{"id":23102690,"url":"https://github.com/dataxujing/quick-demo-from-pytorch-to-tensort-cpp","last_synced_at":"2025-04-03T21:27:23.946Z","repository":{"id":112305835,"uuid":"373865391","full_name":"DataXujing/Quick-Demo-from-Pytorch-to-Tensort-cpp","owner":"DataXujing","description":"A simple and quick example shows how to convert the model of Pytoch to ONNX, and then deploy it with tensorrt in C++","archived":false,"fork":false,"pushed_at":"2021-02-16T07:33:00.000Z","size":91,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-09T09:29:08.109Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DataXujing.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-06-04T14:21:04.000Z","updated_at":"2023-12-09T01:22:41.000Z","dependencies_parsed_at":"2023-05-12T18:30:22.971Z","dependency_job_id":null,"html_url":"https://github.com/DataXujing/Quick-Demo-from-Pytorch-to-Tensort-cpp","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataXujing%2FQuick-Demo-from-Pytorch-to-Tensort-cpp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataXujing%2FQuick-Demo-from-Pytorch-to-Tensort-cpp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataXujing%2FQuick-Demo-from-Pytorch-to-Tensort-cpp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataXujing%2FQuick-Demo-from-Pytorch-to-Tensort-cpp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DataXujing","download_url":"https://codeload.github.com/DataXujing/Quick-Demo-from-Pytorch-to-Tensort-cpp/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247081179,"owners_count":20880385,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-12-17T00:00:20.122Z","updated_at":"2025-04-03T21:27:23.926Z","avatar_url":"https://github.com/DataXujing.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Quick-Demo-from-Pytorch-to-Tensort-cpp\n\n A simple and quick example shows how to convert a pytorch's model to ONNX, and then deploy it with tensorrt using c++.\n\n ## Pipline\n  - **step 1.** Using Pytorch to build a simple neural network and then export to ONNX file `test.onnx`\n ```bash\n git clone https://github.com/hova88/Quick-Demo-from-Pytorch-to-Tensort-cpp.git\n cd Quick-Demo-from-Pytorch-to-Tensort-cpp\n python pytorch_to_onnx.py\n ```\nThe screen will shown as this:\n  ```\n ----------------------------------------------------------------\n        Layer (type)               Output Shape         Param #\n================================================================\n            Conv2d-1           [-1, 10, 24, 24]             260\n            Conv2d-2             [-1, 20, 8, 8]           5,020\n         Dropout2d-3             [-1, 20, 8, 8]               0\n            Linear-4                   [-1, 50]          16,050\n            Linear-5                   [-1, 10]             510\n================================================================\nTotal params: 21,840\nTrainable params: 21,840\nNon-trainable params: 0\n----------------------------------------------------------------\nInput size (MB): 0.00\nForward/backward pass size (MB): 0.06\nParams size (MB): 0.08\nEstimated Total Size (MB): 0.15\n----------------------------------------------------------------\nDummy output:\ntensor([[-2.2734, -2.2539, -2.2107, -2.3713, -2.3443, -2.4683, -2.3709, -2.2777,\n         -2.2169, -2.2676]], device='cuda:0')\n```\n\n - **step 2.** Initialize tensorrt engine by ONNX file, and then DO INFERENCE.\n ```bash\n mkdir build \u0026\u0026 cd build \u0026\u0026 cmake ..\n make -j6\n ./onnxTotrt\n ```\n The screen will shown as this:\n ```bash\n ----------------------------------------------------------------\nInput filename:   ../test.onnx\nONNX IR version:  0.0.4\nOpset version:    10\nProducer name:    pytorch\nProducer version: 1.3\nDomain:           \nModel version:    0\nDoc string:       \n----------------------------------------------------------------\nWARNING: [TRT]/home/hova/onnx-tensorrt/onnx2trt_utils.cpp:220: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.\nloaded trt model , do inference\nCheck output:\n-2.20698 -2.24908 -2.4583 -2.27005 -2.30133 -2.43457 -2.33783 -2.21271 -2.41685 -2.1832\n ```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdataxujing%2Fquick-demo-from-pytorch-to-tensort-cpp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdataxujing%2Fquick-demo-from-pytorch-to-tensort-cpp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdataxujing%2Fquick-demo-from-pytorch-to-tensort-cpp/lists"}