating the original cache based on the key value cache corresponding to the at least one target lexical element. By utilizing the embodiment of the invention, the recall of the key value cache of the target lexical element can be realized, the information loss caused by relatively far lexical element information is avoided, the reasoning of relatively long context can be supported, and the problem of precision loss caused by information loss in a rarefaction process is alleviated.

The utility model relates to a kind of mobile press pin machine devices, including product placement unit, cylindrical pin positioning guide unit and mobile press pin machine unit;Wherein product placement unit includes the mobile trolley of placing camshaft product;Cylindrical pin positioning guide unit includes cylindrical pin positioning guide sleeve, locking screw and cylindrical positioning bolt;Mobile press pin machine unit includes product positioning seat, press pin head, gas-liquid pressure cylinder front seat, gas-liquid pressure cylinder, gas-liquid pressure cylinder rear seat, cylindrical guide rail, flange linear ball bearing, gas-liquid pressure cylinder bottom plate, round flange seat, lifting mechanism bottom plate frame, directional wheel, universal wheel, cylinder, bevel gear elevator, hand wheel, handle, pneumatic element bottom plate, gas source two joint parts, solenoid valve and controller.The utility model can improve the precision and efficiency of camshaft workpiece press-fit positioning pin, and the utility model can reduce workpiece collision risk and personnel safety hazard.

The utility model discloses a photovoltaic power station support rotating part of automatic lubrication function belongs to photovoltaic power station support technical field, it includes base, the base upper end surface center place is equipped with stand, the stand upper end surface center place is equipped with rotating structure, and the rotating structure includes rotating frame, and the both sides wall center upper of rotating frame is equipped with bearing evenly, and the rotating frame inside center upper is equipped with rotating rod, in addition, the utility model discloses, realize through the linear motion of hydraulic telescopic link efficient stably conversion is driven support main body rotation's circular motion to this adjustment photovoltaic board angle better receive sunlight, has reduced equipment cost, has reduced the precision loss of the intermediate transmission link, just control the telescopic amount of hydraulic telescopic link, can accurate control rotating frame and support main body's rotation angle, guarantee photovoltaic board can continuously track sunlight, effectively improve power generation efficiency.

This invention discloses a convolutional neural network pruning method and apparatus based on feature similarity and feature compensation. The method includes: adjusting the size of the input images in the dataset to a fixed size, standardizing the pixel values ​​of the images, and increasing the training data using image enhancement techniques; initializing the network structure and setting model parameters, and training the model using the training data; for the trained model, obtaining the similarity between convolutional kernels, performing cluster analysis based on the similarity, grouping each layer of convolutional kernels into similar groups, selecting the convolutional kernels to be retained in each similar group, and generating a new network structure; copying the parameters of the retained convolutional kernels into the new network structure, and compensating the weight parameters of the pruned convolutional kernels in each similar group into the retained convolutional kernels through parameter superposition; performing model accuracy recovery training using the original dataset, and saving the model parameters and network structure. This pruning method can maintain model accuracy.

This invention relates to a precision positioning device for roof outer panels with detection and transfer functions, comprising a transfer frame, a positioning frame, a front traction device, two front limiting devices, two auxiliary positioning devices, two front flipping Z-axis protection devices, two rear flipping Z-axis protection devices, two rear limiting and positioning devices, and a rear traction device. This precision positioning device for roof outer panels meets the needs of various functional devices during the production, transportation, and assembly processes of the roof, reducing the number of transfers, improving transfer efficiency, and reducing accuracy loss and deformation risks during the process. The invention features a highly modular structure, allowing for flexible production. It can be used for switching between multiple vehicle models to meet the requirements of the above processes, reducing accuracy loss and sheet metal deformation risks caused by multiple roof transfers. It also provides a direct evaluation of whether the roof surface is qualified and whether it can be normally put on the production line and installed on the vehicle. Roofs for different vehicle models can be flexibly used by switching the overall positioning frame or the support positioning blocks.

The application provides a building missing structure point cloud repairing method and device, the method comprises the following steps: obtaining original point cloud data of a target building; determining missing structure features of the original point cloud data, and adjusting the posture of the target building based on the missing structure features to obtain target point cloud data; constructing a cloth structure corresponding to the target building, determining corresponding cloth node rules based on the cloth structure; performing cloth subsidence simulation on the cloth structure based on the target point cloud data and the cloth node rules to obtain a cloth simulation model; determining structure constraints corresponding to the cloth structure, determining recessed areas in the cloth simulation model that need to be repaired based on the structure constraints, and repairing the recessed areas to obtain regional repair results; and fitting the regional repair results to obtain point cloud repair results of the target building. The application can guarantee strong generalization performance and robust performance of point cloud repair.

The invention discloses a color temperature adjusting method and device for double-primary-color mixed light, equipment and a medium, and relates to the technical field of illumination, and the method comprises the steps: obtaining a first chromaticity coordinate and a second chromaticity coordinate of a first primary-color light source and a second primary-color light source in a specified chromaticity space; obtaining a target chromaticity coordinate of a target color point corresponding to the target color temperature in a specified chromaticity space; vertically projecting the target chromaticity coordinate to a straight line determined by the first chromaticity coordinate and the second chromaticity coordinate to obtain a projection point; determining a first color mixing proportion parameter according to the position of the projection point on the straight line; a second color mixing proportion parameter is obtained based on the projective transformation relation between the color spaces and the edge consistency of projective changes; and determining the duty ratio of the first primary color light source and the second primary color light source according to the second color mixing proportion parameter, the target brightness value and the maximum light-emitting capability of the first and second primary color light sources. The method has good performance on CCT and DUV constraints, and the algorithm calculation complexity is low.

