WO2023217263A1 - 数据处理方法、装置、设备及介质 - Google Patents

数据处理方法、装置、设备及介质 Download PDF

Info

Publication number
WO2023217263A1
WO2023217263A1 PCT/CN2023/093805 CN2023093805W WO2023217263A1 WO 2023217263 A1 WO2023217263 A1 WO 2023217263A1 CN 2023093805 W CN2023093805 W CN 2023093805W WO 2023217263 A1 WO2023217263 A1 WO 2023217263A1
Authority
WO
WIPO (PCT)
Prior art keywords
pruning
neural network
network
sub
original
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/CN2023/093805
Other languages
English (en)
French (fr)
Inventor
刘松伟
李明蹊
孔方圆
陈芳民
拜阳
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.)
Beijing Zitiao Network Technology Co Ltd
Original Assignee
Beijing Zitiao Network 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 Beijing Zitiao Network Technology Co Ltd filed Critical Beijing Zitiao Network Technology Co Ltd
Priority to US18/859,935 priority Critical patent/US20250292059A1/en
Publication of WO2023217263A1 publication Critical patent/WO2023217263A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

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
    • G06N3/04—Architecture, e.g. interconnection topology
    • 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
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • 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
    • 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
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections

Definitions

  • the present disclosure relates to the field of computer technology, and in particular, to a data processing method, device, equipment and medium.
  • intelligent mobile terminals are developing rapidly to meet people's various application needs.
  • its main implementation technology includes data processing based on trained neural network model data in video processing language recognition, image recognition and understanding, game vision and other application fields.
  • data processing based on trained neural network model data in video processing language recognition, image recognition and understanding, game vision and other application fields.
  • redundant convolution kernels or redundant convolution kernels in each layer of the neural network are removed through pruning.
  • Neuron a neural network with smaller computing resources and storage resources on mobile terminals.
  • the present disclosure provides a data processing method, device, equipment and medium.
  • Embodiments of the present disclosure provide a data processing method, which includes:
  • the candidate network layers in the original neural network are pruned separately according to multiple preset pruning rates to obtain multiple corresponding sub-neural networks
  • test data set is input into the original neural network and multiple sub-neural networks respectively for processing. Based on the output data sets of the original neural network and multiple sub-neural networks, the reference corresponding to the original neural network is obtained. Performance indicators, and multiple test performance indicators corresponding to multiple sub-neural networks;
  • the method further includes:
  • the plurality of pruning rates are set according to the network compression requirement, wherein the difference between the plurality of pruning rates is positively related to the network compression degree.
  • pruning is performed according to multiple preset pruning rates to obtain corresponding multiple sub-neural networks, including:
  • the preset first pruner is used to perform pruning processing, wherein the norm interval of the first regional distribution is greater than A preset interval threshold, and the minimum norm value of the first regional distribution is zero;
  • the preset second pruner is used to perform pruning processing, wherein the norm variance of the second regional distribution is greater than A preset variance threshold, and the minimum norm value of the second regional distribution is not zero.
  • the test data set includes: multimedia data, where the multimedia data is one or more combinations of audio data, video data, and image data.
  • test data set is input into the original neural network and multiple sub-neural networks respectively for processing, based on the output data of the original neural network and multiple sub-neural networks.
  • Set to obtain the reference performance indicators corresponding to the original neural network and multiple test performance indicators corresponding to multiple sub-neural networks including:
  • the test image data set is respectively input into the original neural network and each of the sub-neural networks for processing, and the output image data set based on the original neural network and multiple sub-neural networks is combined with the test image data set.
  • the pixel processing results between obtain the peak signal-to-noise ratio corresponding to the original neural network as the reference performance index, and each The peak signal-to-noise ratio corresponding to the sub-neural network is used as the test performance index;
  • the test audio data set is input into the original neural network and each of the sub-neural networks for processing, and the recognition text data set based on the output of the original neural network and multiple sub-neural networks is combined with the test audio data
  • the comparison results between the annotated text of the set are obtained, and the accuracy rate corresponding to the original neural network is obtained as the reference performance index, and the accuracy rate corresponding to each of the sub-neural networks is obtained as the test performance index.
  • the method further includes:
  • channel dependence characteristics include: adjacent network layers have at least one of additive data operations and multiplied data operations;
  • the method further includes:
  • the pruned target network layer in the original neural network is determined to generate a target neural network to process the target data set.
  • determining the target network layer to be pruned in the original neural network based on the parameter redundancy of the candidate network layer parameters under different pruning rates includes:
  • the target network layer to be pruned in the original neural network is determined according to the target pruning rate and the maximum pruning rate corresponding to the maximum parameter redundancy of each candidate network layer.
  • An embodiment of the present disclosure also provides a data processing device, which includes:
  • the pruning processing module is used to prune the candidate network layers in the original neural network according to multiple preset pruning rates to obtain multiple corresponding sub-neural networks;
  • a processing and acquisition module configured to input test data sets into the original neural network and multiple sub-neural networks for processing, and obtain the output data sets based on the original neural network and multiple sub-neural networks.
  • a determination module configured to analyze the parameter redundancy of the candidate network layer parameters in the original neural network under different pruning rates based on the performance loss of the multiple test performance indicators relative to the reference performance indicator.
  • An embodiment of the present disclosure also provides an electronic device, the electronic device including: a processor; a memory for storing executable instructions; wherein the executable instructions can be read from the memory by the processor, and executed to implement the data processing method provided by the embodiments of the present disclosure.
  • Embodiments of the present disclosure also provide a computer-readable storage medium, the storage medium stores a computer program, and the computer program is used to execute the data processing method provided by the embodiments of the present disclosure.
  • Embodiments of the present disclosure also provide a computer program product.
  • the computer program product includes a computer program/instruction. When the computer program/instruction is executed by a processor, the above method is implemented.
  • An embodiment of the present disclosure also provides a computer program, including: instructions, which when executed by a processor cause the processor to execute the data processing method provided by the embodiment of the present disclosure.
  • Figure 1 is a schematic flowchart of a data processing method provided by an embodiment of the present disclosure
  • Figure 2 is a schematic flow chart of another data processing method provided by an embodiment of the present disclosure.
  • Figure 3 is a schematic diagram of the relationship between pruning rate and performance indicators provided by an embodiment of the present disclosure
  • Figure 4 is a schematic diagram of another relationship between pruning rate and performance indicators provided by an embodiment of the present disclosure.
  • Figure 5 is a schematic structural diagram of a data processing device provided by an embodiment of the present disclosure.
  • FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • the term “include” and its variations are open-ended, ie, “including but not limited to.”
  • the term “based on” means “based at least in part on.”
  • the term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one additional embodiment”; and the term “some embodiments” means “at least some embodiments”. Relevant definitions of other terms will be given in the description below.
  • pruning solutions result in different network processing performance after pruning. Some pruning solutions result in poor network processing performance, resulting in unreliable results of subsequent data processing.
  • Figure 1 is a schematic flowchart of a data processing method provided by an embodiment of the present disclosure.
  • the method can be executed by a data processing device, where the device can be implemented using software and/or hardware, and can generally be integrated in electronic equipment.
  • the method includes:
  • Step 101 Perform pruning on the candidate network layers in the original neural network according to multiple preset pruning rates to obtain multiple corresponding sub-neural networks.
  • the redundant convolution kernels of each convolution layer in the neural network can be pruned while ensuring the accuracy of the neural network ( That is, structured pruning) or neurons on the convolution kernel (that is, unstructured pruning), thereby obtaining a "slim model" that takes up less computing resources and storage resources, accelerating the reasoning process of the neural network, and assisting the neural network. Deployment at the edge of the network.
  • the original neural network is a neural network model that needs to be pruned.
  • the neural network model can be obtained through training, and the neural network model can be set according to the application scenario and/or user needs, etc., This embodiment is not limiting.
  • the relative importance of all neurons in the original neural network is sorted through specific evaluation criteria, and then relatively unimportant neurons in the network are pruned according to a preset pruning rate, thereby compressing the network.
  • the candidate network layers in the original neural network are pruned according to multiple preset pruning rates to obtain multiple corresponding sub-neural networks; , the original neural network includes multiple candidate network layers.
  • the original neural network includes four convolution layers, namely convolution layer one Conv1, convolution layer two Conv2, convolution layer three Conv3 and convolution layer four Conv4. Then you can use convolution layer one Conv1, convolution layer two Conv2, convolution layer three Conv3 and convolution layer four Conv4 as candidate network layers of the original neural network, or use convolution layer one Conv1 and convolution layer two Conv2 as Candidate network layer, select settings according to application scenario needs.
  • the corresponding pruning rate is set in advance according to the importance of each candidate network layer; the pruning rate refers to the percentage of convolution kernels pruned out of the candidate network layer.
  • the pruning rate refers to the percentage of convolution kernels pruned out of the candidate network layer.
  • candidate network layer A has N convolutions. kernel, the pruning rate is p%. Therefore, candidate network layer A needs to prune N times p% convolution kernels.
  • each candidate network layer is preset with multiple different pruning rates, so that after pruning each candidate network layer according to the preset multiple different pruning rates, each candidate network layer can be obtained.
  • Multiple sub-neural networks corresponding to the candidate network layer for example, ten pruning rates are preset, and each pruning rate differs by 10%, ranging from 10%, 20%, 30% to 100%. , thereby processing the candidate network layers such as the convolutional layer Conv1 based on ten different pruning rates, so that ten sub-neural networks corresponding to the convolutional layer Conv1 can be obtained.
  • Example instructions are as follows:
  • a norm calculation is performed on the weight distribution in the candidate network layer. If it is determined according to the calculation result that the weight distribution belongs to the candidate network layer of the preset first regional distribution, then the preset first clipping is used. The brancher performs pruning processing, in which the norm interval of the first regional distribution is greater than the preset interval threshold, and the minimum norm value of the first regional distribution is zero. If it is determined according to the calculation results that the weight distribution belongs to the preset second The candidate network layer of the regional distribution is pruned using the preset second pruner, wherein the norm variance of the second regional distribution is greater than the preset variance threshold, and the minimum norm value of the second regional distribution is not is zero.
  • the relevant pruner is called according to multiple preset pruning rates to directly prune the candidate network layers of the original neural network to obtain multiple sub-neural networks.
  • Step 102 Input the test data set into the original neural network and multiple sub-neural networks respectively for processing. Based on the output data sets of the original neural network and multiple sub-neural networks, obtain the reference performance indicators corresponding to the original neural network and the corresponding sub-neural networks. Multiple test performance indicators.
  • test data set can be selected and set according to the application scenario, such as multimedia data
  • multimedia data is one or more combinations of audio data, video data, and image data.
  • the reference performance index refers to the performance value obtained by analyzing the output data set obtained after the original neural network processes the test data set
  • the test performance index refers to the test data set of the sub-neural network after pruning rate processing. The performance values obtained by analyzing the output data set obtained after processing.
  • the sub-neural networks after pruning at different pruning rates have different accuracy losses in processing the test data set, that is, different performance losses.
  • the pruning rate is 30% after pruning the candidate network layer.
  • the reference performance indicators and test performance indicators obtained by test data sets in different scenarios are different. Therefore, the test data sets are respectively input into the original neural network and multiple sub-neural networks for processing. Based on the original neural network and multiple sub-neural networks, There are many ways to obtain the output data set of the sub-neural network, the reference performance indicators corresponding to the original neural network, and the multiple test performance indicators corresponding to the multiple sub-neural networks. The selection can be based on the application scenario, etc., and this embodiment is not limited. , examples are as follows:
  • the test image number is The data sets are input into the original neural network and each sub-neural network for processing respectively. Based on the pixel processing results between the output image data set and the test image data set of the original neural network and multiple sub-neural networks, the peak signal corresponding to the original neural network is obtained.
