[go: up one dir, main page]

WO2021143686A1 - Procédés et appareils de point fixe de réseau neuronal, dispositif électronique, et support de stockage lisible - Google Patents

Procédés et appareils de point fixe de réseau neuronal, dispositif électronique, et support de stockage lisible Download PDF

Info

Publication number
WO2021143686A1
WO2021143686A1 PCT/CN2021/071311 CN2021071311W WO2021143686A1 WO 2021143686 A1 WO2021143686 A1 WO 2021143686A1 CN 2021071311 W CN2021071311 W CN 2021071311W WO 2021143686 A1 WO2021143686 A1 WO 2021143686A1
Authority
WO
WIPO (PCT)
Prior art keywords
fixed
point
unit
neural network
output
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2021/071311
Other languages
English (en)
Chinese (zh)
Inventor
浦世亮
彭博
李哲暘
谭文明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Hikvision Digital Technology Co Ltd
Original Assignee
Hangzhou Hikvision Digital Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou Hikvision Digital Technology Co Ltd filed Critical Hangzhou Hikvision Digital Technology Co Ltd
Publication of WO2021143686A1 publication Critical patent/WO2021143686A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0495—Quantised networks; Sparse networks; Compressed networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Definitions

  • This application relates to methods, devices, electronic equipment, and readable storage media for neural network targeting.
  • Neural network fixed-point (also known as quantization) is a commonly used model acceleration algorithm, which quantizes the weight of the model and the output eigenvalue (the weight and the output eigenvalue are float type values) into fixed bits Numbers, such as 8bit, 16bit or very low 1, 2bit, can well solve the problems of complex multiplication and accumulation calculations and huge bandwidth caused by floating-point data on the hardware. The lower the number of quantized bits of the model, the more obvious the acceleration of the model on hardware.
  • a certain number of sample pictures can be input to the original model at one time, the forward calculation of the model records the data distribution of the eigenvalues output by each layer, and then the eigenvalues output by each layer are calculated separately.
  • the fixed-point super-parameters do not consider the impact of the fixed-pointing of the pre-layer on the post-layer, and the performance of the fixed-point neural network is low.
  • this application provides a method, device, electronic device, and readable storage medium for neural network targeting.
  • a neural network fixed-pointing method including: for the pending unit of the neural network, based on the situation that the fixed-pointing unit of the neural network maintains the fixed-pointing state, the pending-pointing method is provided The data distribution of the characteristic value output by the unit determines the fixed-point hyperparameter of the characteristic value output by the to-be-fixed unit; based on the fixed-point super-parameter, the characteristic value output by the to-be-fixed unit is fixed.
  • a neural network fixed-pointing method including: for a neural network to-be-fixed unit, based on the situation that the fixed-pointing unit of the neural network maintains a fixed-point state, the pending point Optimizing the weights of the unit to be fixed with the characteristic value output by the quantization unit and the eigenvalue output by the unit to be fixed in the original floating-point state; and fix the optimized unit to be fixed.
  • a neural network fixed-point method including: analyzing the topological structure of the input floating-point model to generate a neural network data flow graph; based on the sample picture information in the configuration file, Generate the data layer of the neural network; split and merge the topology of the neural network based on the optimization strategy of the platform to be deployed to obtain the preprocessed floating-point model; perform the preprocessing based on the above method
  • the floating-point model is fixed-point.
  • a neural network fixed-pointing device including: a determining module, used for a pending unit of the neural network, based on the situation that the fixed-pointed unit of the neural network maintains a fixed-pointing state Download the data distribution of the characteristic value output by the to-be-fixed unit to determine the fixed-pointing hyperparameter of the characteristic value output by the to-be-fixed unit; the fixed-pointing module is used for the output of the to-be-fixed unit based on the fixed-pointing hyperparameter The characteristic value is fixed-point.
  • a neural network fixed-pointing device including: an optimization module, which is used to maintain a fixed-pointing state for the fixed-pointing unit of the neural network based on the fixed-pointing unit of the neural network
  • the eigenvalue output by the to-be-fixed unit and the eigenvalue output by the to-be-fixed unit in the original floating-point state optimize the weight of the to-be-fixed unit
  • the fixed-point module is used to optimize the The to-be-fixed unit is fixed-pointed.
  • a neural network fixed-pointing device including: an analysis module for analyzing the topological structure of an input floating-point model to generate a neural network data flow graph; a generation module, using Based on the sample picture information in the configuration file, the data layer of the neural network is generated; the processing module is used to split and merge the topology of the neural network based on the optimization strategy of the platform to be deployed to obtain preprocessing The latter floating-point model; a fixed-point module for fixed-pointing the pre-processed floating-point model based on the above method.
  • an electronic device including a processor and a machine-readable storage medium, the machine-readable storage medium stores machine-executable instructions that can be executed by the processor, and The processor is used to execute machine-executable instructions to implement the above-mentioned neural network fixed-point method.
  • a machine-readable storage medium that stores machine-executable instructions in the machine-readable storage medium, and when the machine-executable instructions are executed by a processor, the above-mentioned neural network fixed point is realized ⁇ method.
  • a computer program is provided, the computer program is stored in a machine-readable storage medium, and when the computer program is executed by a processor, the above neural network fixed-pointing method is realized.
  • the technical solution provided in this application can at least bring about the following beneficial effects:
  • For the to-be-fixed unit of the neural network the data distribution of the characteristic value output by the to-be-fixed unit based on the situation that the fixed-point unit of the neural network maintains the fixed-point state , Determine the fixed-point hyperparameter of the eigenvalue output by the to-be-fixed unit, and based on the fixed-point super-parameter, fix the eigenvalue output by the to-be-fixed unit, and perform unit-by-unit fixed-pointing on the neural network.
  • the to-be-fixed unit of the neural network keeps the fixed-point unit in a fixed-point state to obtain a more realistic data distribution of the output characteristic value, thereby improving the performance of the neural network's fixed-pointing.
  • Fig. 1 is a schematic flowchart of a neural network fixed point method shown in an exemplary embodiment of the present application.
  • Fig. 2 is a schematic flowchart of another neural network fixed-pointing method shown in an exemplary embodiment of the present application.
  • Fig. 3 is a schematic flowchart of a final fixed-pointing hyperparameter for determining the characteristic value output by the to-be-fixed unit from the first fixed-pointing superparameter candidate value range according to an exemplary embodiment of the present application.
  • Fig. 4 is a schematic flowchart of another neural network fixed point method according to an exemplary embodiment of the present application.
  • FIG. 5 is a schematic flowchart of a final fixed-pointing hyperparameter for determining the weight of the to-be-fixed unit from the second fixed-pointing super-parameter candidate value range according to an exemplary embodiment of the present application.
  • Fig. 6 is a schematic flowchart of a neural network fixed point method according to an exemplary embodiment of the present application.
  • Fig. 7 is a schematic flowchart of a neural network fixed-pointing method shown in an exemplary embodiment of the present application.
  • Fig. 8 is a schematic diagram of an automated neural network pointing system shown in an exemplary embodiment of the present application.
  • Fig. 9 is a schematic diagram of a functional flow chart of a fixed-point evaluation and tuning module shown in an exemplary embodiment of the present application.
  • Fig. 10 is a schematic diagram showing an implementation of an optimization strategy for minimizing local errors according to an exemplary embodiment of the present application.
