{"id":32373327,"url":"https://github.com/jackhanyuan/deeplabv3plus-ascend","last_synced_at":"2026-07-11T08:32:26.375Z","repository":{"id":43169093,"uuid":"466623264","full_name":"jackhanyuan/deeplabv3plus-ascend","owner":"jackhanyuan","description":"Deeplabv3+ om model inference program on the Huawei Ascend platform","archived":false,"fork":false,"pushed_at":"2022-12-13T10:15:52.000Z","size":11130,"stargazers_count":1,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-01-14T07:50:24.263Z","etag":null,"topics":["ascend","deeplabv3"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jackhanyuan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-03-06T03:11:52.000Z","updated_at":"2023-04-11T15:45:53.000Z","dependencies_parsed_at":"2023-01-28T10:45:17.415Z","dependency_job_id":null,"html_url":"https://github.com/jackhanyuan/deeplabv3plus-ascend","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jackhanyuan/deeplabv3plus-ascend","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackhanyuan%2Fdeeplabv3plus-ascend","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackhanyuan%2Fdeeplabv3plus-ascend/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackhanyuan%2Fdeeplabv3plus-ascend/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackhanyuan%2Fdeeplabv3plus-ascend/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jackhanyuan","download_url":"https://codeload.github.com/jackhanyuan/deeplabv3plus-ascend/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackhanyuan%2Fdeeplabv3plus-ascend/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35356473,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-11T02:00:05.354Z","response_time":104,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["ascend","deeplabv3"],"created_at":"2025-10-24T21:57:08.987Z","updated_at":"2026-07-11T08:32:26.370Z","avatar_url":"https://github.com/jackhanyuan.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# deeplabv3plus ascend\nDeeplabv3+ om model inference program on the Huawei Ascend platform\n\nAll programs passed the test on Huawei `Atlas 300I` inference card (`Ascend 310 AI CPU`, `CANN 5.0.2`, `npu-smi 21.0.2`).\n\nYou can run demo by `python detect_deeplabv3plus_ascend.py`.\n\n## Environments\nIn addition to the Ascend environments with ATC tools, CANN(pyACL), and Python, you will need the following python packages.\n\n```txt\nopencv_python\nPillow\nonnx\ntorch\n```\n\n## Export om model \n(1) Training your Deeplabv3+ model by [bubbliiiing/deeplabv3-plus-pytorch](https://github.com/bubbliiiing/deeplabv3-plus-pytorch). Then export the pytorch model to onnx format.\n\n(2) On the Huawei Ascend platform, using the `atc` tool convert the onnx model to om model.\n```bash\n# on Ascend 310 AI CPU, exporting onnx model to om model.\natc --input_shape=\"images:1,3,512,512\" --input_format=NCHW --output=\"deeplab_mobilenetv2\" --soc_version=Ascend310 --framework=5 --model=\"deeplab_mobilenetv2.onnx\" --output_type=FP32 \n```\n\n## Inference by Ascend NPU\n(1) Clone repo and move `*.om model` to `deeplabv3plus-ascend/ascend/*.om`.\n```bash\ngit clone git@github.com:jackhanyuan/deeplabv3plus-ascend.git\nmv deeplab_mobilenetv2.om deeplabv3plus-ascend/ascend/\n```\n\n(2) Edit label file in `deeplabv3plus-ascend/ascend/deeplabv3plus.label`.\n\n\n(3) Run inference program.\n```bash\npython detect_deeplabv3plus_ascend.py\n```\nThe result will save to `img_out` folder.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjackhanyuan%2Fdeeplabv3plus-ascend","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjackhanyuan%2Fdeeplabv3plus-ascend","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjackhanyuan%2Fdeeplabv3plus-ascend/lists"}