35results about How to "Guaranteed computing power" patented technology

The invention discloses a method for enhancing sharpness of color image with color constancy. The method includes the following steps: based on the red, green and blue three wave bands of an image, calculating a brightness image; setting a neighborhood radius, calculating mean value and standard difference of the brightness image in each pixel neighborhood, obtaining an neighborhood mean value image and a neighborhood standard difference image; based on the neighborhood mean value image and the neighborhood standard difference image, conducting adaptive calculation on weight of each pixel point; based on the neighborhood mean value image and the weights, recalculating a new brightness image; in accordance with the theory of color constancy, based on the new brightness image and an original brightness image, conducting same ratio enhancement on the three wave bands of the original image, obtaining the image with enhanced sharpness with color constancy. According to the invention, the method can greatly increase image sharpness, reduce color distortion as much as possible, maintain color constancy, and effectively increase visual effects of the image.

The invention discloses a high-performance industrial robot controller which comprises a processor board, a machine visual unit, a demonstrator, an external IO unit, a grabber unit, an external sensorand a motor driver. The processor board comprises an ARM processor unit, an FPGA unit, a power module, an Ethernet interface A, an Ethernet interface B, an Ethernet interface C, an Ethernet interfaceD, an IO interface and a CAN interface. The robot controller is small in size, cost is reduced, the computation capacity of the controller can be ensured, and the controller has high expandability and safety; meanwhile, the robot controller is convenient to expand, meanwhile has three-dimensional machine vision and can obtain information (X, Y, Z) of a target, the target is more precisely grabbed, and the robot controller can adapt to various complicated application scenes; and a robot movement control algorithm is evenly allocated in an ARM and an FPGA, and the computation capacity of the robot controller is effectively improved.

The invention relates to a neural network weight discretization method and system. The method comprises the following steps: obtaining a weight value range and a number of discrete weight states; acquiring a previous time step weight state and a current time step weight increment; obtaining a state transition direction by using a direction function according to the weight increment of the currenttime step; obtaining a current time step weight state according to the previous time step weight state, the current time step weight increment, the state transition direction, the weight value range,and the number of discrete weight states. The invention ensures that the weight value is always constrained in the same discrete state space without storing additional virtual continuous state implicit weights, and greatly reduces the consumption of storage space and the computational complexity under the premise of ensuring the computational performance of the neural network.

A method for generating an evaluation of a user's activities on a virtual document, includes:(a) providing a server system, having a server memory and server processing unit;(b) providing an electronic device, having a device memory, device processing unit, elements for connecting with the server system, elements for interacting with and allowing a user to create and modify a virtual document;whereinthe device processing unit: (s1) receives information relating the creation or opening of a virtual document; (s2) encrypts the virtual document at subsequent time intervals, to create a plurality of encrypted copies of the virtual documents, each encrypted copy associated with a different time interval; (s3) sends the encrypted copies to the server memory; (s4) interrupts steps (s2) and (s3) when the virtual document is closed;the server processing unit (s4) compares the encrypted copies; and (s5) generates a report containing the evaluation of the user's activities.

The invention discloses a consensus mechanism and working method of a double-layer fragmented high-efficiency block chain. The consensus mechanism is based on a double-layer gossip topology network, including: full nodes, local full nodes, light nodes and micro nodes, full Nodes are responsible for the maintenance of node topology and sharding. They are elected and updated through the full node maintenance mechanism, and local full nodes are elected and updated through the local full node maintenance mechanism. They are responsible for transaction verification, transaction consensus, transaction storage, and ledger synchronization. The invention also proposes How this consensus mechanism works. A credible and incentivized node joining and updating mechanism proposed by the present invention ensures the stability, bandwidth capacity, and computing power of full nodes and partial full nodes, and reduces the impact on transaction confirmation speed. The consensus mechanism proposed by the present invention passes The "intra-chip autonomy, inter-chip collaboration" approach forms a divide-and-conquer distributed ledger system to ensure decentralization, scalability, and security.

The invention relates to a water environment analysis method based on a geographic information system and a Delft3D-FLOW calculation engine. The water environment analysis method comprises the steps that a software system framework is built through a GIS platform; a Delft3D mesh file format is analyzed; a configuration file MDF file format of the Delft3D-FLOW and meanings of multiple parameters in the configuration file MDF file format are analyzed, and a human-computer interaction configuration interface is developed for configuring the multiple parameters under the GIS platform; a model is built, configuration tasks of a plurality of environmental elements are completed through GIS operation; a configuration result is output as a file format which can be identified by the mathematical calculation engine, and the calculation engine is called to conduct calculation; a calculation result file format is analyzed, a file is read under the GIS platform and processed into a raster image with space coordinates through the image processing technology, and the raster image is loaded into the GIS platform for display. The water environment analysis method combines the mathematical model with spatial and geographic information, thereby improving analysis accuracy. The invention further provides a water environment analysis system based on the geographic information system and the Delft3D-FLOW calculation engine.