  • the noise ratio is used as the reference performance index, and the peak signal-to-noise ratio corresponding to each sub-neural network is used as the test performance index.
  • test audio data set is input into the original neural network and each sub-neural network for processing, and the recognized text data set based on the output of the original neural network and multiple sub-neural networks is compared with Test the comparison results between the annotated texts of the audio data set, obtain the accuracy corresponding to the original neural network as the reference performance index, and obtain the accuracy corresponding to each sub-neural network as the test performance index.
  • Step 103 Analyze the parameter redundancy of the candidate network layer parameters in the original neural network under different pruning rates based on the performance losses of multiple test performance indicators relative to the reference performance indicators.
  • the multiple test performance indicators are calculated relative to the reference performance.
  • the performance loss of the indicator can be used to obtain the parameter redundancy of the candidate network layer parameters in the original neural network under different pruning rates.
  • a performance indicator curve corresponding to the candidate network layer and the multiple pruning rates is drawn, and the candidate network layer parameters at different pruning rates are analyzed based on the performance indicator curve. Parameter redundancy below.
  • the data processing solution provided by the embodiment of the present disclosure performs pruning processing on the candidate network layers in the original neural network according to multiple preset pruning rates to obtain corresponding multiple sub-neural networks, and input the test data sets respectively.
  • the original neural network and multiple sub-neural networks are processed, and based on the output data sets of the original neural network and multiple sub-neural networks, the reference performance indicators corresponding to the original neural network and multiple test performance indicators corresponding to the multiple sub-neural networks are obtained.
  • the performance loss of each test performance index relative to the reference performance index is analyzed, and the parameter redundancy of the candidate network layer parameters in the original neural network under different pruning rates is analyzed. Redundancy.
  • parameter redundancy is obtained based on the actual data set and the reliability of subsequent pruning is improved, thereby improving the high accuracy of the neural network after pruning and improving the efficiency and accuracy of data processing.
  • the pruned target network layer in the original neural network is determined based on the parameter redundancy of the candidate network layer parameters under different pruning rates, so as to generate the target neural network to process the target data set.
  • the target network layer refers to the pruned target network layer determined based on the adjusted pruning rate after re-adjusting the pruning rate of the candidate network layer according to the parameter redundancy.
  • the target neural network refers to the original pruning rate. The neural network after pruning the target network layer in the neural network.
  • the slope of The maximum pruning rate corresponding to the maximum parameter redundancy determines the target network layer to be pruned in the original neural network.
  • the maximum pruning rate of each candidate network layer is determined based on parameter redundancy, and the target network layer to be pruned in the original neural network is directly determined based on the maximum pruning rate.
  • the performance loss between the test performance indicators obtained by the sub-neural network processing the test data set obtained from different pruning rates and the reference performance indicators obtained by the original neural network processing the test data set is analyzed.
  • Parameter redundancy of the candidate network layer Redundancy thereby obtaining the relative parameter redundancy of the specified candidate network layer in the original neural network under the specified pruning rate, and the parameter redundancy is calculated based on the actual test data set, which has high reliability sex.
  • different pruners are selected for different weight distribution layers; at the same time, candidate network layers with channel dependencies are calculated comprehensively for each pruning rate.
  • Candidate network layers that should be pruned and then calculate the parameter redundancy of each candidate network layer separately, and finally use the average parameter redundancy of these layers as the parameter redundancy of all layers to achieve channel dependency-aware parameter redundancy. The remaining calculation is described in detail below in conjunction with Figure 2.
  • FIG. 2 is a schematic flowchart of another data processing method provided by an embodiment of the present disclosure. Based on the above embodiment, this embodiment further optimizes the above data processing method. As shown in Figure 2, the method includes:
  • Step 201 Obtain the network compression requirements, and set multiple pruning rates according to the network compression requirements.
  • the difference between the multiple pruning rates is positively related to the network compression degree.
  • the audio processing platform has relatively high requirements for network compression, so it is necessary to set more pruning rates for pruning attempts, which requires more accurate parameters. redundancy, thereby further improving the processing accuracy of the final target neural network;
  • the image processing platform has relatively low demand for network compression, so it is necessary to set a relatively small number of pruning rates for pruning attempts to improve the original neural network Adjust efficiency.
  • the data difference between multiple pruning rates is positively related to the network compression degree, that is to say, The greater the difference between multiple pruning rates, the greater the network compression; the smaller the difference between multiple pruning rates, the smaller the network compression.
  • Step 202 detect whether there is an associated network layer with channel dependency characteristics in the original neural network, where the channel dependence characteristics include: adjacent network layers have at least one of additive data operations and multiplied data operations, if There are associated network layers, and all associated network layers with channel-dependent characteristics are set as one candidate network layer.
  • a convolution kernel with a p% pruning rate of the nth candidate network layer is selected according to a certain convolution kernel evaluation criterion, that is, N*p% convolution kernels are pruned, and the rest of the original neural network All layers remain unchanged, and the performance of the original neural network on the test data set is B when directly tested.
  • the pruning performance loss of the nth candidate network layer under p% pruning rate is defined as S.
  • S The larger S, the better The greater the accuracy loss caused by pruning of the candidate network layer, the greater the pruning sensitivity of the candidate network layer.
  • the more sensitive the pruning is it means that the candidate network layer contains more important convolution kernels/features.
  • Figure it can be considered that the smaller the parameter redundancy of the candidate network layer, therefore, the parameter redundancy is negatively correlated with pruning sensitivity.
  • multiple performance indicators are parameter redundancies corresponding to candidate network layers and multiple pruning rates respectively, including: obtaining the number of layers of all associated network layers with channel dependency characteristics in the candidate network layer, and Multiple performance indicators are averaged over the number of layers to obtain the parameter redundancy corresponding to each associated network layer and multiple pruning rates.
  • Conv1 and Conv2 analyze the parameter redundancy of Conv1 and Conv2 at the pruning rate p%, first consider Conv1 and Conv2 comprehensively and select N*p% to be Cut off the convolution kernel, then calculate the first parameter redundancy and the second parameter redundancy based on cutting these convolution kernels in Conv1, and finally calculate the average of the first parameter redundancy and the second parameter redundancy. value as Conv1 and Parameter redundancy of Conv2 at compression rate p%.
  • Step 203 Perform norm calculation on the weight distribution in the candidate network layer. If it is determined according to the calculation result that the weight distribution belongs to the candidate network layer with the preset first regional distribution, use the preset first pruner to perform pruning processing. , wherein the norm interval of the first regional distribution is greater than the preset interval threshold, and the minimum norm value of the first regional distribution is zero.
  • Step 204 If it is determined according to the calculation results that the weight distribution belongs to the candidate network layer of the preset second regional distribution, use the preset second pruner to perform pruning processing, wherein the norm variance of the second regional distribution is greater than the preset second region distribution. Set the variance threshold, and the minimum norm value of the second regional distribution is not zero.
  • pruning strategies usually use L1 norm/L2 norm to evaluate the importance of convolution kernels.
  • Norm-based evaluation criteria usually rely on two assumptions that are not always true: (1) the range of the filter. The number distribution is wide and the variance is large; (2) The minimum norm of the filter should be very small and close to 0. Specifically, when the norm deviation of the filter is very small, that is to say, the norm distribution of the filter is very dense, then it will be more difficult to find a suitable threshold to achieve the desired target sparsity rate. At the same time, when the minimum norm of the filter is very large, it means that all filters in the candidate network layer are very important. At this time, selection based on the norm will lose accuracy.
  • the norm-based evaluation criterion is no longer applicable.
  • the weight distribution of the candidate network layer will first be analyzed before pruning, and the weight distribution conforms to the first regional distribution.
  • the preset first pruner for pruning processing that is, use the one-shot pruning algorithm with the first norm.
  • the norm of the first regional distribution is greater than the preset range and the minimum value is Zero, where the preset range is set according to the needs of the application scenario; for candidate network layers whose weight distribution conforms to the second regional distribution, the preset second pruner is used for pruning, that is, the filter through the geometric median is used to prune A one-time branch pruning algorithm, the norm variance of the second region is greater than the preset threshold and the minimum value is not zero.
  • the preset threshold is set according to the needs of the application scenario.
  • Step 205 Input the test image data set into the original neural network and each sub-neural network for processing. Based on the pixel processing results between the output image data set of the original neural network and multiple sub-neural networks and the test image data set, obtain the same result as the original neural network.
  • the peak signal-to-noise ratio corresponding to the neural network is used as the reference performance index, and the peak signal-to-noise ratio corresponding to each sub-neural network is used as the test performance index.
  • the test data set is a test image data set.
  • the test image data set is input into the original neural network and each sub-neural network respectively for processing to obtain the output image data set.
  • the peak signal-to-noise ratio corresponding to the original neural network is obtained as the reference performance index
  • the peak signal-to-noise ratio corresponding to each sub-neural network is used as the test performance index.
  • the reference performance index corresponding to the original neural network and the test performance index corresponding to the sub-neural network are used to determine the candidate network layer in the original neural network based on the performance loss of the test performance index relative to the reference performance index.
  • Step 206 The test audio data set is input into the original neural network and each sub-neural network for processing, and the comparison results between the recognized text data set output by the original neural network and multiple sub-neural networks and the annotated text of the test audio data set are compared , obtain the accuracy corresponding to the original neural network as the reference performance index, and the accuracy corresponding to each sub-neural network as the test performance index.
  • the test data set is a test audio data set.
  • the test audio data set is input into the original neural network and each sub-neural network respectively for processing to obtain a recognition text data set.
  • the corresponding accuracy rate of the original neural network is obtained as a reference performance index, and compared with each sub-neural network The corresponding accuracy rate is used as the test performance indicator.
  • the reference performance index corresponding to the original neural network and the test performance index corresponding to the sub-neural network are used to determine the candidate network layer in the original neural network based on the performance loss of the test performance index relative to the reference performance index.
  • Step 207 Draw performance index curves corresponding to candidate network layers and multiple pruning rates based on the performance losses of multiple test performance indicators relative to the reference performance indicators, calculate the slope of each pruning rate in the performance index curve, and change the slope according to the slope change Determine the maximum pruning rate of the candidate network layer, where the performance index corresponding to the maximum pruning rate represents the maximum parameter redundancy of the candidate network layer parameters.
  • Step 208 Determine the target network layer to be pruned in the original neural network based on the target pruning rate and the maximum pruning rate corresponding to the maximum parameter redundancy of each candidate network layer.
  • the performance index curve corresponding to the candidate network layer and multiple pruning rates is drawn according to the parameter redundancy, that is, multiple pruning rates are used as the abscissa, and the parameter redundancy, that is, multiple
  • the performance loss of the test performance index relative to the reference performance index is used as the ordinate to draw the performance index curve, so that the slope of each pruning rate can be obtained, and the maximum pruning rate of the candidate network layer is determined based on the slope change, such as the pruning rate when the slope change is the largest.
  • the branch rate is the maximum pruning rate of the candidate network layer, and the performance index corresponding to the maximum pruning rate indicates the maximum parameter redundancy corresponding to the candidate network layer parameters.
  • the target network layer to be pruned in the original neural network is determined according to the target pruning rate and the maximum pruning rate corresponding to the maximum parameter redundancy of each candidate network layer, so as to generate the target neural network to process the target data set.
  • the target pruning rate can also be determined based on the specific scenario, and the maximum parameter redundancy of each candidate network layer can be used to determine the pruned target network layer in the original neural network to generate