  • Fig. 11 is a schematic structural diagram of a neural network pointing device according to an exemplary embodiment of the present application.
  • Fig. 12 is a schematic structural diagram of a neural network pointing device according to an exemplary embodiment of the present application.
  • Fig. 13 is a schematic structural diagram of a neural network pointing device according to an exemplary embodiment of the present application.
  • Fig. 14 is a schematic diagram showing the hardware structure of an electronic device according to an exemplary embodiment of the present application.
  • FIG. 1 is a schematic flowchart of a neural network fixed-pointing method provided by an embodiment of this application.
  • the neural network fixed-pointing method may include the following steps S100 and S110.
  • Step S100 For the to-be-fixed unit of the neural network, based on the data distribution of the characteristic value output by the to-be-fixed unit under the condition that the fixed-point unit of the neural network maintains the fixed-point state, determine the characteristic value output by the to-be-fixed unit The fixed-point super-parameters.
  • the fixed-point of the feature value output by the to-be-fixed unit is determined Super parameters.
  • the unit to be fixed when the unit to be fixed is the first unit to be fixed in the neural network, for example, the first unit of the neural network, the neural network does not include the fixed unit, in this case, it can be based on the
  • the data distribution of the characteristic value output by the to-be-fixed unit determines the fixed-point hyperparameter of the characteristic value output by the to-be-fixed unit, and fixes the characteristic value output by the to-be-fixed unit based on the fixed super parameter.
  • unit 1 and unit 2 can be fixed in sequence.
  • the unit 1 is fixed (that is, the unit to be fixed is unit 1)
  • a certain number of samples can be input to the neural network to calculate the data distribution of the eigenvalues output by the unit 1, and based on the eigenvalues output by the unit 1.
  • the data distribution is to determine the fixed-point super-parameters of the eigenvalues output by the unit 1, and to fix the eigenvalues output by the unit 1 based on the determined fixed-point super-parameters.
  • unit 1 After the fixed-pointing of unit 1 is completed, when unit 2 is fixed-pointed (that is, the unit to be fixed is unit 2), unit 1 can be kept in a fixed-point state, a certain number of samples are input to the neural network, and unit 2 is counted. Based on the data distribution of the output feature value, and based on the data distribution of the feature value output by the unit 2, the fixed-point hyperparameter of the feature value output by the unit 2 is determined.
  • the to-be-fixed unit of the neural network when the to-be-fixed unit of the neural network is fixed, if there are multiple fixed-point units before the to-be-fixed unit, it can also be used in some of the multiple fixed-point units.
  • the fixed-point unit maintains the fixed-point state, the pending unit is fixed-pointed, and its specific implementation is not repeated here.
  • step S110 the characteristic value output by the unit to be fixed is fixed based on the fixed super parameter.
  • the characteristic value output by the to-be-fixed unit can be fixed based on the fixed-pointing super-parameter. change.
  • the neural network is fixed unit by unit, and for the pending unit of the neural network, the fixed unit is kept in a fixed state to obtain a more realistic output feature value. Data distribution, thus, improve the performance of neural network fixed-point.
  • step S100 after determining the fixed-pointing hyperparameter of the feature value output by the to-be-fixed unit, the neural network fixed-pointing method provided in the embodiment of the present application may further include The following steps: step S101, determine a first fixed-point super-parameter candidate value range based on the fixed-point super-parameter of the characteristic value output by the to-be-fixed unit; step S102, from the first fixed-point super-parameter candidate value range Determine the final fixed-point hyperparameter of the eigenvalue output by the to-be-fixed unit.
  • step S110 the characteristic value output by the to-be-fixed unit is fixed based on the to-be-fixed super-parameter, including: step S111, the final fixed-pointing super-parameter based on the characteristic value output by the to-be-fixed unit is The eigenvalues output by the pointization unit are fixed-pointed.
  • the determined fixed-point super-parameter may also be optimized to obtain the actual use of the to-be-determined super-parameter.
  • the eigenvalues output by the initiation unit are used for fixed-point fixed-point super-parameters (referred to as final fixed-point super-parameters in this article) to further improve the performance of the neural network fixed-point.
  • the range for searching for the final fixed-pointing hyperparameters (herein referred to as the first fixed-pointing hyperparameter candidate value) may be determined. Range), and determine the final fixed-point super-parameter of the characteristic value output by the to-be-fixed unit from the first fixed-point super-parameter candidate value range.
  • the first fixed-point hyperparameter candidate value range may be a numerical interval including the fixed-point hyperparameter determined in step S100.
  • the lower limit and upper limit of the candidate value range of the first fixed-point super-parameter can be obtained by subtracting and adding a specific value greater than 0 on the basis of the fixed-point super-parameter determined in step S100, thereby determining the first fixed-point super-parameter.
  • the range of hyperparameter candidate values is fixed.
  • the fixed-point super-parameter determined in step S100 may be used as the lower limit of the first fixed-point super-parameter candidate value range, and a specific value greater than 0 can be added to the lower limit to obtain the first fixed-point super-parameter.
  • the upper limit of the parameter candidate value range is determined, thereby determining the first fixed-point hyperparameter candidate value range.
  • step S102 determining the final fixed-pointing hyper-parameter of the characteristic value output by the to-be-fixed unit from the first fixed-pointing super-parameter candidate value range can be implemented by the following steps: Step S1021, respectively, determine the output error of the neural network corresponding to each candidate value in the first fixed-point hyperparameter candidate value range; step S1022, determine the candidate value with the smallest output error of the corresponding neural network as the pending point The final fixed-point hyperparameter of the eigenvalue output by the unit.
  • the fixed-point hyperparameter of the eigenvalue output by the fixed-point unit can be optimized, and the fixed-point hyperparameter that minimizes the output error of the neural network can be selected as the eigenvalue output by the to-be-fixed unit Finally, the super-parameters are fixed.
  • the output error of the neural network corresponding to each candidate value in the first fixed-point hyperparameter candidate value range can be determined separately, and the output error of the corresponding neural network can be minimized
  • the candidate value of is determined as the final fixed-pointing hyperparameter of the feature value output by the to-be-fixed-pointing unit.
  • determining the candidate value with the smallest output error of the corresponding neural network as the final fixed-pointing hyperparameter of the characteristic value output by the to-be-fixed unit is only the determination of the fixed-pointing hyperparameter in the embodiment of this application. It is an implementation manner and is not a limitation of the protection scope of the present application. In the embodiments of the present application, the final fixed-pointing hyperparameter of the characteristic value output by the to-be-fixed unit can also be determined in other ways.
  • the average value of the candidate values whose output error of the corresponding neural network is less than the preset threshold can be determined as the final fixed-pointing hyperparameter of the feature value output by the to-be-fixed unit.
  • the candidate values can be sorted according to the output error of the corresponding neural network from small to large, and the average value of the previously preset number of candidate values after sorting can be determined as the final feature value output by the unit to be fixed. Fixed-point super-parameters.
  • respectively determining the output error of the neural network corresponding to each candidate value in the first fixed-point hyperparameter candidate value range may include: for any candidate value, based on the first type feature value and The second type feature value determines the output error of the neural network corresponding to the candidate value.
  • the fixed-point processing of the neural network may bring errors to the output accuracy of the neural network, and the output of the fixed-point neural network is different from the original floating-point state.
