aimet:AIMET是一个为经过训练的神经网络模型提供高级量化和压缩技术的库
需积分: 50 19 浏览量
2021-03-19
15:24:20
上传
评论
收藏 3.57MB ZIP 举报
aimet:AIMET是一个为经过训练的神经网络模型提供高级量化和压缩技术的库 （491个子文件） 
.clang-format 2KB package_aimet.cmake 5KB commit-msg 3KB SvdAlgorithm.cpp 43KB test_dlcompression_svd.cpp 30KB PyModelOptimizations.cpp 15KB test_quantization_lib_tf_enhanced_cpugpu.cpp 14KB test_gemm_fxp_acc.cpp 13KB QcQuantizeOpDeprecated.cpp 13KB TfEnhancedEncodingAnalyzer.cpp 13KB TestTfEnhancedEncodingAnalyzer.cpp 13KB math_functions.cpp 12KB TestTfEncodingAnalyzer.cpp 11KB MainQuantizationClass.cpp 10KB TestDLEqualization.cpp 10KB QcQuantizeRecurrentParamOp.cpp 9KB BiasCorrection.cpp 9KB test_quantization_lib_tf_cpu.cpp 8KB test_quantization_lib_tf_cpugpu.cpp 8KB QcQuantizeOp.cpp 8KB TfQuantizer.cpp 7KB CrossLayerScaling.cpp 7KB QcQuantizeStaticOp.cpp 7KB TensorOperations.cpp 6KB TfEncodingAnalyzer.cpp 6KB ScaleFactorCalculator.cpp 6KB TestTensorQuantizationSim.cpp 6KB TfEnhancedQuantizer.cpp 6KB TensorQuantizer.cpp 5KB AimetTensorQuantizer.cpp 5KB TestTensorQuantizer.cpp 5KB trim_functions.cpp 5KB BatchNormFold.cpp 5KB BiasCorrectionForPython.cpp 5KB QuantizerFactory.cpp 4KB CrossLayerScalingForPython.cpp 4KB TensorQuantizationSim.cpp 4KB EncodingAnalyzerForPython.cpp 4KB HighBiasFold.cpp 4KB TensorQuantizationSimForPython.cpp 4KB HighBiasFoldForPython.cpp 3KB BatchNormFoldForPython.cpp 3KB AimetOpUtils.cpp 3KB PyTrainingExtensions.cpp 3KB resnet18_eval_scores.csv 940B resnet50_eval_scores.csv 146B QcQuantizeOpGpuDeprecated.cu 6KB math_functions.cu 4KB AimetOpUtilsGpu.cu 3KB trim_functions.cu 3KB cuda_util.cu 3KB trim_functions.cuh 4KB Dockerfile 9KB .gitignore 587B TfEnhancedEncodingAnalyzer.h 7KB TensorQuantizer.h 6KB BiasCorrection.h 4KB TensorOperations.h 4KB CrossLayerScaling.h 4KB BiasCorrectionForPython.h 4KB CrossLayerScalingForPython.h 4KB TensorQuantizerOpFacade.h 4KB ScaleFactorCalculator.h 4KB BatchNormFoldForPython.h 3KB TfEncodingAnalyzer.h 3KB BatchNormFold.h 3KB HighBiasFoldForPython.h 3KB HighBiasFold.h 3KB EncodingAnalyzerForPython.h 3KB TensorQuantizationSim.h 3KB AimetOpUtils.h 3KB TensorQuantizationSimForPython.h 3KB def.h 2KB ITensorQuantizationSim.h 2KB common.h 2KB SvdAlgorithm.hpp 25KB ISVD.hpp 14KB IQuantizer.hpp 10KB qc_quantizer.hpp 7KB math_functions.hpp 6KB test_quantization_lib.hpp 6KB MainQuantizationClass.hpp 5KB TfEnhancedQuantizer.hpp 5KB IQuantizationEncodingAnalyzer.hpp 4KB TfQuantizer.hpp 4KB QuantizerFactory.hpp 4KB IQuantizationAlgorithm.hpp 3KB QcQuantizeOpDeprecated.hpp 3KB Quantization.hpp 3KB cuda_util.hpp 3KB trim_functions.hpp 3KB QcQuantizeStaticOp.hpp 2KB QcQuantizeRecurrentParamOp.hpp 2KB QcQuantizeOp.hpp 2KB setup.py.in 2KB package_info.py.in 2KB pytest.ini 91B pytest.ini 91B pytest.ini 91B Install_AIMET_GoogleColab.ipynb 57KB共 491 条
- 1
- 2
- 3
- 4
- 5
资源评论