  • the target neural network processes the target data set, so that the obtained target neural network is more in line with personalized needs and further improves data processing efficiency and accuracy.
  • relevant tools can be used to Select the network layer to analyze the performance loss of the preset pruning rate.
  • the analysis principle is to perform structured pruning on the set candidate network layers with the preset pruning rate, and then test the pruned sub-neural network.
  • the data set is processed for performance verification, as the performance loss under the current pruning rate of the candidate network layer.
  • the analysis results are shown in Figure 3.
  • the performance loss of manager conv1 for the pruning rate of 0.3 is relatively large, and the parameter redundancy at this time is relatively small.
  • Another example is that individual layers are extremely insensitive to pruning. You can consider removing them in the original neural network design, or increasing their pruning rate. For example, the performance index of conv3 has almost no change when the pruning rate is 0.1-0.9. That is to say, the performance loss of conv3 is relatively small when the pruning rate is 0.1-0.9, that is, the parameter redundancy of conv3 is relatively large when the pruning rate is 0.1-0.9.
  • the attention module is used to make the original neural network focus on more important spatial features by modeling spatial dependencies, showing excellent performance.
  • Figure 4 after analyzing the parameter redundancy of the attention module, it can be seen that the parameters of the three convolutional layers c1-c3 are relatively high in parameter redundancy at each pruning rate, thus proving that it has The high parameter redundancy directly reduces the three convolutional layers c1-c3 to one convolutional layer, and finally shows no loss in performance after retraining the original neural network.
  • the data processing solution provided by the embodiment of the present disclosure obtains the network compression requirements, sets multiple pruning rates according to the network compression requirements, where the difference between the multiple pruning rates is positively related to the network compression degree, and detects whether the original neural network There is an associated network layer with channel dependency characteristics, where the channel dependency characteristics include: adjacent network layers have at least one of additive data operations and multiplied data operations. If there is an associated network layer, it will have channel dependency. All associated network layers of the feature are set as a candidate network layer, and the norm calculation is performed on the weight distribution in the candidate network layer.
  • the first pruner performs pruning processing, in which the norm interval of the first regional distribution is greater than the preset interval threshold, and the minimum norm value of the first regional distribution is zero. If it is determined according to the calculation results that the weight distribution belongs to the preset Assuming the candidate network layer of the second regional distribution, use the preset second pruner to perform pruning processing, wherein the norm variance of the second regional distribution is greater than the preset variance threshold, and the norm variance of the second regional distribution is The minimum value of the number is not zero.
  • the test image data set is input into the original neural network and each sub-neural network for processing.
  • the performance indicator curve corresponding to the candidate network layer and multiple pruning rates is drawn, and each performance indicator curve is calculated.
  • the slope of the pruning rate determines the maximum pruning rate of the candidate network layer based on the slope change.
  • the performance index corresponding to the maximum pruning rate represents the maximum parameter redundancy of the candidate network layer parameters.
  • each candidate The maximum pruning rate corresponding to the maximum parameter redundancy of the network layer determines the target network layer to be pruned in the original neural network.
  • FIG. 5 is a schematic structural diagram of a data processing device provided by an embodiment of the present disclosure.
  • the device can be implemented by software and/or hardware, and can generally be integrated in electronic equipment. As shown in Figure 5, the device includes:
  • the pruning processing module 301 is used to perform pruning processing on each candidate network layer in the original neural network according to multiple preset pruning rates to obtain corresponding multiple sub-neural networks;
  • the processing and acquisition module 302 is used to input test data sets into the original neural network and multiple sub-neural networks for processing, and obtain all the output data sets based on the original neural network and multiple sub-neural networks.
  • the analysis module 303 is configured to analyze the parameter redundancy of the candidate network layer parameters in the original neural network under different pruning rates based on the performance loss of the multiple test performance indicators relative to the reference performance indicators.
  • test data set includes: multimedia data, and the multimedia data is one or more combinations of audio data, video data, and image data.
  • the device also includes:
  • a setting module configured to set the plurality of pruning rates according to the network compression requirement, wherein the difference between the plurality of pruning rates is positively related to the network compression degree.
  • the pruning processing module 301 is specifically used to:
  • the preset first pruner is used to perform pruning processing, wherein the norm interval of the first regional distribution is greater than A preset interval threshold, and the minimum norm value of the first regional distribution is zero;
  • the preset second pruner is used to perform pruning processing, wherein the norm variance of the second regional distribution is greater than A preset variance threshold, and the minimum norm value of the second regional distribution is not zero.
  • processing acquisition module 302 is specifically used to:
  • the test image data set is input into the original neural network and each of the sub-neural networks respectively.
  • the network performs processing, and based on the pixel processing results between the output image data set of the original neural network and multiple sub-neural networks and the test image data set, a peak signal-to-noise ratio corresponding to the original neural network is obtained.
  • the reference performance index and the peak signal-to-noise ratio corresponding to each of the sub-neural networks as the test performance index;
  • the test audio data set is input into the original neural network and each of the sub-neural networks for processing, and the recognition text data set based on the output of the original neural network and multiple sub-neural networks is combined with the test audio data
  • the comparison results between the annotated text of the set are obtained, and the accuracy rate corresponding to the original neural network is obtained as the reference performance index, and the accuracy rate corresponding to each of the sub-neural networks is obtained as the test performance index.
  • the device also includes:
  • a detection module for detecting whether there is an associated network layer with channel dependency characteristics in the original neural network, wherein the channel dependence characteristics include: adjacent network layers have additive data operations and multiplied data operations. at least one of;
  • An association setting module configured to set all associated network layers with channel-dependent characteristics as one of the candidate network layers if the associated network layer exists.
  • the device also includes:
  • Obtain calculation module used to obtain the number of layers of all associated network layers with channel dependency characteristics in the candidate network layer, average the multiple performance indicators for the number of layers, and obtain the relationship between each associated network layer and multiple The pruning rate corresponds to the parameter redundancy respectively.
  • the device also includes a determining module for:
  • the pruned target network layer in the original neural network is determined to generate a target neural network to process the target data set.
  • the determination module is specifically used for:
  • the target network layer to be pruned in the original neural network is determined according to the target pruning rate and the maximum pruning rate corresponding to the maximum parameter redundancy of each candidate network layer.
  • the data processing device provided by the embodiments of the present disclosure can execute the data processing method provided by any embodiment of the present disclosure, and has functional modules and beneficial effects corresponding to the execution method.
  • the data processing solution provided by the embodiment of the present disclosure prunes the candidate network layers in the original neural network respectively according to multiple preset pruning rates.
  • Process to obtain the corresponding multiple sub-neural networks input the test data set into the original neural network and multiple sub-neural networks for processing, and obtain the reference performance corresponding to the original neural network based on the output data sets of the original neural network and multiple sub-neural networks indicators, as well as multiple test performance indicators corresponding to multiple sub-neural networks.
  • Based on the performance loss of multiple test performance indicators relative to the reference performance indicators analyze the parameter redundancy of candidate network layer parameters in the original neural network under different pruning rates.
  • Spend Using the above technical solution, parameter redundancy is obtained based on the actual test data set, and the reliability of subsequent pruning is improved, thereby improving the high accuracy of the neural network after pruning and improving the efficiency and accuracy of data processing.
  • An embodiment of the present disclosure also provides a computer program product, which includes a computer program/instruction.
  • a computer program product which includes a computer program/instruction.
  • FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • the electronic device 400 in the embodiment of the present disclosure may include, but is not limited to, mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals ( Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc.
  • the electronic device shown in FIG. 6 is only an example and should not be used in connection with the embodiments of the present disclosure. any limitations on its functions and scope of use.
  • the electronic device 400 may include a processing device (eg, central processing unit, graphics processor, etc.) 401 , which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 402 or from a storage device 408 .
  • the program in the memory (RAM) 403 executes various appropriate actions and processes.
  • various programs and data required for the operation of the electronic device 400 are also stored.
  • the processing device 401, ROM 402 and RAM 403 are connected to each other via a bus 404.
  • An input/output (I/O) interface 405 is also connected to bus 404.
  • the following devices may be connected to the I/O interface 405: input devices 406 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration An output device 407 such as a computer; a storage device 408 including a magnetic tape, a hard disk, etc.; and a communication device 409.
  • the communication device 409 may allow the electronic device 400 to communicate wirelessly or wiredly with other devices to exchange data.
  • FIG. 6 illustrates electronic device 400 with various means, it should be understood that implementation or availability of all illustrated means is not required. More or fewer means may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product including a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via communication device 409, or from storage device 408, or from ROM 402.
  • the processing device 401 When the computer program is executed by the processing device 401, the above-mentioned functions defined in the data processing method of the embodiment of the present disclosure are performed.
  • the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
  • the computer-readable storage medium may be, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof.
  • computer More specific examples of readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable Read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device .
  • Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wire, optical cable, RF (radio frequency), etc., or any suitable combination of the above.
  • the client and server can communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and can communicate with digital data in any form or medium.
  • Data communications e.g., communications network
  • communications networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or developed in the future network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; it may also exist independently without being assembled into the electronic device.
  • the computer-readable medium carries one or more programs.
  • the electronic device receives the user's information display triggering operation during the playback of the video; obtains the At least two target information associated with the video; display the first target information among the at least two target information in the information display area of the playback page of the video, wherein the size of the information display area is smaller than the Play the size of the page; receive the user's first switching trigger operation, and switch the first target information displayed in the information display area to the second target information among the at least two target information.
  • Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and Includes conventional procedural programming languages—such as "C” or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as an Internet service provider through Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider such as an Internet service provider through Internet connection
  • each block in the flowchart or block diagram may represent a module, segment, or portion of code that contains one or more logic functions that implement the specified executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved.
  • each block of the block diagram and/or flowchart illustration, and combinations of blocks in the block diagram and/or flowchart illustration can be implemented by special purpose hardware-based systems that perform the specified functions or operations. , or can be implemented using a combination of specialized hardware and computer instructions.
  • the units involved in the embodiments of the present disclosure can be implemented in software or hardware. Among them, the name of a unit does not constitute a limitation on the unit itself under certain circumstances.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs Systems on Chips
  • CPLD Complex Programmable Logical device
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, laptop disks, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM portable compact disk read-only memory
  • magnetic storage device or any suitable combination of the above.
  • the present disclosure provides an electronic device, including:
  • Memory used to store executable instructions
  • the executable instructions can be read from the memory by the processor and executed to implement any of the data processing methods provided by this disclosure.
  • the present disclosure provides a computer-readable storage medium, the storage medium stores a computer program, the computer program is used to execute any of the data provided by the present disclosure Approach.
  • the present disclosure provides a computer program, including: instructions that, when executed by a processor, cause the processor to execute any of the data provided by the present disclosure. Approach.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Stored Programmes (AREA)