  • the smaller the output error of the neural network the higher the output accuracy of the fixed-point neural network. Therefore, the fixed-point can be fixed based on the error between the output of the fixed-point neural network and the output of the neural network in the original floating-point state Super parameters are optimized.
  • the characteristic value output by each unit of the neural network when using the candidate value to fix the characteristic value output by the fixed-point unit (herein (Referred to as the first type feature value), and, in the original floating point state, the feature value output by each unit of the neural network (herein referred to as the second type feature value), determine the output error of the neural network corresponding to the candidate value, which
  • the specific implementation may be described below in conjunction with specific examples, and the embodiments of the present application will not be repeated here.
  • the neural network positioning method provided in the embodiment of the present application may further include the following steps S400, S410, S420, and S430.
  • Step S400 For the to-be-fixed unit of the neural network, based on the data distribution of the weight of the to-be-fixed unit, determine the fixed-point hyperparameter of the weight of the to-be-fixed unit.
  • Step S410 based on the fixed-pointed super-parameter of the weight of the to-be-fixed unit, determine a second fixed-pointed super-parameter candidate value range.
  • Step S420 Determine the final fixed super parameter of the weight value of the to-be-fixed unit from the second fixed super parameter candidate value range.
  • step S430 the weight of the unit to be fixed is fixed based on the final super-parameter of the weight of the unit to be fixed.
  • the to-be-fixed unit of the neural network in addition to the characteristic value output by the to-be-fixed unit can be fixed according to the method described in the above embodiment, it also needs to be fixed.
  • the weight of the unit is fixed-point.
  • the weight of the floating-point state of each unit has been determined when the neural network is trained (the neural network is in the original floating-point state at this time).
  • the data distribution of the weights of the floating-point state of the unit is not affected by the fixation of the previous unit. Therefore, for the weights of the neural network, when the weights of the to-be-fixed units of the neural network are fixed, the The specific implementation can refer to the related implementation in the traditional neural network fixed-point solution.
  • the determined Optimize the fixed-point super-parameters to obtain the fixed-point super-parameters that are actually used to fix the weights of the to-be-fixed units referred to as the final fixed-point super-parameters in this article
  • the range of the final fixed-pointing super-parameters used to search for the weights of the to-be-fixed units may be determined.
  • Hyperparameter candidate value range determines the final fixed-point hyperparameter of the weight of the to-be-fixed unit from the second fixed-pointed super-parameter candidate value range, and further, the final fixed-point based on the weight of the to-be-fixed unit
  • the super-parameters are used to fix the weights of the units to be fixed.
  • the fixed-point hyperparameter of the weight of the fixed-point unit can be optimized based on the output error of the neural network, and the fixed-point super-parameter that minimizes the output error of the neural network can be selected as the final fixed point of the weight of the to-be-fixed unit ⁇ .
  • the output error of the neural network corresponding to each candidate value in the second fixed-point hyperparameter candidate value range can be determined separately, and the candidate with the smallest output error of the corresponding neural network can be determined The value is determined as the final fixed-pointing hyperparameter of the weight of the to-be-fixed unit.
  • respectively determining the output error of the neural network corresponding to each candidate value in the second fixed-point hyperparameter candidate value range may include: for any candidate value, based on the third type feature value and the first The four types of feature values determine the output error of the neural network corresponding to the candidate value.
  • the fixed-point processing of the neural network may bring errors to the output accuracy of the neural network, and the output of the fixed-point neural network is different from the original floating-point state.
  • the smaller the output error of the neural network the higher the output accuracy of the fixed-point neural network. Therefore, the fixed-point can be fixed based on the error between the output of the fixed-point neural network and the output of the neural network in the original floating-point state Super parameters are optimized.
  • the eigenvalues output by each unit of the neural network when the weight of the fixed-point unit is fixed using the candidate value (referred to herein as The third type feature value), and, in the original floating point state, the feature value output by each unit of the neural network (herein referred to as the fourth type feature value), determine the output error of the neural network corresponding to the candidate value, and its specific implementation It may be described below in conjunction with specific examples, and the embodiments of the present application will not be repeated here.
  • the neural network fixed-pointing method provided in the embodiment of the present application may further include: the pending point is based on the situation that the fixed-pointed unit of the neural network maintains the fixed-pointing state The eigenvalues output by the transformation unit, and the eigenvalues output by the to-be-fixed unit in the original floating-point state, optimize the weight of the to-be-fixed unit.
  • each layer of the neural network is fixed-pointed, there may be errors in accuracy. As the number of layers deepens, the cumulative error in fixed-pointing may bring a greater impact on the overall performance of the neural network. Therefore, reducing the deviation caused by the fixed-pointing of each layer can reduce the accuracy loss of each layer of the neural network after the fixed-pointing, and improve the overall performance of the neural network.
  • the fixed-point unit based on the neural network may be kept fixed.
  • the eigenvalue output by the to-be-fixed unit in the state of the state and the characteristic value output by the to-be-fixed unit in the original floating-point state are optimized for the weight of the to-be-fixed unit.
  • the weight optimization may not be performed for the first to-be-fixed unit of the neural network handle.
  • the above-mentioned neural network-based fixed-point unit maintains the fixed-point state of the characteristic value output by the to-be-fixed unit and the characteristic value output by the to-be-fixed unit in the original floating-point state.
  • Optimizing the weight of the to-be-fixed unit may include: optimizing the weight of the to-be-fixed unit, so that the fixed-point unit of the neural network maintains the fixed-point state of the characteristic value output by the to-be-fixed unit , And, the error between the eigenvalues output by the to-be-fixed unit in the original floating-point state is the smallest.
  • one may be determined based on the characteristic value output by the to-be-fixed unit under the condition that the fixed-point unit of the neural network remains in the fixed-point state, and the characteristic value output by the to-be-fixed unit in the original floating-point state.
  • the weight value of the unit to be fixed is optimized based on the principle of minimizing the error.
  • FIG. 6 is a schematic flowchart of a neural network fixed-pointing method provided by an embodiment of this application.
  • the neural network fixed-pointing method may include the following steps S600 and S610.
  • Step S600 For the to-be-fixed unit of the neural network, the characteristic value output by the to-be-fixed unit under the condition that the fixed-point unit of the neural network maintains the fixed-point state, and the output of the to-be-fixed unit in the original floating-point state The eigenvalues of, optimize the weight of the unit to be fixed.
  • the neural network in order to improve the flexibility of neural network fixed-pointing, can be divided into multiple units according to one layer or continuous multiple layers of one unit, and the neural network can be fixed-pointed unit by unit.
  • the The weights of the pointized units are optimized.
  • the optimization processing of the weight may not be performed.
  • step S610 the optimized unit to be fixed is fixed.
  • the optimized unit to be fixed when the weight of the unit to be fixed is optimized in the manner described in step S600, the optimized unit to be fixed can be fixed.
