Wangtwohappy's picture
Upload folder using huggingface_hub
f8ba0eb verified
2025-08-22 05:21:34 - INFO - Loading model: openbmb/MiniCPM-V-4-int4
2025-08-22 05:21:34 - INFO - vision_config is None, using default vision config
2025-08-22 05:21:41 - INFO - Model loaded in 6.88 seconds
2025-08-22 05:21:41 - INFO - GPU Memory Usage after model load: 2694.64 MB
2025-08-22 05:21:41 - INFO - [b1130834-0115-4a56-831d-192b1629d030] Processing video: 'videos/sample1_rotated_270.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 05:21:41 - INFO - [b1130834-0115-4a56-831d-192b1629d030] Extracting frames using method: uniform, rate/threshold: 30
2025-08-22 05:21:42 - INFO - [b1130834-0115-4a56-831d-192b1629d030] Extracted 30 frames successfully. Saving to temporary files...
2025-08-22 05:21:42 - INFO - [b1130834-0115-4a56-831d-192b1629d030] 30 frames saved to temp_videos/b1130834-0115-4a56-831d-192b1629d030
2025-08-22 05:21:56 - INFO - vision_config is None, using default vision config
2025-08-22 05:22:16 - INFO - [b1130834-0115-4a56-831d-192b1629d030] Cleaned up temporary frame directory: temp_videos/b1130834-0115-4a56-831d-192b1629d030