Abstract

本公开实施例涉及一种数据处理方法、装置、设备及介质，其中该方法包括：对原始神经网络中的候选网络层，按照预设的多个剪枝率分别进行剪枝处理，以获取对应的多个子神经网络，将测试数据集分别输入原始神经网络和多个子神经网络进行处理，基于原始神经网络和多个子神经网络的输出数据集，获取原始神经网络对应的参考性能指标，以及多个子神经网络对应的多个测试性能指标，根据多个测试性能指标相对于参考性能指标的性能损失，分析原始神经网络中的候选网络层参数在不同剪枝率下的参数冗余度。

Description

数据处理方法、装置、设备及介质
本申请以申请号为202210524932.0，申请日为2022年5月13日的中国申请为基础，并主张其优先权，该中国申请的公开内容在此作为整体引入本申请中。
技术领域
本公开涉及计算机技术领域，尤其涉及一种数据处理方法、装置、设备及介质。
背景技术
基于神经网络的人工智能技术在移动终端上的应用，智能移动终端飞速发展满足人们的各种应用需求。其中，其主要实现技术包括基于训练好的神经网络模型数据在视频处理语言识别、图像识别与理解、游戏视觉等应用领域的数据处理。基于移动终端有限的计算资源，考虑到绝大多数的卷积神经网络均存在一定程度上的参数冗余，因此通过剪枝去除神经网络中各层冗余的卷积内核或卷积内核上的神经元，在移动终端上得到计算资源和存储资源更小的神经网络。
发明内容
为了解决上述技术问题或者至少部分地解决上述技术问题，本公开提供了一种数据处理方法、装置、设备及介质。
本公开实施例提供了一种数据处理方法，所述方法包括：
对原始神经网络中的候选网络层，按照预设的多个剪枝率分别进行剪枝处理，以获取对应的多个子神经网络；
将测试数据集分别输入所述原始神经网络和多个所述子神经网络进行处理，基于所述原始神经网络和多个所述子神经网络的输出数据集，获取所述原始神经网络对应的参考性能指标，以及多个所述子神经网络对应的多个测试性能指标；
根据所述多个测试性能指标相对于所述参考性能指标的性能损 失，分析所述原始神经网络中的候选网络层参数在不同剪枝率下的参数冗余度。
一种可选的实施方式中，所述的方法，还包括：
获取网络压缩需求；
根据所述网络压缩需求设置所述多个剪枝率，其中，所述多个剪枝率之间的差异与网络压缩度正相关。
一种可选的实施方式中，所述按照预设的多个剪枝率分别进行剪枝处理，以获取对应的多个子神经网络，包括：
对所述候选网络层中的权重分布进行范数计算；
如果根据计算结果确定所述权重分布属于预设的第一区域分布的候选网络层，则使用预设的第一剪枝器进行剪枝处理，其中，所述第一区域分布的范数区间大于预设的区间阈值，且所述第一区域分布的范数最小值为零；
如果根据计算结果确定所述权重分布属于预设的第二区域分布的候选网络层，则使用预设的第二剪枝器进行剪枝处理，其中，所述第二区域分布的范数方差大于预设的方差阈值，且所述第二区域分布的范数最小值不为零。
一种可选的实施方式中，所述测试数据集包括：多媒体数据，其中，所述多媒体数据为音频数据、视频数据、图像数据中的一种或者多种组合。
一种可选的实施方式中，所述将测试数据集分别输入所述原始神经网络和多个所述子神经网络进行处理，基于所述原始神经网络和多个所述子神经网络的输出数据集，获取所述原始神经网络对应的参考性能指标，以及多个所述子神经网络对应的多个测试性能指标，包括：
将测试图像数据集分别输入所述原始神经网络和每个所述子神经网络进行处理，基于所述原始神经网络和多个所述子神经网络的输出图像数据集与所述测试图像数据集之间的像素处理结果，获取与所述原始神经网络对应的峰值信噪比作为所述参考性能指标，以及与每个 所述子神经网络对应的峰值信噪比作为所述测试性能指标；
或者，
将测试音频数据集分别输入所述原始神经网络和每个所述子神经网络进行处理，基于所述原始神经网络和多个所述子神经网络的输出的识别文字数据集与所述测试音频数据集的标注文字之间的对比结果，获取与所述原始神经网络对应的准确率作为所述参考性能指标，以及与每个所述子神经网络对应的准确率作为所述测试性能指标。
一种可选的实施方式中，所述的方法，还包括：
检测所述原始神经网络中是否存在具有通道依赖特征的关联网络层，其中，所述通道依赖特征包括：相邻的网络层具有相加的数据操作和相乘的数据操作中的至少一种；
如果存在所述关联网络层，将所述具有通道依赖特征的所有关联网络层设置为一个所述候选网络层。
一种可选的实施方式中，所述方法，还包括：
根据所述候选网络层参数在不同剪枝率下的参数冗余度，确定所述原始神经网络中被剪枝的目标网络层，以生成目标神经网络对目标数据集进行处理。
一种可选的实施方式中，所述根据所述候选网络层参数在不同剪枝率下的参数冗余度，确定所述原始神经网络中被剪枝的目标网络层，包括：
根据所述多个测试性能指标相对于所述参考性能指标的性能损失，绘制所述候选网络层与所述多个剪枝率对应的性能指标曲线；
计算所述性能指标曲线中每个剪枝率的斜率，根据斜率变化确定所述候选网络层的最大剪枝率，其中，所述最大剪枝率对应的性能指标表示所述候选网络层参数的最大参数冗余度；
根据目标剪枝率、每个所述候选网络层的所述最大参数冗余度对应的所述最大剪枝率，确定所述原始神经网络中被剪枝的目标网络层。
本公开实施例还提供了一种数据处理装置，所述装置包括：
剪枝处理模块，用于对原始神经网络中的候选网络层，按照预设的多个剪枝率分别进行剪枝处理，以获取对应的多个子神经网络；
处理获取模块，用于将测试数据集分别输入所述原始神经网络和多个所述子神经网络进行处理，基于所述原始神经网络和多个所述子神经网络的输出数据集，获取所述原始神经网络对应的参考性能指标，以及多个所述子神经网络对应的多个测试性能指标；
确定模块，用于根据所述多个测试性能指标相对于所述参考性能指标的性能损失，分析所述原始神经网络中的候选网络层参数在不同剪枝率下的参数冗余度。
本公开实施例还提供了一种电子设备，所述电子设备包括：处理器；用于存储可执行指令的存储器；其中所述可执行指令能够由所述处理器从所述存储器中读取，并执行以实现如本公开实施例提供的数据处理方法。
本公开实施例还提供了一种计算机可读存储介质，所述存储介质存储有计算机程序，所述计算机程序用于执行如本公开实施例提供的数据处理方法。
本公开实施例还提供了一种计算机程序产品，所述计算机程序产品包括计算机程序/指令，所述计算机程序/指令被处理器执行时实现上述的方法。
本公开实施例还提供了一种计算机程序，包括：指令，所述指令当由处理器执行时使所述处理器执行如本公开实施例提供的数据处理方法。
附图说明
结合附图并参考以下具体实施方式，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，原件和元素不一定按照比例绘制。
图1为本公开实施例提供的一种数据处理方法的流程示意图；
图2为本公开实施例提供的另一种数据处理方法的流程示意图；
图3为本公开实施例提供的一种剪枝率和性能指标关系的示意图；
图4为本公开实施例提供的另一种剪枝率和性能指标关系的示意图；
图5为本公开实施例提供的一种数据处理装置的结构示意图；
图6为本公开实施例提供的一种电子设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例，相反提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。
本文使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出， 否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
相关技术中，剪枝方案使得剪枝后的网络处理性能不同，有的剪枝方案导致的网络处理性能比较差，从而导致后续数据处理的结果不可靠。
图1为本公开实施例提供的一种数据处理方法的流程示意图，该方法可以由数据处理装置执行，其中该装置可以采用软件和/或硬件实现，一般可集成在电子设备中。如图1所示，该方法包括：
步骤101、对原始神经网络中的候选网络层，按照预设的多个剪枝率分别进行剪枝处理，以获取对应的多个子神经网络。
为了保证模型效果，在神经网络中可能存在一定数量的参数冗余，通过剪枝处理，能够在保证神经网络精度的前提下，剪枝掉神经网络中各卷积层冗余的卷积内核(即，结构化剪枝)或卷积内核上的神经元(即，非结构化剪枝)，从而得到计算资源和存储资源占用更小的"瘦身模型"，加速神经网络的推理过程，助力神经网络的边缘部署。
然而，不同的剪枝方案使得剪枝后的网络处理性能不同，有的剪枝方案所导致的网络处理性能比较差，从而导致数据处理的结果不可靠。
在本实施例中，原始神经网络为需要进行剪枝处理的神经网络模型，该神经网络模型可以是经过训练获得的，并且该神经网络模型可以根据应用场景和/或用户需求等进行设定，本实施例不作限制。
在本公开实施例中，通过特定的评估准则对原始神经网络中的所有神经元的相对重要性进行排序，然后根据预设的剪枝率剪掉网络中相对不重要的神经元，从而压缩网络模型。
在本公开实施例中，对原始神经网络中的候选网络层，按照预设的多个剪枝率分别进行剪枝处理，以获取对应的多个子神经网络；其 中，原始神经网络包括多个候选网络层，比如原始神经网络中包括四个卷积层，分别为卷积层一Conv1，卷积层二Conv2、卷积层三Conv3和卷积层四Conv4，则可以将卷积层一Conv1，卷积层二Conv2、卷积层三Conv3和卷积层四Conv4都作为原始神经网络的候选网络层，或者将卷积层一Conv1和卷积层二Conv2作为候选网络层，具体根据应用场景需要选择设置。