  • the neural network is divided into multiple units and fixed-point processing is performed unit by unit, which improves the flexibility of the fixed-point neural network; in addition, when the unit to be fixed is fixed-pointed Previously, the weight of the fixed-point unit was optimized to reduce the error caused by the fixed-pointization of the previous fixed-point unit, reduce the accuracy loss of the neural network fixed-point, and improve the performance of the neural network fixed-point.
  • the characteristic value output by the to-be-fixed unit under the condition that the neural network-based fixed-point unit remains in the fixed-point state, and the to-be-fixed unit in the original floating-point state may include: optimizing the weight of the to-be-fixed unit, so that the fixed-point unit of the neural network maintains the fixed-point state.
  • the error between the characteristic value output by the initiation unit and the characteristic value output by the to-be-fixed initiation unit in the original floating-point state is the smallest.
  • one may be determined based on the characteristic value output by the to-be-fixed unit under the condition that the fixed-point unit of the neural network remains in the fixed-point state, and the characteristic value output by the to-be-fixed unit in the original floating-point state.
  • the specific implementation can be described below in conjunction with specific examples, and the embodiments of the present application will not repeat them here.
  • the optimization of the to-be-fixed unit may include: output of the to-be-fixed unit under the condition that the fixed-point unit based on the neural network maintains the fixed-point state According to the data distribution of the characteristic value, the optimized fixed-point hyperparameter of the characteristic value output by the to-be-fixed unit is determined, and based on the fixed-point super-parameter, the optimized characteristic value output by the to-be-fixed unit is fixed.
  • the unit to be fixed when the unit to be fixed is the first unit to be fixed in the neural network, for example, the first unit of the neural network, the neural network does not include the fixed unit, in this case, it can be based on the
  • the data distribution of the characteristic value output by the to-be-fixed unit determines the fixed-point super-parameter of the characteristic value output by the to-be-fixed unit, and fixes the characteristic value output by the to-be-fixed unit based on the fixed super-parameter.
  • the characteristic value output by the optimized unit to be fixed can be fixed based on the determined super-parameter.
  • the optimized fixed-pointing hyperparameters of the characteristic values output by the to-be-fixed unit may further include: determining the fixed-pointing hyperparameters based on the optimized characteristic values output by the to-be-fixed unit, The third fixed-point super-parameter candidate value range; the final fixed-point super-parameter of the characteristic value output by the to-be-fixed unit after optimization is determined from the third fixed-point super-parameter candidate value range.
  • the above-mentioned fixed-pointing based on the fixed-pointing super-parameters on the optimized eigenvalues output by the to-be-fixed unit may include: a final fixed-pointing super-parameter pair optimized based on the eigenvalues output by the to-be-fixed unit The eigenvalue output by the to-be-fixed unit is fixed-pointed.
  • the determined fixed-point super-parameter can also be optimized to obtain the to-be-fixed point that is actually used for optimization.
  • the eigenvalues output by the transformation unit are used for fixed-point fixed-point super-parameters (referred to as final fixed-point super-parameters in this article) to further improve the performance of neural network fixed-point.
  • the range for searching the final fixed-point super-parameters (referred to herein as the third fixed-point super-parameter candidate value) may be determined. Range), and determine the final fixed-point super-parameter of the characteristic value output by the optimized to-be-fixed unit from the third fixed-point super-parameter candidate value range.
  • the foregoing determination of the optimized final fixed-pointing hyperparameters of the characteristic values output by the to-be-fixed unit after optimization from the third fixed-pointing hyperparameter candidate value range may include: respectively determining the third fixed-pointing hyperparameters The output error of the neural network corresponding to each candidate value in the candidate value range; the candidate value with the smallest output error of the corresponding neural network is determined as the final fixed-pointing hyperparameter of the characteristic value output by the optimized point-to-fixed unit.
  • the fixed-point hyperparameters of the characteristic value output by the fixed-point unit can be optimized based on the output error of the neural network, and the fixed-point super-parameter that minimizes the output error of the neural network can be selected as the output of the optimized to-be-fixed unit The final fixed-point hyperparameter of the eigenvalue.
  • the output error of the neural network corresponding to each candidate value in the third fixed-point hyperparameter candidate value range can be determined separately, and the candidate with the smallest output error of the corresponding neural network can be determined The value is determined as the final fixed-pointing hyperparameter of the eigenvalue output by the pending-pointing unit after optimization.
  • the foregoing determination of the output error of the neural network corresponding to each candidate value in the third fixed-point hyperparameter candidate value range may include: for any candidate value, based on the fifth-type feature value and the sixth-type feature The value determines the output error of the neural network corresponding to the candidate value.
  • the fixed-point processing of the neural network may bring errors to the output accuracy of the neural network, and the output of the fixed-point neural network is different from the original floating-point state.
  • the smaller the output error of the neural network the higher the output accuracy of the fixed-point neural network. Therefore, the fixed-point can be fixed based on the error between the output of the fixed-point neural network and the output of the neural network in the original floating-point state Super parameters are optimized.
  • the characteristic value output by each unit of the neural network ( This article is called the fifth type feature value), and, in the original floating point state, the feature value output by each unit of the neural network (herein referred to as the six type feature value), determine the output error of the neural network corresponding to the candidate value,
  • the fifth type feature value the characteristic value output by each unit of the neural network
  • the six type feature value determine the output error of the neural network corresponding to the candidate value
  • the weight of the to-be-fixed unit in addition to the characteristic value output by the to-be-fixed unit, the weight of the to-be-fixed unit needs to be fixed. Since the weight of the unit to be fixed is not affected by the fixed unit of the neural network, after optimizing the weight of the unit to be fixed according to the method shown in Figure 6, you can refer to the traditional neural network fixed-point solution In the implementation of fixed-point weighting, the weights of the optimized units to be fixed-point are fixed-pointed.
  • the determined fixed-point hyperparameter can also be determined. Carry out optimization to determine the final fixed-point hyperparameters.
  • the optimization of the to-be-fixed unit may include: determining the optimized weight of the to-be-fixed unit based on the data distribution of the weight of the to-be-fixed unit after optimization.
  • Fixed-point super-parameter based on the optimized fixed-point super-parameter of the weight of the unit to be fixed, determine the fourth fixed-point super-parameter candidate value range; determine the optimized value from the fourth fixed-point super-parameter candidate value range
  • the final fixed-pointing super parameter of the weight of the to-be-fixed unit based on the optimized final fixed-pointing super-parameter of the weight of the to-be-fixed unit, the optimized weight of the to-be-fixed unit is fixed.
  • FIG. 7 is a schematic flowchart of a neural network fixed-pointing method provided by an embodiment of this application.
  • the neural network fixed-pointing method may include the following steps S700, S710, S720, and S730.
  • Step S700 Analyze the topological structure of the input floating-point model to generate a neural network data flow graph.
  • Step S710 Generate a data layer of the neural network based on the sample picture information in the configuration file.
  • Step S720 Based on the optimization strategy of the platform to be deployed in the configuration file, split and merge the topology of the neural network to obtain a preprocessed floating-point model.