The invention discloses a method for enhancing sharpness of color image with color constancy. The method includes the following steps: based on the red, green and blue three wave bands of an image, calculating a brightness image; setting a neighborhood radius, calculating mean value and standard difference of the brightness image in each pixel neighborhood, obtaining an neighborhood mean value image and a neighborhood standard difference image; based on the neighborhood mean value image and the neighborhood standard difference image, conducting adaptive calculation on weight of each pixel point; based on the neighborhood mean value image and the weights, recalculating a new brightness image; in accordance with the theory of color constancy, based on the new brightness image and an original brightness image, conducting same ratio enhancement on the three wave bands of the original image, obtaining the image with enhanced sharpness with color constancy. According to the invention, the method can greatly increase image sharpness, reduce color distortion as much as possible, maintain color constancy, and effectively increase visual effects of the image.

The invention is applicable to the technical field of computers, and provides a coprocessor, and a method and a system for matrix operation acceleration. The coprocessor comprises a controller, a register bank, a multiplier-adder MAC array, and a memory. The controller parses a vector expansion instruction, and calls and sends data to be calculated to the register bank according to a parsing result. The register bank transmits the data to be calculated to the MAC array and transmits an operation result to the memory, the operation result being obtained by matrix operation of the MAC array on the data to be calculated, and the data to be calculated and / or the operation result are stored in the memory. In the process, the MAC array performs matrix operation according to the vector expansioninstruction, and the vector expansion instruction is generated by a main processor according to a preset function, ensuring computational power of a general microprocessor. The register bank transmitsand stores all kinds of data, and a data storage channel is independent of a receiving channel of the vector expansion instruction, improving data throughput of a general-purpose microprocessor in anoperation process.

Embodiments of the present invention provide a power supply voltage control method and device for a digital currency mining machine, and a digital currency mining machine. The method includes: determining the computing power ratio of the digital currency mining machine based on the actual computing power and theoretical computing power of the digital currency mining machine; generating a power control instruction based on the comparison result of the computing power ratio and a predetermined threshold value; The above power control command controls the output voltage of the power supply of the mining machine. The embodiment of the present invention controls the output voltage of the power supply according to the calculation power ratio, and can achieve a good compromise between the power consumption loss and the calculation power of the mining machine.

The invention discloses a method for controlling energy consumption of a cluster system based on changing a control mode, which carries out system level management and control under the operating condition of a computation task on a computation node in the cluster system through a control node and belongs to the field of computer cluster systems. In the method for controlling the energy consumption, the control node respectively chooses fixed, manual or semi-automatic control modes for the change of a computation task amount and the frequency of the change and controls the energy consumption through controlling the state of a computation node and the computation node enters different sleep states according to an idle rule so as to save the energy consumption of a processor. In the invention, the energy consumption of the cluster system is greatly reduced aiming at parallel computation of the cluster system under the premise of not greatly degrading computation performance and the balance between the performance and the energy consumption is obtained.

The invention discloses a flexibly configurable neural network computing unit, a computing array and a construction method thereof. The neural network computing unit includes: a configurable storage module, a configurable control module, and a multiply-add computing module capable of time-division multiplexing; a configurable storage module The modules include: feature map data buffer, step size data buffer and weight data buffer; the configurable control module includes: counter module and state machine module; the multiplication and addition calculation module includes: multiplier and accumulator. The invention can support any type of convolution calculation, and supports parallel calculation of multi-size convolution kernels, fully explores the flexibility and data reusability of convolutional neural network calculation units, greatly reduces system power consumption caused by data migration, and improves The computational efficiency of the system.

The invention discloses a CNN processing method and device, which are used for realizing the module operation in the CNN model on the ASIC, and reducing the operation cost while ensuring the calculation performance of the CNN. An embodiment of the present invention provides a CNN processing method, including: obtaining the intensive type of the first module in the CNN model; if the intensive type of the first module is computationally intensive, deploying the first module to a dedicated integration on the circuit ASIC, and obtain the multiple computing resources of the ASIC occupied by the first module; merge the same computing resources among the multiple computing resources of the ASIC occupied by the first module, and obtain the deployment The first module on the ASIC after completing the combination of computing resources; running the first module deployed on the ASIC after completing the combining of computing resources.