File tree Expand file tree Collapse file tree 1 file changed +4
-4
lines changed Expand file tree Collapse file tree 1 file changed +4
-4
lines changed Original file line number Diff line number Diff line change 1- #
1+ ##
22## B站同步视频讲解
33- https://www.bilibili.com/video/BV1Xw411f7FW
44- 相关PPTX下载:http://zifuture.com:1556/fs/sxai/tensorRT.pptx
15153 . TensorRT.vcxproj文件中,修改` <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 10.0.targets" /> ` 为你配置的CUDA路径
16164 . TensorRT.vcxproj文件中,修改` <CodeGeneration>compute_61,sm_61</CodeGeneration> ` 为你显卡配备的计算能力
1717 - 根据型号参考这里:https://developer.nvidia.com/zh-cn/cuda-gpus#compute
18- 5 . 配置依赖,或者下载依赖到lean中 。配置VC++目录->包含目录和引用目录
18+ 5 . 配置依赖或者下载依赖到lean中 。配置VC++目录->包含目录和引用目录
19196 . 配置环境,调试->环境,设置PATH路径
20207 . 编译并运行案例
2121
@@ -28,7 +28,7 @@ image = cv2.imread("inference/car.jpg")
2828bboxes = yolo.commit(image).get()
2929```
3030
31- - Pytorch无缝对接
31+ - Pytorch的无缝对接
3232``` python
3333model = models.resnet18(True ).eval().to(device)
3434trt_model = tp.convert_torch_to_trt(model, input )
@@ -367,7 +367,7 @@ engine->print();
367367// 加载图像
368368auto image = imread(" demo.jpg" );
369369
370- // 获取模型的输入和输出tensor节点,可以根据名字或者索引获取第几个
370+ // 获取模型的输入和输出tensor节点,可以根据名字或者索引获取具体第几个
371371auto input = engine-> input (0 );
372372auto output = engine-> output(0 );
373373
You can’t perform that action at this time.
0 commit comments