其中，预先根据每个候选网络层的重要性设置对应的剪枝率；剪枝率指的是候选网络层剪掉的卷积核的百分之比，比如候选网络层A具有N个卷积核，剪枝率为p％，因此，候选网络层A需要将N乘以p％个卷积核剪掉。
在本公开实施例中，每个候选网络层预先设置多个不同的剪枝率，从而按照预先设置多个不同的剪枝率分别对每个候选网络层进行剪枝处理后，可以得到每个候选网络层对应的多个子神经网络，比如预先设置十个剪枝率，每个剪枝率相差百分之十，分别为百分之十、百分之二十、百分之三十直到百分之百，从而基于十个不同的剪枝率分别对候选网络层比如卷积层一Conv1进行处理，从而可以得到卷积层一Conv1对应的十个子神经网络。
在本公开实施例中，按照预设的多个剪枝率分别进行剪枝处理以获取对应的多个子神经网络的方式有多种，可以根据应用场景等进行选择，本实施例不做限制，示例说明如下：
一种可选的实施方式中，对候选网络层中的权重分布进行范数计算，如果根据计算结果确定权重分布属于预设的第一区域分布的候选网络层，则使用预设的第一剪枝器进行剪枝处理，其中，第一区域分布的范数区间大于预设的区间阈值，且第一区域分布的范数最小值为零，如果根据计算结果确定权重分布属于预设的第二区域分布的候选网络层，则使用预设的第二剪枝器进行剪枝处理，其中，第二区域分布的范数方差大于预设的方差阈值，且第二区域分布的范数最小值不为零。
另一种可选的实施方式中，根据预设的多个剪枝率调用相关剪枝器直接对原始神经网络的候选网络层进行剪枝处理，得到多个子神经网络。
需要说明的是，每次针对一个候选网络层按照预设的一个剪枝率进行处理，其他候选网络层不变，得到一个子神经网络。
步骤102、将测试数据集分别输入原始神经网络和多个子神经网络进行处理，基于原始神经网络和多个子神经网络的输出数据集，获取原始神经网络对应的参考性能指标，以及多个子神经网络对应的多个测试性能指标。
在本公开实施例中，测试数据集可以根据应用场景选择设置，比如为多媒体数据，多媒体数据为音频数据、视频数据、图像数据中的一种或者多种组合。
其中，参考性能指标指的是原始神经网络对测试数据集进行处理后得到的输出数据集进行分析得到的性能数值，测试性能指标指的是经过剪枝率处理后的子神经网络对测试数据集进行处理后得到的输出数据集进行分析得到的性能数值。
具体地，在不同剪枝率剪枝处理后的子神经网络对测试数据集进行处理损失的精度不同，即性能损失不同，比如剪枝率为百分之三十对候选网络层剪枝处理后的子神经网络对测试数据集进行处理损失的精度越大，即性能损失越大，表示候选网络层在剪枝率百分之三十时的参数冗余度比较小。
在本公开实施例中，不同场景的测试数据集，得到的参考性能指标和测试性能指标不同，因此，将测试数据集分别输入原始神经网络和多个子神经网络进行处理，基于原始神经网络和多个子神经网络的输出数据集，获取原始神经网络对应的参考性能指标，以及多个子神经网络对应的多个测试性能指标的方式有多种，可以根据应用场景等进行选择，本实施例不做限制，示例说明如下：
一种可选的实施方式中，比如画面质量增强场景，将测试图像数 据集分别输入原始神经网络和每个子神经网络进行处理，基于原始神经网络和多个子神经网络的输出图像数据集与测试图像数据集之间的像素处理结果，获取与原始神经网络对应的峰值信噪比作为参考性能指标，以及与每个子神经网络对应的峰值信噪比作为测试性能指标。
另一种可选的实施方式中，比如语音识别场景，将测试音频数据集分别输入原始神经网络和每个子神经网络进行处理，基于原始神经网络和多个子神经网络的输出的识别文字数据集与测试音频数据集的标注文字之间的对比结果，获取与原始神经网络对应的准确率作为参考性能指标，以及与每个子神经网络对应的准确率作为测试性能指标。
步骤103，根据多个测试性能指标相对于参考性能指标的性能损失，分析原始神经网络中的候选网络层参数在不同剪枝率下的参数冗余度。
在本公开实施例中，针对每个候选网络层，设置多少不同的剪枝率得到多少个子神经网络，多少个子神经网络对应多少个测试性能指标，因此，计算多个测试性能指标相对于参考性能指标的性能损失，可以得到原始神经网络中的候选网络层参数在不同剪枝率下的参数冗余度。
具体地，根据多个测试性能指标相对于参考性能指标的性能损失，绘制候选网络层与所述多个剪枝率对应的性能指标曲线，基于性能指标曲线分析候选网络层参数在不同剪枝率下的参数冗余度。
本公开实施例提供的数据处理方案，对原始神经网络中的候选网络层，按照预设的多个剪枝率分别进行剪枝处理，以获取对应的多个子神经网络，将测试数据集分别输入原始神经网络和多个子神经网络进行处理，基于原始神经网络和多个子神经网络的输出数据集，获取原始神经网络对应的参考性能指标，以及多个子神经网络对应的多个测试性能指标，根据多个测试性能指标相对于参考性能指标的性能损失，分析原始神经网络中的候选网络层参数在不同剪枝率下的参数冗 余度。采用上述技术方案，基于实际的数据集获取参数冗余度，提高后续剪枝的可靠性，从而提高剪枝之后神经网络的高精度，提高数据处理的效率和精确性。
在一些实施例中，根据候选网络层参数在不同剪枝率下的参数冗余度，确定原始神经网络中被剪枝的目标网络层，以生成目标神经网络对目标数据集进行处理。
其中，目标网络层指的是根据参数冗余度重新调整候选网络层的剪枝率后，并基于调整后的剪枝率确定的被剪枝的目标网络层，目标神经网络指的是针对原始神经网络中的目标网络层剪掉后的神经网络。
在本公开实施例中，根据候选网络层参数在不同剪枝率下的参数冗余度，确定原始神经网络中被剪枝的目标网络层的方式有多种，可以根据应用场景等进行选择，本实施例不做限制，示例说明如下：
一种可选的实施方式中，根据多个测试性能指标相对于参考性能指标的性能损失，绘制候选网络层与多个剪枝率对应的性能指标曲线，计算性能指标曲线中每个剪枝率的斜率，根据斜率变化确定候选网络层的最大剪枝率，其中，最大剪枝率对应的性能指标表示候选网络层参数的最大参数冗余度，根据目标剪枝率、每个候选网络层的最大参数冗余度对应的最大剪枝率，确定原始神经网络中被剪枝的目标网络层。
另一种可选的实施方式中，根据参数冗余度确定每个候选网络层的最大剪枝率，直接根据最大剪枝率确定原始神经网络中被剪枝的目标网络层。
基于上述实施例的描述，不同的应用场景对于网络具有不同压缩需求，从而剪枝率不同，并且需要针对候选网络层进行不同剪枝率的剪枝尝试，以剪枝之后的测试数据集的准确率作为候选网络层在不同剪枝率下的参数冗余度，因此需要不同的范数准则进行评估选择不同的剪枝器进行剪枝处理，以及原始神经网络中不同候选网络层之间通 道数量可能存在依赖关系，存在通道依赖关系的不同候选网络层的剪枝需要关联以进一步提高处理效率。
本公开实施例，从不同剪枝率得到子神经网络对测试数据集处理得到的测试性能指标和原始神经网络对测试数据集处理得到的参考性能指标之间的性能损失分析候选网络层的参数冗余度，从而得到原始神经网络中指定的候选网络层在指定的剪枝率下的相对参数冗余度，并且该参数冗余度是基于实际的测试数据集计算得到的，具有较高的可靠性。此外，在参数冗余度的求解过程中，为了进一步提高可靠性，针对不同的权重分布层选择不同的剪枝器；同时针对具有通道依赖关系的候选网络层针对每一个剪枝率综合考虑计算应该剪枝的候选网络层，然后再分别计算每个候选网络层的参数冗余度，最后以这些层的参数冗余度平均值作为所有层的参数冗余度，实现通道依赖感知的参数冗余计算，下面结合图2进行详细描述。
具体地，图2为本公开实施例提供的另一种数据处理方法的流程示意图，本实施例在上述实施例的基础上，进一步优化了上述数据处理方法。如图2所示，该方法包括：
步骤201、获取网络压缩需求，根据网络压缩需求设置多个剪枝率，其中，多个剪枝率之间的差异与网络压缩度正相关。
具体地，在参数冗余度分析过程中，需要针对候选网络层进行不同的剪枝率的剪枝尝试，以剪枝之后的测试数据集准确率作为候选网络层在不同剪枝率下的参数冗余度。
在本公开实施例中，不同的应用场景对于网络压缩需求不同，比如音频处理平台对于网络压缩需求比较高，从而需要设置更多个数的剪枝率进行剪枝尝试，以需要更加精确的参数冗余度，从而进一步提高最终获取目标神经网络的处理精度；再比如图像处理平台对于网络压缩需求相对比较低，从而需要设置相对少个数的剪枝率进行剪枝尝试，以提高原始神经网络调整效率。
其中，多个剪枝率之间的数据差与网络压缩度正相关，也就是说， 多个剪枝率之间的差异越大，网络压缩度越大；多个剪枝率之间的差异越小，网络压缩度越小。
步骤202，检测原始神经网络中是否存在具有通道依赖特征的关联网络层，其中，通道依赖特征包括：相邻的网络层具有相加的数据操作和相乘的数据操作中的至少一种，如果存在关联网络层，将具有通道依赖特征的所有关联网络层设置为一个候选网络层。
具体地，由于原始神经网络中候选网络层之间通道数量可能存在依赖关系，具有通道依赖特征的关联网络层的剪枝需要对齐进行才能取得实际的加速效果，因此，在分析关联网络层的剪枝敏感性的时候应该将所有关联网络层设置为一个候选网络层，因此具有通道依赖特征的关联网络层具有相同的参数冗余度。
在本公开实施例中，根据某种卷积核评估准则选取第n候选网络层的剪枝率为p％的卷积核，即N*p％个卷积核剪掉，该原始神经网络其余所有的层保持不变，直接测试此时原始神经网络在测试数据集上的性能为B，定义第n候选网络层在p％剪枝率下的剪枝性能损失为S，S越大表示对该候选网络层进行剪枝造成的精度损失越大，该候选网络层的剪枝敏感性越大，剪枝越敏感就意味着该候选网络层包含了比较多的较为重要的卷积核/特征图，因此可以认为该候选网络层的参数冗余度越小，因此，参数冗余度与剪枝敏感性呈负相关的关系。