  • embodiments of the present application provide a solution for automatically realizing neural network positioning.
  • the topological structure of the floating point model can be analyzed to generate a data flow diagram of the neural network, that is, according to the process of data from input to output, sequentially
  • the structure diagram of the floating-point model determined by each layer of the floating-point model is passed, and the data layer of the neural network is generated according to the sample image information in the configuration file, such as the access path of the sample image and the preprocessing method of the sample image.
  • the platform characteristics of different deployment platforms in order to optimize the effect of neural network deployment on different platforms, it can be based on the platform characteristics of the platform to be deployed in the configuration file (which can be called optimization strategy), and the topology of the neural network Splitting (such as splitting part of the topological structure of the floating-point model according to the optimization strategy of the platform to be deployed) and fusion (such as merging the BN layer of the floating-point model into the pre-Conv layer), etc., to obtain the pre-processed floating
  • the point model makes the topological structure of the pre-processed floating-point model more suitable for the platform characteristics of the platform to be deployed, improves the efficiency of the pre-processed floating-point model on hardware, and optimizes the operating effect.
  • Step S730 Perform fixed-point conversion on the pre-processed floating-point model.
  • the pre-processed floating-point model when the preprocessing of the floating-point mode is completed, can be fixed-point to obtain a fixed-point model that can be used for deployment.
  • the pre-processed floating-point model may be fixed-point processed in the manner described in any of the foregoing embodiments.
  • the fixed-point simulation test can be performed on the fixed-point model to evaluate the fixed-point performance of the model.
  • the preset performance evaluation methods and indicators determine whether the performance of the fixed-point model meets the demand. If the demand is met, the model can be finally converted and deployed; if the demand is not met, the fixed-point model optimization is carried out to further Improve the performance of fixed-point models.
  • the model can be tuned in a more global and detailed manner.
  • model training based on a fixed-point budget can be performed.
  • the knowledge distillation training method can be used to guide the training and tuning of the fixed-point model using the original model.
  • the tuning performance meets the requirements, the final fixed-point hyperparameter table and the model to be converted are output.
  • intelligent analysis and processing can be performed based on the neural network after the fixed point, including but not limited to computer vision processing (such as image classification, target detection) Or speech segmentation, etc.) or natural language processing.
  • Neural network fixed-pointization is a commonly used model acceleration algorithm. By quantizing the weight of the model and the output feature value into a fixed bit number, such as 8bit, 16bit or very low 1bit, 2bit, it can be well solved in hardware
  • a fixed bit number such as 8bit, 16bit or very low 1bit, 2bit
  • the automated neural network fixed-point system may include a fixed-point evaluation and tuning module and a fixed-point conversion module.
  • the pre-configured fixed-point configuration information (which can be provided in the form of a configuration file), the to-be-fixed model (that is, the floating-point model), and the sample set can be used to obtain The deployed fixed-point model file.
  • the specific functions of each module are described in detail below.
  • FIG. 9 The functional flowchart of the fixed-point evaluation and tuning module can be shown in Figure 9, which mainly includes the following processes: floating-point model preprocessing, statistical evaluation and optimization, and fixed-point testing and tuning. Each process will be described in detail below.
  • the preprocessing process of the floating-point model mainly includes: analyzing the topological structure of the input floating-point model to generate a neural network data flow diagram; based on the sample picture information in the configuration file, generating the data layer of the neural network; based on the configuration file
  • the optimization strategy of the platform to be deployed splitting the topology of the neural network (such as splitting part of the topological structure of the floating-point model according to the optimization strategy of the platform to be deployed) and fusion (such as merging the BN layer of the floating-point model into Pre-Conv layer) to obtain a model that is more suitable for deployment on the platform to be deployed with a topology structure (that is, a preprocessed floating-point model).
  • the pre-processed floating-point model obtained after the pre-processing of the floating-point model can be subjected to subsequent processing.
  • the purpose of the fixed-point neural network is to quantify the weight of the model and the output feature value into a fixed bit value to achieve the effect of accelerating the reasoning.
  • fixed-point algorithms including but not limited to linear symmetric fixed-point algorithms, linear asymmetric fixed-point algorithms, and Power-of-Two fixed-point algorithms can be used to realize neural network fixed-pointization.
  • linear symmetric fixed-point algorithm linear asymmetric fixed-point algorithm
  • Power-of-Two fixed-point algorithm Power-of-Two fixed-point algorithm
  • X represents the original floating-point data
  • C x represents the cut-off value of the absolute value of the floating-point data
  • B w represents the fixed-point bit width
  • X Q represents the fixed-point value
  • X represents the original floating point data
  • C n represents the left side truncation value of the floating point data
  • C p represents the right side truncation value of the floating point data
  • B w represents the bit width of the fixed point
  • X Q represents the fixed-point value.
  • X represents the original floating-point data
  • C x represents the cutoff value of the absolute value of the floating-point data
  • B w represents the bit width of the fixed-point
  • X Q represents the fixed-point Value
  • the cut-off value of floating-point data (that is, the fixed-point hyperparameter) needs to be used.
  • the selection of the cut-off value is very important for the effect of fixed-point, and it is often determined according to the distribution of the original data.
  • the weights are fixed: for the neural network of the original floating-point state, the weight of the floating-point state of each unit is determined when the neural network is trained, and the floating-point state of each unit The data distribution of the weights of is not affected by the fixed-pointing of the previous unit. Therefore, the data distributions of the weights of each unit of the neural network in the original floating-point state can be separately counted, and the fixed-point hyperparameters can be calculated.
  • the neural network fixed-point solution provided by the embodiments of the present application has at least the following improvements.
  • a layer-by-layer evaluation that is, a unit including a layer of the neural network as an example
  • the current layer To be fixed-pointed layer
  • the linear symmetric fixed-point algorithm the linear asymmetric fixed-point algorithm, and the Power-of-Two fixed-point algorithm are still taken as examples to describe the fixed-point hyperparameter calculation implemented by the layer-by-layer evaluation method in the embodiment of the present application.
  • any subsequent to-be-fixed layer while the fixed-point layer remains in the fixed-point state, again input a certain number of sample pictures to the model for forward calculation, and count the feature values and weights output by the to-be-fixed layer
  • the data distribution of the feature calculate the fixed super parameter of the feature value output by the to-be-fixed layer and the fixed super-parameter of the weight value, and use the formulas (1) and (2) to convert the to-be-fixed layer into a fixed-point Operation state, until all layers of the model are converted into fixed-point operation state.
  • any subsequent to-be-fixed layer while the fixed-point layer remains in the fixed-point state, again input a certain number of sample pictures to the model for forward calculation, and count the feature values and weights output by the to-be-fixed layer
  • the data distribution of the feature calculate the fixed super-parameter of the feature value output by the to-be-fixed layer and the fixed-point super-parameter of the weight value, and use the formulas (3) and (4) to convert the to-be-fixed layer into a fixed-point Operation state, until all layers of the model are converted into fixed-point operation state.
