{"id":24305710,"url":"https://github.com/berlin0308/raspberrypi-movinet-tflite","last_synced_at":"2026-04-20T19:04:42.923Z","repository":{"id":249825866,"uuid":"832648992","full_name":"berlin0308/Raspberrypi-MoViNet-TFLite","owner":"berlin0308","description":null,"archived":false,"fork":false,"pushed_at":"2025-03-03T06:39:00.000Z","size":77686,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-03T07:28:18.529Z","etag":null,"topics":["post-training-quantization","raspberry-pi-4","tensorflow","tensorflow-lite"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"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/berlin0308.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":"2024-07-23T12:52:05.000Z","updated_at":"2025-03-03T06:39:04.000Z","dependencies_parsed_at":"2025-03-03T07:35:03.866Z","dependency_job_id":null,"html_url":"https://github.com/berlin0308/Raspberrypi-MoViNet-TFLite","commit_stats":null,"previous_names":["berlin0308/raspberrypi-tflite-movinet"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/berlin0308%2FRaspberrypi-MoViNet-TFLite","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/berlin0308%2FRaspberrypi-MoViNet-TFLite/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/berlin0308%2FRaspberrypi-MoViNet-TFLite/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/berlin0308%2FRaspberrypi-MoViNet-TFLite/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/berlin0308","download_url":"https://codeload.github.com/berlin0308/Raspberrypi-MoViNet-TFLite/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242250744,"owners_count":20096895,"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":["post-training-quantization","raspberry-pi-4","tensorflow","tensorflow-lite"],"created_at":"2025-01-17T02:15:32.971Z","updated_at":"2026-04-20T19:04:42.884Z","avatar_url":"https://github.com/berlin0308.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"#  Running MoViNet-Stream Models on Raspberry Pi with TFLite\n\n\n## 1. Download Code Example\n\n```\ngit clone https://github.com/berlin0308/Raspberrypi-MoViNet-TFLite.git --depth 1\n```\n\n## 2. Install Python Packages\n\n```\nsh setup.sh\n```\n\n+ For model inference on Raspberry Pi, install ```tflite-runtime``` only instead of the whole ```tensorflow``` package\n\n## 3. Run Inference\n\n```\npython3 classify.py --model models/a1_v2_stream_b16_lr0.0001_g1.5_d0.5_918/a1_float16.tflite\n```\n\n+ ```--model``` : MoViNet model path\n+ ```--label``` : Path to the label map txt\n+ ```--numThreads``` : CPU threads to run the model\n\n# Model Details\n\n| Model ID | Quantization | Model Path (* Recommended) | Latency | F1-score |\n|----------|--------------|------------|---------------------------|----------|\n| A0 | Int8 | models/a0_v5_stream_b16_lr0.0004_g2.0_d0.1_sd0.0_92/a0_int8.tflite | 35 ms | 0.312 |\n| A0 | Float16 |models/a0_v5_stream_b16_lr0.0004_g2.0_d0.1_sd0.0_92/a0_float16.tflite| 47 ms | 0.916 |\n| A1 | Int8 | models/a1_stream_b16_lr0.0001_g1.5_d0.5_918/a1_int8.tflite | 49 ms | 0.579 |\n| A1 | Float16 | models/a1_stream_b16_lr0.0001_g1.5_d0.5_918/a1_float16.tflite | 98 ms | 0.918 |\n| A2 | Int8 | models/a2_stream_b16_lr0.0004_g1.2_d0.5_sd0.3_929/a2_int8.tflite | 78 ms | 0.764 |\n| A2 | Float16 | models/a2_stream_b16_lr0.0004_g1.2_d0.5_sd0.3_929/a2_float16.tflite | 154 ms | 0.929 |\n\n+ Raspberry Pi 4 Model B\n+ Raspberry Pi OS / 64-bit / 4 Threads\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fberlin0308%2Fraspberrypi-movinet-tflite","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fberlin0308%2Fraspberrypi-movinet-tflite","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fberlin0308%2Fraspberrypi-movinet-tflite/lists"}