在本公开实施例中，多个性能指标为候选网络层与多个剪枝率分别对应的参数冗余度，包括：获取候选网络层中具有通道依赖特征的所有关联网络层的层数，将多个性能指标对层数取平均，获取每个关联网络层与多个剪枝率分别对应的参数冗余度。
举例而言，假设现在存在具有通道依赖特征的两个层Conv1和Conv2，分析Conv1和Conv2在剪枝率p％情况下的参数冗余度，首先综合考虑Conv1和Conv2选取N*p％个待剪掉的卷积核，然后根据在Conv1中剪掉这些卷积核计算第一参数冗余度和第二参数冗余度，最后计算第一参数冗余度和第二参数冗余度的平均值作为Conv1和 Conv2在压缩率为p％时的参数冗余度。
步骤203，对候选网络层中的权重分布进行范数计算，如果根据计算结果确定权重分布属于预设的第一区域分布的候选网络层，则使用预设的第一剪枝器进行剪枝处理，其中，第一区域分布的范数区间大于预设的区间阈值，且第一区域分布的范数最小值为零。
步骤204，如果根据计算结果确定权重分布属于预设的第二区域分布的候选网络层，则使用预设的第二剪枝器进行剪枝处理，其中，第二区域分布的范数方差大于预设的方差阈值，且第二区域分布的范数最小值不为零。
具体地，在进行参数冗余度分析过程中，需要针对候选网络层进行不同剪枝率的剪枝尝试，以剪枝之后的测试数据集的准确率作为候选网络层在不同剪枝率下的参数冗余度。因此剪枝性能直接影响不同剪枝率的可信度。
具体地，剪枝策略通常使用L1范数/L2范数来评估卷积核的重要性，基于范数的评估准则通常依赖于两个并不总是成立的假设：(1)滤波器的范数分布广，方差大；(2)滤波器的最小范数应该很小，逼近于0。具体地，当滤波器的范数偏差很小的时候，也就是说滤波器的范数分布非常密集，那么将会比较难找到一个合适的阈值来达到想要的目标稀疏率。同时当滤波器的最小范数很大的时候，表示该候选网络层的所有的滤波器都非常重要，此时再基于范数进行选择便会丧失准确性。
因此，在上述两种情况下，基于范数的评估准则变得不再适用，本公开实施例中，在剪枝之前会首先分析候选网络层的权重分布，针对权重分布符合第一区域分布的候选网络层，使用预设的第一剪枝器进行剪枝处理，即采用第一范数的一次性(one shot)剪枝算法，第一区域分布的范数大于预设范围且最小值为零，其中，预设范围根据应用场景需要设置；针对权重分布符合第二区域分布的候选网络层，使用预设的第二剪枝器进行剪枝处理，即采用通过几何中值的过滤器剪 枝的一次性剪枝算法，第二区域的范数方差大于预设阈值且最小值不为零。其中，预设阈值根据应用场景需要设置。
步骤205、将测试图像数据集分别输入原始神经网络和每个子神经网络进行处理，基于原始神经网络和多个子神经网络的输出图像数据集与测试图像数据集之间的像素处理结果，获取与原始神经网络对应的峰值信噪比作为参考性能指标，以及与每个子神经网络对应的峰值信噪比作为测试性能指标。
在本公开实施例中，针对画面增强场景，需要对图像进行增强处理，测试数据集为测试图像数据集，将测试图像数据集分别输入原始神经网络和每个子神经网络进行处理获取输出图像数据集，通过输出图像数据集与测试图像数据集之间的像素处理结果，获取与原始神经网络对应的峰值信噪比作为参考性能指标，以及与每个子神经网络对应的峰值信噪比作为测试性能指标。
由此，在画面增强场景中，原始神经网络对应的参考性能指标，以及子神经网络对应的测试性能指标，从而基于测试性能指标相对于参考性能指标的性能损失确定原始神经网络中的候选网络层参数在不同剪枝率下的参数冗余度，从而基于该参数冗余度进行剪枝后的网络进行图像增强处理的具有更好处理效率和效果。
步骤206，将测试音频数据集分别输入原始神经网络和每个子神经网络进行处理，基于原始神经网络和多个子神经网络的输出的识别文字数据集与测试音频数据集的标注文字之间的对比结果，获取与原始神经网络对应的准确率作为参考性能指标，以及与每个子神经网络对应的准确率作为测试性能指标。
在本公开实施例中，针对语音识别场景，需要对语音进行识别处理，测试数据集为测试音频数据集，将测试音频数据集分别输入原始神经网络和每个子神经网络进行处理获取识别文字数据集，通过识别文字数据集与测试音频数据集的标注文字之间的对比结果，获取原始神经网络对应的准确率作为参考性能指标，以及与每个子神经网络对 应的准确率作为测试性能指标。
由此，在语音识别场景中，原始神经网络对应的参考性能指标，以及子神经网络对应的测试性能指标，从而基于测试性能指标相对于参考性能指标的性能损失确定原始神经网络中的候选网络层参数在不同剪枝率下的参数冗余度，从而基于该参数冗余度进行剪枝后的网络进行语音识别处理的具有更好处理效率和效果。
步骤207，根据多个测试性能指标相对于参考性能指标的性能损失，绘制候选网络层与多个剪枝率对应的性能指标曲线，计算性能指标曲线中每个剪枝率的斜率，根据斜率变化确定候选网络层的最大剪枝率，其中，最大剪枝率对应的性能指标表示候选网络层参数的最大参数冗余度。
步骤208，根据目标剪枝率、每个候选网络层的最大参数冗余度对应的最大剪枝率，确定原始神经网络中被剪枝的目标网络层。
在本公开实施例中，根据参数冗余度绘制候选网络层与多个剪枝率对应的性能指标曲线，也就是说，将多个剪枝率作为横坐标，参数冗余度，即多个测试性能指标相对于参考性能指标的性能损失作为纵坐标绘制性能指标曲线，从而可以得到每个剪枝率的斜率，根据斜率变化确定候选网络层的最大剪枝率，比如斜率变化最大时的剪枝率为候选网络层的最大剪枝率，最大剪枝率对应的性能指标表示候选网络层参数对应的最大参数冗余度。
进一步地，根据目标剪枝率、每个候选网络层的最大参数冗余度对应的最大剪枝率确定原始神经网络中被剪枝的目标网络层，以生成目标神经网络对目标数据集进行处理，也就是说，在确定最大剪枝率后还可以基于具体场景确定目标剪枝率，以及每个候选网络层的最大参数冗余度确定原始神经网络中被剪枝的目标网络层，以生成目标神经网络对目标数据集进行处理，从而获取的目标神经网络更符合个性化需求，进一步提高数据处理效率和精度。
作为一种场景举例，可使用相关工具对原始神经网络的指定的候 选网络层进行预设的剪枝率的性能损失分析，分析原理是分别对设定的候选网络层进行预设的剪枝率的结构化剪枝，然后将剪枝后的子神经网络对测试数据集处理以进行性能验证，作为该候选网络层当前剪枝率下的性能损失，分析结果如图3所示，各候选网络层之间的剪枝性能损失存在较大的差异，对于一些关键的候选网络层，比如conv1和conv2分别在剪枝率为0.2和0.3时，性能损失比较多，即conv1对剪枝率为0.2的性能损失比较大，此时的参数冗余度比较小，同理conv1对剪枝率为0.3的性能损失比较大，此时的参数冗余度比较小。
再比如个别层对剪枝处理极不敏感，可以考虑在原始神经网络设计中将其去除，或者增大其剪枝率，比如conv3在剪枝率为0.1-0.9对应的性能指标几乎没有变化，即conv3对剪枝率为0.1-0.9的性能损失都比较小，即conv3在剪枝率为0.1-0.9的参数冗余度都比较大。
作为另一种场景举例，采用注意力模块通过建模空间依赖关系使原始神经网络关注更为重要的空间特征，显示优异的性能。如图4所示，分析了注意力模块的参数冗余度，可以看到三个卷积层c1-c3的参数在各个剪枝率下的参数冗余度都比较靠前，因此证明其具有较高的参数冗余度，直接将三个卷积层c1-c3减少为一个卷积层，最后重新训练原始神经网络后显示性能无损。
本公开实施例提供的数据处理方案，获取网络压缩需求，根据网络压缩需求设置多个剪枝率，其中，多个剪枝率之间的差异与网络压缩度正相关，检测原始神经网络中是否存在具有通道依赖特征的关联网络层，其中，通道依赖特征包括：相邻的网络层具有相加的数据操作和相乘的数据操作中的至少一种，如果存在关联网络层，将具有通道依赖特征的所有关联网络层设置为一个候选网络层，对候选网络层中的权重分布进行范数计算，如果根据计算结果确定权重分布属于预设的第一区域分布的候选网络层，则使用预设的第一剪枝器进行剪枝处理，其中，第一区域分布的范数区间大于预设的区间阈值，且第一区域分布的范数最小值为零，如果根据计算结果确定权重分布属于预 设的第二区域分布的候选网络层，则使用预设的第二剪枝器进行剪枝处理，其中，第二区域分布的范数方差大于预设的方差阈值，且第二区域分布的范数最小值不为零，将测试图像数据集分别输入原始神经网络和每个子神经网络进行处理，基于原始神经网络和多个子神经网络的输出图像数据集与测试图像数据集之间的像素处理结果，获取与原始神经网络对应的峰值信噪比作为参考性能指标，以及与每个子神经网络对应的峰值信噪比作为测试性能指标，或将测试音频数据集分别输入原始神经网络和每个子神经网络进行处理，基于原始神经网络和多个子神经网络的输出的识别文字数据集与测试音频数据集的标注文字之间的对比结果，获取与原始神经网络对应的准确率作为参考性能指标，以及与每个子神经网络对应的准确率作为测试性能指标，根据多个测试性能指标相对于参考性能指标的性能损失，绘制候选网络层与多个剪枝率对应的性能指标曲线，计算性能指标曲线中每个剪枝率的斜率，根据斜率变化确定候选网络层的最大剪枝率，其中，最大剪枝率对应的性能指标表示候选网络层参数的最大参数冗余度，根据目标剪枝率、每个候选网络层的最大参数冗余度对应的最大剪枝率，确定原始神经网络中被剪枝的目标网络层。采用上述技术方案，分析原始神经网络中每个候选网络层在指定的剪枝率下的相对参数冗余度，并且该参数冗余度是基于实际的测试数据集获取的，具有较高的可靠性，此外，在参数冗余度的求解过程中，为了进一步提高可靠性，针对候选网络层中的权重分布选择不同的剪枝器进行剪枝处理，同时将具有通道依赖特征的所有关联网络层设置为一个候选网络层，以及根据所有关联网络层的层数平均计算获取每个关联网络层与多个剪枝率分别对应的参数冗余度，进一步提高后续计算的精确度，从而提高目标神经网络的可靠性。