The invention discloses a BSD algorithm end-side deployment method based on a YOLO model and capable of running stably. The method comprises the following steps: S1, optimizing a model structure; according to the method, through model structure optimization, three-stage training and export of full-link collaborative design of quantization and end-side deployment, a lightweight and high-precision detection framework BSDYOLO is constructed; mobileNet structured pruning, BiFPN feature fusion and decoupling detection head simplified calculation are adopted, and distillation training, multi-illumination robustness training and quantitative fine tuning are combined to guarantee precision; through a standardized preprocessing process and CPU / NPU collaborative post-processing, stable deployment and real-time reasoning of the model on an end side are realized, the method is suitable for a truck electronic rearview mirror BSD blind area monitoring scene, nine types of targets can be rapidly detected at an edge end with limited computing power, engineering indexes such as detection frequency, response time and missing report rate are met, and a deployment link is stable and reproducible.

The invention provides a main shaft mechanism and a machine tool with the main shaft mechanism, the main shaft mechanism comprises a shaft body assembly, the shaft body assembly comprises a main shaft and a shell, and the shell is internally provided with a cooling channel for circulating cooling liquid; the supporting bearing is arranged on the main shaft in a sleeving mode, a circulation channel is formed in the supporting bearing, and the circulation channel communicates with the cooling channel so that cooling liquid can flow into the circulation channel to cool the supporting bearing; and the sealing component is arranged on the main shaft in a sleeving mode and located on the side of the supporting bearing, at least part of the sealing component is movably arranged in the axial direction of the main shaft, and the problem that in the prior art, the cooling efficiency of the main shaft is low is solved.

The invention provides a video content intelligent analysis method based on an edge computing platform, and the method comprises the steps: collecting a video stream through an image collection interface of the edge computing platform, and carrying out the preprocessing of a video frame at a CPU end, and obtaining standardized image data; the method comprises the following steps: converting a pre-trained neural network model into a special format model adaptive to an NPU (Network Processing Unit), and adopting a hierarchical quantization strategy in the conversion process: quantizing at least one network layer responsible for basic feature extraction in the model by adopting first numerical value precision, quantizing other network layers responsible for classification and regression in the model by adopting second numerical value precision lower than the first numerical value precision; dynamically scheduling the number of processing cores in an activated state in the NPU based on a processing load determined by analyzing the current video frame content represented by the standardized image data, and utilizing the processing cores in the activated state to load a special format model to infer the standardized image data; and post-processing the reasoning output result of the NPU to generate a structured analysis result.

An ALU, processor, chip, device, and texel index calculation method are disclosed, belonging to the field of chip technology. The ALU includes: a multiplier for calculating the product of the mantissa of the input texture coordinates in floating-point format and the texture size, obtaining a first product; a first conversion unit for shifting the input offset left by N bits, obtaining a shifted input offset; an adder for calculating the sum of the first product and the shifted input offset, obtaining a first calculation result; a second conversion unit for shifting the first calculation result right by M bits, obtaining a shifted first calculation result; and a second calculation result based on the shifted first calculation result and a rounding mode, the second calculation result being used to determine the texel index corresponding to the input texture coordinates. This method only requires one unified right shift operation to obtain the second calculation result in a preset floating-point format, reducing the number of right shift operations and thus making the determined texel index more accurate.

The invention discloses a strip mine rasterized road network center line extraction method fusing track time sequence characteristics. The method comprises the following steps: reading and preprocessing track data; extracting effective track segments; performing trajectory interpolation completion driven by a time sequence; track rasterization and matrix construction are carried out; the grid density is enhanced; density refinement and central line primary extraction; road network topology construction and redundancy elimination; carrying out coordinate back calculation and precision enhancement; and outputting the road network. According to the method, the road network model with higher precision and high adaptation can be quickly provided through automatic calculation of fewer parameters under the condition that the method is universal as far as possible, and the requirement of quick modification is met.

The application belongs to the technical field of underwater robot visual perception, edge computing and target detection, and discloses an underwater target automatic identification method and system based on an improved YOLO algorithm, wherein the post-processing speed is greatly improved, an INT8 domain pre-confidence screening mechanism filters more than 90% of background candidate boxes, the time consumption ratio of post-processing is reduced from more than 30% of the traditional to less than 10%, and the overall operation speed of the application is significantly improved. The application has good real-time performance, a multi-thread parallel inference pipeline architecture fully utilizes the heterogeneous computing power of RK3588S, hides single-frame inference delay, realizes stable real-time detection frame rate of 15-25 FPS under 1280*720 resolution, and can timely capture fast-moving underwater targets. The application has high integration, realizes deep integration of the identification application and technologies such as mechanical grabbing and autonomous return, forms a full-autonomous operation closed loop of identification-positioning-grabbing, and the autonomous decision rate is more than 90%, thereby greatly reducing the dependence on manual operation.