  • any subsequent to-be-fixed layer while the fixed-point layer remains in the fixed-point state, again input a certain number of sample pictures to the model for forward calculation, and count the feature values and weights output by the to-be-fixed layer
  • the data distribution of the feature calculate the fixed super parameter of the feature value output by the to-be-fixed layer and the fixed super-parameter of the weight value, and use the formulas (5), (6) and (7) to convert the to-be-fixed layer It is a fixed-point computing state until all layers of the model are converted into a fixed-point computing state.
  • the determined fixed-point hyperparameters can also be optimized, that is, after the fixed-point hyperparameters (including the fixed-point hyperparameters and/or output eigenvalues of the output eigenvalues) are determined according to the above method
  • the search range of the final fixed-point super-parameters can be determined based on the determined fixed-point super-parameters (such as the first fixed-point super-parameter candidate value range or the second fixed-point super-parameter above). Candidate value range, etc.), and search for the fixed-point hyperparameter that has the least impact on the output error of the neural network in the search range, as the final fixed-point hyperparameter.
  • the calculation method of the neural network output error includes, but is not limited to, the mean square error, KL divergence, Euclidean distance, and the like.
  • the mean square error as an example, the output error of the neural network can be determined in the following way:
  • L represents the total number of layers of the model
  • O i represents the output feature value of the layer in the fixed-point state
  • represents the number of feature data.
  • the output error of layer i of the neural network can be determined. Based on the output error of each layer of the neural network, the output error of the neural network can be determined by formula (9).
  • the The weights of the pointization unit are optimized, and the specific implementation process may include the following steps 1 and 2.
  • Step 1 Perform a fixed-point evaluation on the first to-be-fixed layer L 1 of the original model M to obtain a fixed-point hyperparameter, and then fix the layer to obtain a model Q 1 .
  • Step 2 the calculation model and the original model M L Q 1 in the first floating point error output layer L 2 after a layer to minimize this error to optimize the power of two L principle.
  • determining the output error of the original model and the quantized model in the to-be-fixed layer can be achieved through functions such as L1-loss, L2-loss, and expected deviation.
  • L1-loss L2-loss
  • expected deviation expected deviation
  • Equation (10) and (11) Represents the forward inference function of the L 2 layer, and L 2 represent the weight of the layer and the BIAS (L 2 layer to an example convolution layer), Y is the first step extracted from the original model M eigenvalues layer L 2, X Q Q from the current model The input eigenvalues of the L 2 layer in 1, and They respectively represent the optimized weight and bias of the L 2 layer (still floating-point at this time).
  • the solid-line box represents the original floating-point layer
  • the dashed box represents the fixed-point layer obtained by fixed-pointing the original floating-point layer
  • the solid-line box with filled squares represents the updated floating-point layer based on minimizing local errors.
  • the dashed frame with filled squares represents the fixed-point layer obtained after the updated floating-point layer is fixed-point.
  • the performance of the fixed-point neural network is evaluated instead of According to the error between the final output of the quantized model and the true value of the sample in the traditional neural network fixed-point solution, the performance of the neural network fixed-point is evaluated. Therefore, the sample used for the neural network fixed-point can be without annotated information The sample, which reduces the requirements on the sample, and improves the feasibility of the plan.
  • the fixed-point model can be subjected to a fixed-point simulation test to evaluate the fixed-point performance of the model. According to the preset performance evaluation methods and indicators, determine whether the performance of the fixed-point model meets the demand. If the demand is met, the model can be finally converted and deployed; if the demand is not met, the fixed-point model optimization is carried out to further Improve the performance of fixed-point models.
  • the model can be tuned in a more global and detailed manner.
  • model training based on a fixed-point budget can be performed.
  • the knowledge distillation training method can be used to guide the training and tuning of the fixed-point model using the original model.
  • the tuning performance meets the requirements, the final fixed-point hyperparameter table and the model to be converted are output.
  • the fixed-point conversion module can output a deployable file to deploy a quantified neural network model on the platform to be deployed based on the deployable file.
  • intelligent analysis and processing can be performed based on the fixed neural network, including but not limited to computer vision processing (such as image classification, target detection, or speech segmentation, etc.) or natural language processing.
  • the characteristics of the output of the to-be-fixed unit based on the situation that the fixed-point unit of the neural network maintains the fixed-point state The data distribution of the value, the fixed-point hyperparameter of the eigenvalue output by the to-be-fixed unit is determined, and the eigenvalue output by the to-be-fixed unit is fixed based on the fixed-point super-parameter, and the neural network is unit-by-unit.
  • Fixed-point for the to-be-fixed unit of the neural network, keep the fixed-point unit in the fixed-point state to obtain a more realistic data distribution of the output feature value, thereby improving the performance of the fixed-point neural network.
  • the neural network fixed-pointing device may include: a determination module for determining a pending unit of the neural network , Based on the data distribution of the feature value output by the to-be-fixed unit under the condition that the fixed-point unit of the neural network maintains the fixed-point state, the fixed-point hyperparameter of the feature value output by the to-be-fixed unit is determined; the fixed-point module , Used to fix the characteristic value output by the unit to be fixed based on the fixed super parameter.
  • the determining module is further configured to: determine the fixed-pointing hyperparameter based on the characteristic value output by the to-be-fixed unit The first fixed point hyperparameter candidate value range; the final fixed point hyperparameter of the characteristic value output by the to-be-fixed unit is determined from the first fixed point hyperparameter candidate value range.
  • the fixed-pointing module based on the fixed-pointing super-parameter, fixes the characteristic value output by the to-be-fixed unit, including: the final fixed-pointing super-parameter based on the characteristic value output by the to-be-fixed unit to the pending point
  • the eigenvalues output by the transformation unit are fixed-pointed.
  • the determining module determines the final fixed-pointing hyper-parameter of the characteristic value output by the to-be-fixed unit from the range of the first fixed-pointing super-parameter candidate value, including: separately determining the first fixed-pointing hyperparameter The output error of the neural network corresponding to each candidate value in the fixed-point hyperparameter candidate value range; the candidate value with the smallest output error of the corresponding neural network is determined as the final fixed-point hyperparameter of the feature value output by the to-be-fixed unit .
  • the determining module separately determines the output error of the neural network corresponding to each candidate value in the first fixed-point hyperparameter candidate value range, including: for any candidate value, based on the first type The feature value and the second type feature value determine the output error of the neural network corresponding to the candidate value, and the first type feature value is the neural network when the feature value output by the to-be-fixed unit is fixed using the candidate value The feature value output by each unit; the second type feature value is the feature value output by each unit of the neural network in the original floating point state.
  • the determining module is further configured to determine the weight of the pending unit of the neural network based on the data distribution of the weight of the pending unit The fixed-point super-parameter of the; based on the fixed-point super-parameter of the weight of the to-be-fixed unit, determine the second fixed-point super-parameter candidate value range; determine the to-be-fixed unit from the second fixed-point super-parameter candidate value range The final fixed-point hyperparameters of the weights.
