| 2025-08-22 04:05:10 - INFO - Loading model: openbmb/MiniCPM-V-4 |
| 2025-08-22 04:05:11 - INFO - vision_config is None, using default vision config |
| 2025-08-22 04:06:14 - INFO - Model loaded in 64.06 seconds |
| 2025-08-22 04:06:14 - INFO - GPU Memory Usage after model load: 7802.99 MB |
| 2025-08-22 04:06:14 - INFO - [83e6ecab-4aa8-4145-a723-df97c6a534ff] Processing video: 'videos/sample1_raw.mp4', Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see; do not interpret intentions, relationships, or work efficiency. Avoid all repetitive descriptions of the store's layout or shelves.' |
| 2025-08-22 04:06:14 - INFO - [83e6ecab-4aa8-4145-a723-df97c6a534ff] Extracting frames using method: uniform, rate/threshold: 30 |
| 2025-08-22 04:06:19 - INFO - [83e6ecab-4aa8-4145-a723-df97c6a534ff] Extracted 30 frames successfully. Saving to temporary files... |
| 2025-08-22 04:06:20 - INFO - [83e6ecab-4aa8-4145-a723-df97c6a534ff] 30 frames saved to temp_videos/83e6ecab-4aa8-4145-a723-df97c6a534ff |
| 2025-08-22 04:06:36 - INFO - vision_config is None, using default vision config |
| 2025-08-22 04:06:52 - INFO - Tokens per second: 7.668726473028378, Peak GPU memory MB: 13140.375 |
| 2025-08-22 04:06:52 - INFO - [83e6ecab-4aa8-4145-a723-df97c6a534ff] Inference time: 37.56 seconds, CPU usage: 19.3%, CPU core utilization: [22.7, 15.6, 20.2, 18.5] |
| 2025-08-22 04:06:52 - INFO - [83e6ecab-4aa8-4145-a723-df97c6a534ff] Cleaned up temporary frame directory: temp_videos/83e6ecab-4aa8-4145-a723-df97c6a534ff |
| 2025-08-22 04:06:52 - INFO - [1cfb935b-5c0c-4f97-a288-7f0436b30c26] Processing video: 'videos/sample1_rotated.mp4', Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see; do not interpret intentions, relationships, or work efficiency. Avoid all repetitive descriptions of the store's layout or shelves.' |
| 2025-08-22 04:06:52 - INFO - [1cfb935b-5c0c-4f97-a288-7f0436b30c26] Extracting frames using method: uniform, rate/threshold: 30 |
| 2025-08-22 04:06:53 - INFO - [1cfb935b-5c0c-4f97-a288-7f0436b30c26] Extracted 30 frames successfully. Saving to temporary files... |
| 2025-08-22 04:06:53 - INFO - [1cfb935b-5c0c-4f97-a288-7f0436b30c26] 30 frames saved to temp_videos/1cfb935b-5c0c-4f97-a288-7f0436b30c26 |
| 2025-08-22 04:07:06 - INFO - vision_config is None, using default vision config |
| 2025-08-22 04:07:16 - INFO - Tokens per second: 4.763776873285316, Peak GPU memory MB: 13140.375 |
| 2025-08-22 04:07:16 - INFO - [1cfb935b-5c0c-4f97-a288-7f0436b30c26] Inference time: 23.99 seconds, CPU usage: 29.7%, CPU core utilization: [27.6, 33.2, 34.1, 24.0] |
| 2025-08-22 04:07:16 - INFO - [1cfb935b-5c0c-4f97-a288-7f0436b30c26] Cleaned up temporary frame directory: temp_videos/1cfb935b-5c0c-4f97-a288-7f0436b30c26 |
|
|
