课程目录：

├──一、并行处理与GPU体系架构
| ├──001.第一章课件 并行处理、GPU体系架构与课程简介.pdf 5.54M
| ├──002.1.0 课程介绍_ev.mp4 53.59M
| ├──003.1.1 并行处理简介_ev.mp4 88.02M
| ├──004.1.2 GPU并行处理_ev.mp4 96.79M
| ├──005.1.3.1 环境搭建_ev.mp4 27.91M
| ├──006.1.3.2 CUDA cuDNN TRT版本选择_ev.mp4 124.77M
| ├──007.1.3.3 常用软件安装_ev.mp4 59.46M
| ├──008.1.3.4 服务器的环境配置_ev.mp4 113.15M
| └──009.1.3.5 编辑器的环境配置_ev.mp4 101.76M
├──二、CUDA编程入门
| ├──001.第二章课件 CUDA编程入门.pdf 10.11M
| ├──002.2.1.1 理解CUDA中的Grid和Block_ev.mp4 62.74M
| ├──003.2.1.2 理解.cu和.cpp的相互引用及Makefile_ev.mp4 59.57M
| ├──004.2.2.1 CUDA Core的矩阵乘法计算_ev.mp4 63.17M
| ├──005.2.2.2 CUDA中的Error Handle_ev.mp4 37.37M
| ├──006.2.2.3 GPU的硬件信息获取_ev.mp4 19.32M
| ├──007.2.3.1 安装Nsight system and compute-上_ev.mp4 31.22M
| ├──008.2.3.2 安装Nsight system and compute-下_ev.mp4 49.11M
| ├──009.2.4.1 共享内存-上_ev.mp4 34.09M
| ├──010.2.4.1 共享内存-下_ev.mp4 40.69M
| ├──011.2.4.2 Bank Conflict-上_ev.mp4 28.22M
| ├──012.2.4.2 Bank Conflict-下_ev.mp4 29.63M
| ├──013.2.5.1 Stream与Event-上_ev.mp4 61.89M
| ├──014.2.5.2 Stream与Event-下_ev.mp4 37.74M
| ├──015.2.6.1 双线性插值与仿射变换-上_ev.mp4 34.57M
| └──016.2.6.2 双线性插值与仿射变换-下_ev.mp4 98.11M
├──三、TensorRT基础入门
| ├──001.第三章课件.pdf 10.92M
| ├──002.3.1 TensorRT概述_ev.mp4 47.12M
| ├──003.3.2 TensorRT的应用场景_ev.mp4 41.75M
| ├──004.3.3 TensorRT的模块_ev.mp4 44.15M
| ├──005.3.4 导出并分析ONNX_ev.mp4 62.74M
| ├──006.3.5 剖析ONNX架构并理解ProtoBuf-上_ev.mp4 59.15M
| ├──007.3.5 剖析ONNX架构并理解ProtoBuf-下_ev.mp4 57.08M
| ├──008.3.6 ONNX注册算子的方法_ev.mp4 89.31M
| ├──009.3.7 ONNX graph surgeon-上_ev.mp4 27.05M
| ├──010.3.7 ONNX graph surgeon-下_ev.mp4 96.72M
| ├──011.3.8 快速分析开源代码并导出ONNX_ev.mp4 111.47M
| ├──012.3.9 使用trtexec_ev.mp4 268.37M
| └──013.3.10 trtexec log分析_ev.mp4 198.13M
├──四、TensorRT模型部署优化
| ├──001.第四章课件.pdf 12.14M
| ├──002.4.1.1 FLOPS和TOPS_ev.mp4 54.85M
| ├──003.4.1.2 Roofline model_ev.mp4 133.67M
| ├──004.4.2 模型部署的几大误区_ev.mp4 36.85M
| ├──005.4.3.1 quantization(mapping-and-shift)_ev.mp4 89.41M
| ├──006.4.3.2 quantization(quantization-granularity)_ev.mp4 32.06M
| ├──007.4.3.3 quantization(calibration-algorithm)_ev.mp4 80.66M
| ├──008.4.3.4 quantization(PTQ-and-quantization-analy_ev.mp4 46.91M
| ├──009.4.3.5 quantization(QAT-and-layer-fusion)_ev.mp4 80.86M
| ├──010.4.4.1 pruning(pruning granularity)_ev.mp4 61.76M
| ├──011.4.4.2 pruning(channel level pruning)_ev.mp4 70.80M
| └──012.4.4.3 pruning(sparse tensor core)_ev.mp4 41.87M
├──五、TensorRT API的基本使用
| ├──001.5.1 MNISIT-model-build-infer_ev.mp4 52.08M
| ├──002.5.2 build-model_ev.mp4 35.61M
| ├──003.5.3 infer-model_ev.mp4 21.27M
| ├──004.5.4 TensorRT-network-structure_ev.mp4 44.88M
| ├──005.5.5.1 build-model-from-scratch-上_ev.mp4 78.92M
| ├──006.5.5.2 build-model-from-scratch-下_ev.mp4 62.58M
| ├──007.5.6.1 build-trt-module-上_ev.mp4 46.99M
| ├──008.5.6.2 build-trt-module-下_ev.mp4 36.47M
| ├──009.5.7 custom-trt-plugin_ev.mp4 139.84M
| └──010.5.8 plugin-unit-test(python+cpp)_ev.mp4 99.51M
├──六、实战：部署分类器（CNN&ViT）
| ├──001.6.0 preprocess-speed-compare_ev.mp4 48.46M
| ├──002.6.1 deploy-classification-basic_ev.mp4 55.94M
| ├──003.6.2.1 design-of-inference-model_ev.mp4 44.44M
| ├──004.6.2.2 deploy-classification-advanced_ev.mp4 71.56M
| ├──005.6.3 int8-calibration_ev.mp4 87.62M
| └──006.6.4 trt-engine-explorer_ev.mp4 89.70M
├──七、实战：部署YOLOv8检测器
| ├──001.7.1 load-save-tensor_ev.mp4 60.05M
| ├──002.7.2 affine-transformation_ev.mp4 40.52M
| ├──003.7.3 deploy-yolov8-basics_ev.mp4 126.58M
| └──004.7.4 quantization-analysis_ev.mp4 114.25M
├──八、实战：部署BEVFusion模型
| ├──002.8.1 Overview-and-setting-environment-_ev.mp4 112.56M
| ├──003.8.2 About-spconv-algorithm_ev.mp4 48.21M
| ├──004.8.3 Export-SParse-Convolution-Network_ev.mp4 87.23M
| ├──005.8.4 Spconv-with-Explicit-GEMM-Conv_ev.mp4 57.29M
| ├──006.8.5 Spconv-with-Implicit-GEMM-Conv_ev.mp4 52.62M
| ├──007.8.6 BEVPool-Optimization_ev.mp4 58.35M
| ├──008.8.7 Analyze-each-onnx_ev.mp4 68.58M
| └──009.8.8 CUDA-BEVFusion-Framework-Design_ev.mp4 60.57M