  • the fixed-pointing module is further configured to fix the weight of the to-be-fixed unit based on the final fixed-pointing hyperparameter of the weight of the to-be-fixed unit.
  • the determining module determines the final fixed-pointing hyperparameter of the weight value of the to-be-fixed unit from the second fixed-pointing super-parameter candidate value range, including: separately determining the second fixed-pointing hyperparameter The output error of the neural network corresponding to each candidate value in the hyperparameter candidate value range; the candidate value with the smallest output error of the corresponding neural network is determined as the final fixed point super parameter of the weight of the to-be-fixed unit.
  • the determining module separately determines the output error of the neural network corresponding to each candidate value in the second fixed-point hyperparameter candidate value range, including: for any candidate value, based on a third type of feature Value and the fourth type feature value determine the output error of the neural network corresponding to the candidate value.
  • the third type feature value uses the candidate value to fix the weight of the to-be-fixed unit, each of the neural networks The feature value output by the unit; the fourth type feature value is the feature value output by each unit of the neural network in the original floating point state.
  • the determining module is based on the feature value output by the to-be-fixed unit in the case where the fixed-point unit of the neural network remains in a fixed-point state
  • the determining module is also used to: based on the situation that the fixed-pointing unit of the neural network maintains the fixed-pointing state, the pending-pointing
  • the eigenvalue output by the unit and the eigenvalue output by the to-be-fixed unit in the original floating-point state are optimized for the weight of the to-be-fixed unit.
  • the determining module is based on the characteristic value output by the to-be-fixed unit under the condition that the fixed-point unit of the neural network maintains the fixed-point state, and the to-be-fixed unit in the original floating-point state
  • the output characteristic value, optimizing the weight of the pending unit includes: optimizing the weight of the pending unit, so that the determined unit of the neural network maintains the fixed state when the pending unit
  • the error between the characteristic value output by the initiation unit and the characteristic value output by the to-be-fixed initiation unit in the original floating-point state is the smallest.
  • the unit includes one layer or successive multiple layers of the neural network, and the neural network includes a plurality of units.
  • the neural network fixed-pointing device may include: an optimization module for undetermined neural network Unit, based on the characteristic value output by the to-be-fixed unit under the condition that the fixed-point unit of the neural network maintains the fixed-point state, and the characteristic value output by the to-be-fixed unit in the original floating-point state, for the pending point The weight of the unit is optimized; the fixed-point module is used to fix the optimized unit to be fixed.
  • the optimization module is based on the characteristic value output by the to-be-fixed unit under the condition that the fixed-point unit of the neural network remains in the fixed-point state, and the to-be-fixed unit in the original floating-point state
  • the output characteristic value, optimizing the weight of the pending unit includes: optimizing the weight of the pending unit, so that the determined unit of the neural network maintains the fixed state when the pending unit
  • the error between the characteristic value output by the initiation unit and the characteristic value output by the to-be-fixed initiation unit in the original floating-point state is the smallest.
  • the fixed-pointing module performs fixed-pointing on the optimized unit to be fixed, including: performing the fixed-pointing based on the situation that the fixed-pointing unit of the neural network maintains the fixed-pointing state.
  • the data distribution of the eigenvalues output by the unit determine the optimized fixed-point hyperparameters of the eigenvalues output by the to-be-fixed unit, and fix the optimized eigenvalues output by the to-be-fixed unit based on the fixed-point hyperparameters change.
  • the fixed-pointing module determines the optimized fixed-pointing hyperparameter of the characteristic value output by the to-be-fixed unit, it is also used to: based on the optimized characteristic value output by the to-be-fixed unit Determine the third fixed-point super-parameter candidate value range; from the third fixed-point super-parameter candidate value range, determine the optimized final fixed-point super-parameter of the characteristic value output by the to-be-fixed unit.
  • the fixed-pointing module fixes the optimized eigenvalues output by the unit to be fixed based on the super-parameters, including: the final fixed-point super-parameter pair optimized based on the characteristic values output by the unit to be fixed
  • the eigenvalues output by the to-be-fixed unit are fixed-pointed.
  • the fixed-pointing module determines from the third fixed-pointing super-parameter candidate value range the final fixed-pointing super-parameters of the characteristic values output by the to-be-fixed unit after optimization, including: respectively determining The output error of the neural network corresponding to each candidate value in the third fixed-point hyperparameter candidate value range; the candidate value with the smallest output error of the corresponding neural network is determined as the eigenvalue output of the optimized unit to be fixed Finally, the super-parameters are fixed-pointed.
  • the fixed-pointing module separately determines the output error of the neural network corresponding to each candidate value in the third fixed-pointing hyperparameter candidate value range, including: for any candidate value, based on the fifth type The feature value and the sixth type feature value determine the output error of the neural network corresponding to the candidate value; wherein the fifth type feature value uses the candidate value to locate the optimized feature value output by the to-be-fixed unit When, the eigenvalues output by the units of the neural network; the sixth type eigenvalues are the eigenvalues output by the units of the neural network in the original floating-point state.
  • the neural network includes a plurality of units, and each unit includes one layer or successive multiple layers of the neural network.
  • the neural network fixed-pointing device may include: an analysis module for analyzing the input floating-point model The topology structure is analyzed to generate a neural network data flow graph; a generation module is used to generate the data layer of the neural network based on the sample picture information in the configuration file; the processing module is used to generate the data layer of the neural network based on the configuration file to be deployed
  • the optimization strategy of the platform is to split and merge the topology of the neural network to obtain the pre-processed floating-point model; the fixed-point module is used to perform the pre-processing based on the method described in the above method embodiment
  • the floating-point model is fixed-point.
  • FIG. 14 is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of this application.
  • the electronic device may include a processor 1401 and a memory 1402 storing machine-executable instructions.
  • the processor 1401 and the memory 1402 may communicate via a system bus 1403.
  • the processor 1401 can execute the neural network fixed-pointing method described above.
  • the memory 1402 mentioned herein may be any electronic, magnetic, optical, or other physical storage device, and may contain or store information, such as executable instructions, data, and so on.
  • the machine-readable storage medium can be: RAM (Radom Access Memory), volatile memory, non-volatile memory, flash memory, storage drive (such as hard drive), solid state drive, any type of storage disk (Such as CD, DVD, etc.), or similar storage media, or a combination of them.
  • a machine-readable storage medium is also provided, such as the memory 1402 in FIG. 14.
  • the machine-readable storage medium stores machine-executable instructions.
  • the machine-executable instructions When executed by the processor, Realize the neural network fixed-point method described above.
  • the machine-readable storage medium may be ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
  • a computer program is also provided, the computer program is stored in a machine-readable storage medium, and when the computer program is executed by a processor, the neural network fixed-pointing method described above is realized.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Image Analysis (AREA)

