Custom_TensorRT-main.zip （56个子文件） 
Custom_TensorRT-main reference_pdf 
8-bit-inference-with-tensorrt.pdf 1.74MB How_to_use_TensorRT_by_ONNX.pdf 1.9MB
simple_mnist.cpp 11KB kernel my_convolution.cu 3KB Pooling.cu 3KB PoolinINT8.cu 3KB add.cu 452B add.cpp 1KB .vscode settings.json 199B mnist_torch_tensorrt.py 7KB weights ip1bias_torch_float32.wts 480B conv1bias_torch_float32.wts 20B ip2filter_torch_float32.wts 5KB ip2bias_torch_float32.wts 40B ip1filter_torch_float32.wts 338KB ip2filter_tf_float32.wts 5KB conv1bias_tf_float32.wts 20B ip1bias_tf_float32.wts 480B conv1filter_torch_float32.wts 500B ip1filter_tf_float32.wts 338KB conv1filter_tf_float32.wts 500B ip2bias_tf_float32.wts 40B plugin ConvPluginKernel.cu 3KB ReluPlugin.cpp 0B PoolingPlugin.h 2KB main_simple.cpp 11KB ConvPlugin.cpp 4KB ReluKernel.cu 1KB main_poolingplugin+int8calibrator.cpp 13KB MyInt8Calibrator.cpp 4KB main_convplugin.cpp 12KB PoolingPluginKernel.cu 5KB utils.h 1KB ReluPlugin.h 0B ConvPlugin.h 2KB PoolingPlugin.cpp 6KB MyInt8Calibrator.h 1KB main_int8calibrator.cpp 13KB value result_torch_float32.bin 391KB
tensorrt in ubuntu16.04.pptx 44KB README.md 568B Summary Relu.cu 1KB Int8Calibrator.h 7KB smart_ptr_ver.cpp 26KB main.cpp 21KB PoolingPlugin.h 7KB ReluKernel.cu 2KB ReluPlugin.h 4KB Pooling.cu 5KB Utils.h 2KB MyTensorRT.h 2KB
tensorRT.txt 8KB data 
data.zip 2.35MB python torch_mnist.py 6KB convplugin+int8calibrator convplugin+int8calibrator.cpp 24KB conv_plugin.cu 3KB资源评论