图5为本公开实施例提供的一种数据处理装置的结构示意图，该装置可由软件和/或硬件实现，一般可集成在电子设备中。如图5所示，该装置包括：
剪枝处理模块301，用于对原始神经网络中的每个候选网络层，按照预设的多个剪枝率分别进行剪枝处理，以获取对应的多个子神经网络；
处理获取模块302，用于将测试数据集分别输入所述原始神经网络和多个所述子神经网络进行处理，基于所述原始神经网络和多个所述子神经网络的输出数据集，获取所述原始神经网络对应的参考性能指标，以及多个所述子神经网络对应的多个测试性能指标；
分析模块303，用于根据所述多个测试性能指标相对于所述参考性能指标的性能损失，分析所述原始神经网络中的候选网络层参数在不同剪枝率下的参数冗余度。
可选的，所述测试数据集包括：多媒体数据，多媒体数据为音频数据、视频数据、图像数据中的一种或者多种组合。
可选的，所述装置，还包括：
获取模块，用于获取网络压缩需求；
设置模块，用于根据所述网络压缩需求设置所述多个剪枝率，其中，所述多个剪枝率之间的差异与网络压缩度正相关。
可选的，所述剪枝处理模块301具体用于：
对所述候选网络层中的权重分布进行范数计算；
如果根据计算结果确定所述权重分布属于预设的第一区域分布的候选网络层，则使用预设的第一剪枝器进行剪枝处理，其中，所述第一区域分布的范数区间大于预设的区间阈值，且所述第一区域分布的范数最小值为零；
如果根据计算结果确定所述权重分布属于预设的第二区域分布的候选网络层，则使用预设的第二剪枝器进行剪枝处理，其中，所述第二区域分布的范数方差大于预设的方差阈值，且所述第二区域分布的范数最小值不为零。
可选的，所述处理获取模块302具体用于：
将测试图像数据集分别输入所述原始神经网络和每个所述子神经 网络进行处理，基于所述原始神经网络和多个所述子神经网络的输出图像数据集与所述测试图像数据集之间的像素处理结果，获取与所述原始神经网络对应的峰值信噪比作为所述参考性能指标，以及与每个所述子神经网络对应的峰值信噪比作为所述测试性能指标；
或者，
将测试音频数据集分别输入所述原始神经网络和每个所述子神经网络进行处理，基于所述原始神经网络和多个所述子神经网络的输出的识别文字数据集与所述测试音频数据集的标注文字之间的对比结果，获取与所述原始神经网络对应的准确率作为所述参考性能指标，以及与每个所述子神经网络对应的准确率作为所述测试性能指标。
可选的，所述装置，还包括：
检测模块，用于检测所述原始神经网络中是否存在具有通道依赖特征的关联网络层，其中，所述通道依赖特征包括：相邻的网络层具有相加的数据操作和相乘的数据操作中的至少一种；
关联设置模块，用于如果存在所述关联网络层，将所述具有通道依赖特征的所有关联网络层设置为一个所述候选网络层。
可选的，所述装置还包括：
获取计算模块，用于获取所述候选网络层中具有通道依赖特征的所有关联网络层的层数，将所述多个性能指标对所述层数取平均，获取每个关联网络层与多个所述剪枝率分别对应的参数冗余度。
可选的，所述装置还包括确定模块，用于：
根据所述候选网络层参数在不同剪枝率下的参数冗余度，确定所述原始神经网络中被剪枝的目标网络层，以生成目标神经网络对目标数据集进行处理。
可选的，所述确定模块具体用于：
根据所述多个测试性能指标相对于所述参考性能指标的性能损失，绘制所述候选网络层与所述多个剪枝率对应的性能指标曲线；
计算所述性能指标曲线中每个剪枝率的斜率，根据斜率变化确定 所述候选网络层的最大剪枝率，其中，所述最大剪枝率对应的性能指标表示所述候选网络层参数的最大参数冗余度；
根据目标剪枝率、每个所述候选网络层的所述最大参数冗余度对应的所述最大剪枝率，确定所述原始神经网络中被剪枝的目标网络层。本公开实施例所提供的数据处理装置可执行本公开任意实施例所提供的数据处理方法，具备执行方法相应的功能模块和有益效果。
本公开实施例提供的技术方案与相关技术相比具有如下优点：本公开实施例提供的数据处理方案，对原始神经网络中的候选网络层，按照预设的多个剪枝率分别进行剪枝处理，以获取对应的多个子神经网络，将测试数据集分别输入原始神经网络和多个子神经网络进行处理，基于原始神经网络和多个子神经网络的输出数据集，获取原始神经网络对应的参考性能指标，以及多个子神经网络对应的多个测试性能指标，根据多个测试性能指标相对于参考性能指标的性能损失，分析原始神经网络中的候选网络层参数在不同剪枝率下的参数冗余度。采用上述技术方案，基于实际的测试数据集获取参数冗余度，提高后续剪枝的可靠性，从而提高剪枝之后神经网络的高精度，提高数据处理的效率和精确性。
本公开实施例还提供了一种计算机程序产品，包括计算机程序/指令，该计算机程序/指令被处理器执行时实现本公开任意实施例所提供的数据处理方法。
图6为本公开实施例提供的一种电子设备的结构示意图。下面具体参考图6，其示出了适于用来实现本公开实施例中的电子设备400的结构示意图。本公开实施例中的电子设备400可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图6示出的电子设备仅仅是一个示例，不应对本公开实施例 的功能和使用范围带来任何限制。
如图6所示，电子设备400可以包括处理装置(例如中央处理器、图形处理器等)401，其可以根据存储在只读存储器(ROM)402中的程序或者从存储装置408加载到随机访问存储器(RAM)403中的程序而执行各种适当的动作和处理。在RAM 403中，还存储有电子设备400操作所需的各种程序和数据。处理装置401、ROM 402以及RAM 403通过总线404彼此相连。输入/输出(I/O)接口405也连接至总线404。
通常，以下装置可以连接至I/O接口405：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置406；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置407；包括例如磁带、硬盘等的存储装置408；以及通信装置409。通信装置409可以允许电子设备400与其他设备进行无线或有线通信以交换数据。虽然图6示出了具有各种装置的电子设备400，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置409从网络上被下载和安装，或者从存储装置408被安装，或者从ROM 402被安装。在该计算机程序被处理装置401执行时，执行本公开实施例的数据处理方法中限定的上述功能。
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机 可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(Hyper Text Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：在视频的播放过程中，接收用户的信息展示触发操作；获取所述视频关联的至少两个目标信息；在所述视频的播放页面的信息展示区域中展示所述至少两个目标信息中的第一目标信息其中，所述信息展示区域的尺寸小于所述 播放页面的尺寸；接收用户的第一切换触发操作，将所述信息展示区域中展示的所述第一目标信息切换为所述至少两个目标信息中的第二目标信息。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，单元的名称在某种情况下并不构成对该单元本身的限定。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部 件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
根据本公开的一个或多个实施例，本公开提供了一种电子设备，包括：
处理器；
用于存储可执行指令的存储器；
其中所述可执行指令能够由所述处理器从所述存储器中读取，并执行以实现如本公开提供的任一所述的数据处理方法。
根据本公开的一个或多个实施例，本公开提供了一种计算机可读存储介质，所述存储介质存储有计算机程序，所述计算机程序用于执行如本公开提供的任一所述的数据处理方法。
根据本公开的一个或多个实施例，本公开提供了一种计算机程序，包括：指令，所述指令当由处理器执行时使所述处理器执行如本公开提供的任一所述的数据处理方法。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
此外，虽然采用特定次序描绘了各操作，但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。同样地，虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题，但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反，上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。