Abstract

La présente invention concerne un procédé et un appareil de point fixe de réseau neuronal, un dispositif électronique, et un support de stockage lisible. Le procédé de point fixe de réseau neuronal comporte les étapes consistant: pour une unité à mettre au point fixe d'un réseau neuronal, d'après la distribution de données de valeurs caractéristiques délivrées par l'unité à mettre au point fixe dans le cas où une unité au point fixe du réseau neuronal maintient un état de point fixe, à déterminer des hyperparamètres de point fixe des valeurs caractéristiques délivrées par l'unité à mettre au point fixe; et d'après les hyperparamètres de point fixe, à effectuer un point fixe sur les valeurs caractéristiques délivrées par l'unité à mettre au point fixe. Le procédé peut améliorer les performances de point fixe du réseau neuronal.
PCT/CN2021/071311 2020-01-14 2021-01-12 Procédés et appareils de point fixe de réseau neuronal, dispositif électronique, et support de stockage lisible Ceased WO2021143686A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010038017.1 2020-01-14
CN202010038017.1A CN113128659B (zh) 2020-01-14 2020-01-14 神经网络定点化方法、装置、电子设备及可读存储介质

Publications (1)

Publication Number Publication Date
WO2021143686A1 true WO2021143686A1 (fr) 2021-07-22

Family

ID=76771130

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/071311 Ceased WO2021143686A1 (fr) 2020-01-14 2021-01-12 Procédés et appareils de point fixe de réseau neuronal, dispositif électronique, et support de stockage lisible

Country Status (2)

Country Link
CN (1) CN113128659B (fr)
WO (1) WO2021143686A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024149245A1 (fr) * 2023-01-13 2024-07-18 杭州海康威视数字技术股份有限公司 Procédé et appareil de décodage, procédé et appareil de codage, et dispositifs associés
CN119316617A (zh) * 2023-07-12 2025-01-14 杭州海康威视数字技术股份有限公司 一种解码方法、装置及其设备

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116341633B (zh) * 2023-05-29 2023-09-01 山东浪潮科学研究院有限公司 一种模型部署方法、装置、设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150170020A1 (en) * 2013-12-13 2015-06-18 Amazon Technologies, Inc. Reducing dynamic range of low-rank decomposition matrices
CN105760933A (zh) * 2016-02-18 2016-07-13 清华大学 卷积神经网络的逐层变精度定点化方法及装置
CN106611216A (zh) * 2016-12-29 2017-05-03 北京旷视科技有限公司 基于神经网络的计算方法及装置
CN107688849A (zh) * 2017-07-28 2018-02-13 北京深鉴科技有限公司 一种动态策略定点化训练方法及装置

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101609416B (zh) * 2009-07-13 2012-11-14 清华大学 提高分布式系统性能调优速度的方法
CN109934331B (zh) * 2016-04-29 2020-06-19 中科寒武纪科技股份有限公司 用于执行人工神经网络正向运算的装置和方法
US10621486B2 (en) * 2016-08-12 2020-04-14 Beijing Deephi Intelligent Technology Co., Ltd. Method for optimizing an artificial neural network (ANN)
US10643124B2 (en) * 2016-08-12 2020-05-05 Beijing Deephi Intelligent Technology Co., Ltd. Method and device for quantizing complex artificial neural network
CN106650922B (zh) * 2016-09-29 2019-05-03 清华大学 硬件神经网络转换方法、计算装置、软硬件协作系统
CN107239826A (zh) * 2017-06-06 2017-10-10 上海兆芯集成电路有限公司 在卷积神经网络中的计算方法及装置
KR102589303B1 (ko) * 2017-11-02 2023-10-24 삼성전자주식회사 고정 소수점 타입의 뉴럴 네트워크를 생성하는 방법 및 장치
CN110413255B (zh) * 2018-04-28 2022-08-19 赛灵思电子科技(北京)有限公司 人工神经网络调整方法和装置
KR102824642B1 (ko) * 2018-05-14 2025-06-25 삼성전자주식회사 뉴럴 네트워크의 양자화 방법 및 장치
CN109635935B (zh) * 2018-12-29 2022-10-14 北京航空航天大学 基于模长聚类的深度卷积神经网络模型自适应量化方法
CN110135565B (zh) * 2019-05-20 2023-03-24 上海大学 针对神经网络算法在集成电路上实现性能的评估系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150170020A1 (en) * 2013-12-13 2015-06-18 Amazon Technologies, Inc. Reducing dynamic range of low-rank decomposition matrices
CN105760933A (zh) * 2016-02-18 2016-07-13 清华大学 卷积神经网络的逐层变精度定点化方法及装置
CN106611216A (zh) * 2016-12-29 2017-05-03 北京旷视科技有限公司 基于神经网络的计算方法及装置
CN107688849A (zh) * 2017-07-28 2018-02-13 北京深鉴科技有限公司 一种动态策略定点化训练方法及装置

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024149245A1 (fr) * 2023-01-13 2024-07-18 杭州海康威视数字技术股份有限公司 Procédé et appareil de décodage, procédé et appareil de codage, et dispositifs associés
CN119316617A (zh) * 2023-07-12 2025-01-14 杭州海康威视数字技术股份有限公司 一种解码方法、装置及其设备
WO2025011638A1 (fr) * 2023-07-12 2025-01-16 杭州海康威视数字技术股份有限公司 Procédé et appareil de décodage, et dispositif

Also Published As

Publication number Publication date
CN113128659B (zh) 2024-06-28
CN113128659A (zh) 2021-07-16

Similar Documents

Publication Publication Date Title
US20240161474A1 (en) Neural Network Inference Acceleration Method, Target Detection Method, Device, and Storage Medium
CN109165664B (zh) 一种基于生成对抗网络的属性缺失数据集补全与预测方法
US11341424B2 (en) Method, apparatus and system for estimating causality among observed variables
Liu et al. Muon is scalable for LLM training
CN113283426A (zh) 基于多目标神经网络搜索的嵌入式目标检测模型生成方法
WO2021143686A1 (fr) Procédés et appareils de point fixe de réseau neuronal, dispositif électronique, et support de stockage lisible
CN111027629A (zh) 基于改进随机森林的配电网故障停电率预测方法及系统
CN111968744B (zh) 基于贝叶斯优化的脑卒中与慢性病模型的参数优化方法
JP2020009301A (ja) 情報処理装置および情報処理方法
KR20220032861A (ko) 하드웨어에서의 성능을 고려한 뉴럴 아키텍처 서치 방법 빛 장치
CN118414621A (zh) 使用预算感知的贝叶斯优化的超参数选择
CN119599946A (zh) 一种路面裂缝检测方法、装置和电子设备
CN120296046A (zh) 多表关联查询的智能路由优化方法及系统
Gupta et al. Grafenne: learning on graphs with heterogeneous and dynamic feature sets
CN117371511A (zh) 图像分类模型的训练方法、装置、设备及存储介质
CN119514647B (zh) 一种基于拓扑熵分解的深度记忆迁移学习方法
CN115168326A (zh) Hadoop大数据平台分布式能源数据清洗方法及系统
CN111026661B (zh) 一种软件易用性全面测试方法及系统
KR102248975B1 (ko) 심층 콘볼루션 신경망의 학습 방법 및 그 장치
CN119201130A (zh) 一种针对动态形状算子的编译优化方法
CN117669669A (zh) 基于数据流芯片的神经网络结构优化的方法及计算设备
CN116861373A (zh) 一种查询选择率估算方法、系统、终端设备及存储介质
CN119415554B (zh) 基于两阶段搜索的学习型查询优化器构建方法与装置
CN120409567B (zh) 数据受限场景下的Transformer自适应压缩方法与系统
CN117057409B (zh) 一种边云协同场景下的基于结构化剪枝的卷积神经网络组件化方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21741215

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21741215

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 21741215

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 28.02.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21741215

Country of ref document: EP

Kind code of ref document: A1