Instructions to use flatala-research/VideoMAE-conflab-traj-direction-RH with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use flatala-research/VideoMAE-conflab-traj-direction-RH with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("video-classification", model="flatala-research/VideoMAE-conflab-traj-direction-RH")# Load model directly from transformers import AutoImageProcessor, AutoModelForVideoClassification processor = AutoImageProcessor.from_pretrained("flatala-research/VideoMAE-conflab-traj-direction-RH") model = AutoModelForVideoClassification.from_pretrained("flatala-research/VideoMAE-conflab-traj-direction-RH") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 6.135531135531136, | |
| "eval_accuracy": 0.5756097560975609, | |
| "eval_loss": 1.497787356376648, | |
| "eval_runtime": 33.1995, | |
| "eval_samples_per_second": 6.175, | |
| "eval_steps_per_second": 0.783 | |
| } |