Claims (13)

  1. 一种数据处理方法，包括：
    对原始神经网络中的候选网络层，按照预设的多个剪枝率分别进行剪枝处理，以获取对应的多个子神经网络；
    将测试数据集分别输入所述原始神经网络和多个所述子神经网络进行处理，基于所述原始神经网络和多个所述子神经网络的输出数据集，获取所述原始神经网络对应的参考性能指标，以及多个所述子神经网络对应的多个测试性能指标；
    根据所述多个测试性能指标相对于所述参考性能指标的性能损失，分析所述原始神经网络中的候选网络层参数在不同剪枝率下的参数冗余度。
  2. 根据权利要求1所述的数据处理方法，还包括：
    获取网络压缩需求；
    根据所述网络压缩需求设置所述多个剪枝率，其中，所述多个剪枝率之间的差异与网络压缩度正相关。
  3. 根据权利要求1所述的数据处理方法，其中，所述按照预设的多个剪枝率分别进行剪枝处理，以获取对应的多个子神经网络，包括：
    对所述候选网络层中的权重分布进行范数计算；
    如果根据计算结果确定所述权重分布属于预设的第一区域分布的候选网络层，则使用预设的第一剪枝器进行剪枝处理，其中，所述第一区域分布的范数区间大于预设的区间阈值，且所述第一区域分布的范数最小值为零；
    如果根据计算结果确定所述权重分布属于预设的第二区域分布的候选网络层，则使用预设的第二剪枝器进行剪枝处理，其中，所述第二区域分布的范数方差大于预设的方差阈值，且所述第二区域分布的范数最小值不为零。
  4. 根据权利要求1所述的数据处理方法，其中，所述测试数据集包括：多媒体数据，其中，所述多媒体数据为音频数据、视频数据、图 像数据中的一种或者多种组合。
  5. 根据权利要求4所述的数据处理方法，其中，所述将测试数据集分别输入所述原始神经网络和多个所述子神经网络进行处理，基于所述原始神经网络和多个所述子神经网络的输出数据集，获取所述原始神经网络对应的参考性能指标，以及多个所述子神经网络对应的多个测试性能指标，包括：
    将测试图像数据集分别输入所述原始神经网络和每个所述子神经网络进行处理，基于所述原始神经网络和多个所述子神经网络的输出图像数据集与所述测试图像数据集之间的像素处理结果，获取与所述原始神经网络对应的峰值信噪比作为所述参考性能指标，以及与每个所述子神经网络对应的峰值信噪比作为所述测试性能指标；
    或者，
    将测试音频数据集分别输入所述原始神经网络和每个所述子神经网络进行处理，基于所述原始神经网络和多个所述子神经网络的输出的识别文字数据集与所述测试音频数据集的标注文字之间的对比结果，获取与所述原始神经网络对应的准确率作为所述参考性能指标，以及与每个所述子神经网络对应的准确率作为所述测试性能指标。
  6. 根据权利要求1所述的数据处理方法，还包括：
    检测所述原始神经网络中是否存在具有通道依赖特征的关联网络层，其中，所述通道依赖特征包括：相邻的网络层具有相加的数据操作和相乘的数据操作中的至少一种；
    如果存在所述关联网络层，将所述具有通道依赖特征的所有关联网络层设置为一个所述候选网络层。
  7. 根据权利要求1-6任一项所述的数据处理方法，还包括：
    根据所述候选网络层参数在不同剪枝率下的参数冗余度，确定所述原始神经网络中被剪枝的目标网络层，以生成目标神经网络对目标数据集进行处理。
  8. 根据权利要求7所述的数据处理方法，其中，所述根据所述候选 网络层参数在不同剪枝率下的参数冗余度，确定所述原始神经网络中被剪枝的目标网络层，包括：
    根据所述多个测试性能指标相对于所述参考性能指标的性能损失，绘制所述候选网络层与所述多个剪枝率对应的性能指标曲线；
    计算所述性能指标曲线中每个剪枝率的斜率，根据斜率变化确定所述候选网络层的最大剪枝率，其中，所述最大剪枝率对应的性能指标表示所述候选网络层参数的最大参数冗余度；
    根据目标剪枝率、每个所述候选网络层的所述最大参数冗余度对应的所述最大剪枝率，确定所述原始神经网络中被剪枝的目标网络层。
  9. 一种数据处理装置，包括：
    剪枝处理模块，用于对原始神经网络中的候选网络层，按照预设的多个剪枝率分别进行剪枝处理，以获取对应的多个子神经网络；
    处理获取模块，用于将测试数据集分别输入所述原始神经网络和多个所述子神经网络进行处理，基于所述原始神经网络和多个所述子神经网络的输出数据集，获取所述原始神经网络对应的参考性能指标，以及多个所述子神经网络对应的多个测试性能指标；
    分析模块，用于根据所述多个测试性能指标相对于所述参考性能指标的性能损失，分析所述原始神经网络中的候选网络层参数在不同剪枝率下的参数冗余度。
  10. 一种电子设备，所述电子设备包括：
    处理器；
    用于存储可执行指令的存储器；
    其中所述可执行指令能够由所述处理器从所述存储器中读取，并执行以实现上述权利要求1-8中任一项所述的数据处理方法。
  11. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序用于执行上述权利要求1-8中任一项所述的数据处理方法。
  12. 一种计算机程序产品，所述计算机程序产品包括计算机程序， 所述计算机程序被处理器执行时实现如权利要求1-8中任一项所述的数据处理方法。
  13. 一种计算机程序，包括：
    指令，所述指令当由处理器执行时使所述处理器执行根据权利要求1-8中任一项所述的数据处理方法。
PCT/CN2023/093805 2022-05-13 2023-05-12 数据处理方法、装置、设备及介质 Ceased WO2023217263A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US18/859,935 US20250292059A1 (en) 2022-05-13 2023-05-12 Data processing method and apparatus, device, and medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210524932.0 2022-05-13
CN202210524932.0A CN117114073B (zh) 2022-05-13 2022-05-13 数据处理方法、装置、设备及介质

Publications (1)

Publication Number Publication Date
WO2023217263A1 true WO2023217263A1 (zh) 2023-11-16

Family

ID=88729783

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/093805 Ceased WO2023217263A1 (zh) 2022-05-13 2023-05-12 数据处理方法、装置、设备及介质

Country Status (3)

Country Link
US (1) US20250292059A1 (zh)
CN (1) CN117114073B (zh)
WO (1) WO2023217263A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118821893A (zh) * 2024-09-19 2024-10-22 浙江大华技术股份有限公司 一种网络剪枝方法、装置、终端及计算机可读存储介质
CN119741724A (zh) * 2025-03-05 2025-04-01 杰软科技(集团)有限公司 基于ocr的实验数据分析方法、装置及电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111931930A (zh) * 2020-08-03 2020-11-13 Oppo广东移动通信有限公司 模型剪枝方法、装置及电子设备
CN113255910A (zh) * 2021-05-31 2021-08-13 浙江宇视科技有限公司 卷积神经网络的剪枝方法、装置、电子设备和存储介质
US20210264278A1 (en) * 2020-02-24 2021-08-26 Adobe Inc. Neural network architecture pruning
WO2022057262A1 (zh) * 2020-09-17 2022-03-24 苏州浪潮智能科技有限公司 图像识别方法、装置及计算机可读存储介质
CN114282670A (zh) * 2022-01-14 2022-04-05 北京百度网讯科技有限公司 神经网络模型的压缩方法、设备和存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200272905A1 (en) * 2019-02-26 2020-08-27 GE Precision Healthcare LLC Artificial neural network compression via iterative hybrid reinforcement learning approach
CN110633747A (zh) * 2019-09-12 2019-12-31 网易（杭州）网络有限公司 目标检测器的压缩方法、装置、介质以及电子设备
CN112101547B (zh) * 2020-09-14 2024-04-16 中国科学院上海微系统与信息技术研究所 一种对网络模型的剪枝方法、装置、电子设备及存储介质
CN112906889A (zh) * 2021-03-03 2021-06-04 中国科学院计算技术研究所 一种用于压缩深度神经网络模型的方法和系统
CN113627389B (zh) * 2021-08-30 2024-08-23 京东方科技集团股份有限公司 一种目标检测的优化方法及设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210264278A1 (en) * 2020-02-24 2021-08-26 Adobe Inc. Neural network architecture pruning
CN111931930A (zh) * 2020-08-03 2020-11-13 Oppo广东移动通信有限公司 模型剪枝方法、装置及电子设备
WO2022057262A1 (zh) * 2020-09-17 2022-03-24 苏州浪潮智能科技有限公司 图像识别方法、装置及计算机可读存储介质
CN113255910A (zh) * 2021-05-31 2021-08-13 浙江宇视科技有限公司 卷积神经网络的剪枝方法、装置、电子设备和存储介质
CN114282670A (zh) * 2022-01-14 2022-04-05 北京百度网讯科技有限公司 神经网络模型的压缩方法、设备和存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118821893A (zh) * 2024-09-19 2024-10-22 浙江大华技术股份有限公司 一种网络剪枝方法、装置、终端及计算机可读存储介质
CN119741724A (zh) * 2025-03-05 2025-04-01 杰软科技(集团)有限公司 基于ocr的实验数据分析方法、装置及电子设备

Also Published As

Publication number Publication date
US20250292059A1 (en) 2025-09-18
CN117114073A (zh) 2023-11-24
CN117114073B (zh) 2026-02-03

Similar Documents

Publication Publication Date Title
CN114004313B (zh) 故障gpu的预测方法、装置、电子设备及存储介质
CN112907628A (zh) 视频目标追踪方法、装置、存储介质及电子设备
CN117131281B (zh) 舆情事件处理方法、装置、电子设备和计算机可读介质
CN113934938A (zh) 信息展示的方法、装置、可读介质和电子设备
WO2023217263A1 (zh) 数据处理方法、装置、设备及介质
CN110347875B (zh) 一种视频场景分类方法、装置、移动终端及存储介质
CN111460214B (zh) 分类模型训练方法、音频分类方法、装置、介质及设备
CN115052188A (zh) 一种视频剪辑方法、装置、设备及介质
WO2023000782A1 (zh) 获取视频热点的方法、装置、可读介质和电子设备
CN112241761A (zh) 模型训练方法、装置和电子设备
CN110956127A (zh) 用于生成特征向量的方法、装置、电子设备和介质
CN114697763B (zh) 一种视频处理方法、装置、电子设备及介质
CN112906551B (zh) 视频处理方法、装置、存储介质及电子设备
CN111582456B (zh) 用于生成网络模型信息的方法、装置、设备和介质
CN115631514B (zh) 基于掌静脉指纹的用户识别方法、装置、设备与介质
CN118784342A (zh) 访问设备异常检测方法、装置、电子设备与计算机介质
CN117055904A (zh) 内容理解模型的自动化迭代部署方法、装置、设备及介质
CN116738184A (zh) 一种应用程序故障分析方法、装置、电子设备及存储介质
CN116011553A (zh) 一种数据处理方法、装置、设备和存储介质
CN113033770A (zh) 神经网络模型的测试方法、装置和电子设备
CN114399355B (zh) 基于用户转化率的信息推送方法、装置和电子设备
CN116312619B (zh) 语音活动检测模型生成方法、装置、介质及电子设备
CN116343905B (zh) 蛋白质特征的预处理方法、装置、介质及设备
CN112070163B (zh) 图像分割模型训练和图像分割方法、装置、设备
WO2025185276A1 (zh) 音频处理方法、装置、存储介质及电子设备

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: 23803031

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 18859935

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

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 1205 DATED 07/03/2025)

WWP Wipo information: published in national office

Ref document number: 18859935

Country of ref document: US

122 Ep: pct application non-entry in european phase

Ref document number: 23803031

Country of ref document: EP

Kind code of ref document: A1