【加密】JM118 – CUDA与TensorRT部署实战课程[15.5G]

【加密】JM118 – CUDA与TensorRT部署实战课程[15.5G]
┣━━1.并行处理与GPU体系架构 [5.9G]
┃ ┣━━1.0 课程介绍.abc [405.5M]
┃ ┣━━1.1 并行处理简介.abc [828.3M]
┃ ┣━━1.2 GPU并行处理.abc [892.9M]
┃ ┣━━1.3.1 环境搭建.abc [215.5M]
┃ ┣━━1.3.2 CUDA cuDNN TRT版本选择.abc [1.1G]
┃ ┣━━1.3.3 常用软件安装.abc [503.5M]
┃ ┣━━1.3.4 服务器的环境配置.abc [1.3G]
┃ ┣━━1.3.5 编辑器的环境配置.abc [804.2M]
┃ ┗━━第一章课件 并行处理、GPU体系架构与课程简介.pdf [5.5M]
┣━━2.CUDA编程入门 [2.6G]
┃ ┣━━2.1.1 理解CUDA中的Grid和Block.abc [109.7M]
┃ ┣━━2.1.2 理解.cu和.cpp的相互引用及Makefile.abc [107.2M]
┃ ┣━━2.2.1 CUDA Core的矩阵乘法计算.abc [590M]
┃ ┣━━2.2.2 CUDA中的Error Handle.abc [247.2M]
┃ ┣━━2.2.3 GPU的硬件信息获取.abc [117.1M]
┃ ┣━━2.3.1 安装Nsight system and compute-上.abc [91.2M]
┃ ┣━━2.3.2 安装Nsight system and compute-下.abc [163.1M]
┃ ┣━━2.4.1 共享内存-上.abc [114.4M]
┃ ┣━━2.4.1 共享内存-下.abc [143M]
┃ ┣━━2.4.2 Bank Conflict-上.abc [86.6M]
┃ ┣━━2.4.2 Bank Conflict-下.abc [97.9M]
┃ ┣━━2.5.1 Stream与Event-上.abc [182.6M]
┃ ┣━━2.5.2 Stream与Event-下.abc [124.7M]
┃ ┣━━2.6.1 双线性插值与仿射变换-上.abc [112.9M]
┃ ┣━━2.6.2 双线性插值与仿射变换-下.abc [330.7M]
┃ ┗━━第二章课件 CUDA编程入门.pdf [10.1M]
┣━━3.TensorRT基础入门 [2.7G]
┃ ┣━━3.1 TensorRT概述.abc [143.5M]
┃ ┣━━3.10 trtexec log分析.abc [207.9M]
┃ ┣━━3.2 TensorRT的应用场景.abc [131.9M]
┃ ┣━━3.3 TensorRT的模块.abc [120.6M]
┃ ┣━━3.4 导出并分析ONNX.abc [227.5M]
┃ ┣━━3.5 剖析ONNX架构并理解ProtoBuf-上.abc [257M]
┃ ┣━━3.5 剖析ONNX架构并理解ProtoBuf-下.abc [226.1M]
┃ ┣━━3.6 ONNX注册算子的方法.abc [354.1M]
┃ ┣━━3.7 ONNX graph surgeon-上.abc [79.8M]
┃ ┣━━3.7 ONNX graph surgeon-下.abc [382M]
┃ ┣━━3.8 快速分析开源代码并导出ONNX.abc [313.5M]
┃ ┣━━3.9 使用trtexec.abc [288.4M]
┃ ┗━━第三章课件.pdf [10.9M]
┣━━4.TensorRT模型部署优化 [1.4G]
┃ ┣━━4.1.1 FLOPS和TOPS.abc [158.9M]
┃ ┣━━4.1.2 Roofline model.abc [149.9M]
┃ ┣━━4.2 模型部署的几大误区.abc [155.9M]
┃ ┣━━4.3.1 quantization(mapping-and-shift).abc [102.4M]
┃ ┣━━4.3.2 quantization(quantization-granularity).abc [36.6M]
┃ ┣━━4.3.3 quantization(calibration-algorithm).abc [90.4M]
┃ ┣━━4.3.4 quantization(PTQ-and-quantization-analy.abc [267.1M]
┃ ┣━━4.3.5 quantization(QAT-and-layer-fusion).abc [178.3M]
┃ ┣━━4.4.1 pruning(pruning granularity).abc [114.2M]
┃ ┣━━4.4.2 pruning(channel level pruning).abc [130.3M]
┃ ┣━━4.4.3 pruning(sparse tensor core).abc [79.9M]
┃ ┗━━第四章课件.pdf [12.1M]
┣━━5.TensorRT API的基本使用 [984.7M]
┃ ┣━━5.1 MNISIT-model-build-infer.abc [84.7M]
┃ ┣━━5.2 build-model.abc [55.2M]
┃ ┣━━5.3 infer-model.abc [34.8M]
┃ ┣━━5.4 TensorRT-network-structure.abc [72.5M]
┃ ┣━━5.5.1 build-model-from-scratch-上.abc [122.4M]
┃ ┣━━5.5.2 build-model-from-scratch-下.abc [94.5M]
┃ ┣━━5.6.1 build-trt-module-上.abc [72.1M]
┃ ┣━━5.6.2 build-trt-module-下.abc [54.7M]
┃ ┣━━5.7 custom-trt-plugin.abc [220.2M]
┃ ┗━━5.8 plugin-unit-test(python+cpp).abc [173.5M]
┣━━6.实战：部署分类器（CNN&ViT） [625.5M]
┃ ┣━━6.0 preprocess-speed-compare.abc [74.8M]
┃ ┣━━6.1 deploy-classification-basic.abc [86M]
┃ ┣━━6.2.1 design-of-inference-model.abc [78.3M]
┃ ┣━━6.2.2 deploy-classification-advanced.abc [111.8M]
┃ ┣━━6.3 int8-calibration.abc [143.9M]
┃ ┗━━6.4 trt-engine-explorer.abc [130.8M]
┣━━7.实战：部署YOLOv8检测器 [492.4M]
┃ ┣━━7.1 load-save-tensor.abc [92M]
┃ ┣━━7.2 affine-transformation.abc [64.8M]
┃ ┣━━7.3 deploy-yolov8-basics.abc [184.6M]
┃ ┗━━7.4 quantization-analysis.abc [151.1M]
┗━━8.实战：部署BEVFusion模型 [852.6M]
┣━━8.1 Overview-and-setting-environment-.abc [188.1M]
┣━━8.2 About-spconv-algorithm.abc [70.8M]
┣━━8.3 Export-SParse-Convolution-Network.abc [124.4M]
┣━━8.4 Spconv-with-Explicit-GEMM-Conv.abc [90.9M]
┣━━8.5 Spconv-with-Implicit-GEMM-Conv.abc [84.5M]
┣━━8.6 BEVPool-Optimization.abc [98.4M]
┣━━8.7 Analyze-each-onnx.abc [94.6M]
┗━━8.8 CUDA-BEVFusion-Framework-Design.abc [100.8M]

admin网站管理

收藏 海报 链接