Instructions to use basant18/MoBiLSTM-violence-detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use basant18/MoBiLSTM-violence-detection with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://basant18/MoBiLSTM-violence-detection") - Notebooks
- Google Colab
- Kaggle
| { | |
| "last_epoch": 15, | |
| "best_val_acc": 0.9375, | |
| "history": { | |
| "accuracy": [ | |
| 0.5553385615348816, | |
| 0.7578125, | |
| 0.8665364384651184, | |
| 0.927734375, | |
| 0.9622395634651184, | |
| 0.9778645634651184, | |
| 0.9908854365348816, | |
| 0.9895833134651184, | |
| 0.98828125, | |
| 0.521484375, | |
| 0.6686198115348816, | |
| 0.8229166865348816, | |
| 0.921875, | |
| 0.9485676884651184, | |
| 0.970703125, | |
| 0.978515625 | |
| ], | |
| "val_accuracy": [ | |
| 0.8020833134651184, | |
| 0.765625, | |
| 0.7135416865348816, | |
| 0.7916666865348816, | |
| 0.7526041865348816, | |
| 0.7421875, | |
| 0.7864583134651184, | |
| 0.8697916865348816, | |
| 0.9166666865348816, | |
| 0.7369791865348816, | |
| 0.8203125, | |
| 0.9114583134651184, | |
| 0.7864583134651184, | |
| 0.9114583134651184, | |
| 0.8307291865348816, | |
| 0.9375 | |
| ], | |
| "loss": [ | |
| 0.6800053119659424, | |
| 0.5507908463478088, | |
| 0.3556845486164093, | |
| 0.20352034270763397, | |
| 0.12936332821846008, | |
| 0.08566807955503464, | |
| 0.04819059371948242, | |
| 0.040873412042856216, | |
| 0.03668588399887085, | |
| 0.691375195980072, | |
| 0.6279469132423401, | |
| 0.44201838970184326, | |
| 0.2507573366165161, | |
| 0.16552196443080902, | |
| 0.11516818404197693, | |
| 0.06602582335472107 | |
| ], | |
| "val_loss": [ | |
| 0.6139814257621765, | |
| 0.46780678629875183, | |
| 0.6475608944892883, | |
| 0.45695874094963074, | |
| 0.8027079701423645, | |
| 0.911980926990509, | |
| 0.8351767659187317, | |
| 0.5829562544822693, | |
| 0.29997509717941284, | |
| 0.6668654084205627, | |
| 0.5111598372459412, | |
| 0.24878698587417603, | |
| 0.5317790508270264, | |
| 0.2548995316028595, | |
| 0.4509934186935425, | |
| 0.20648451149463654 | |
| ] | |
| }, | |
| "epoch": 138, | |
| "metrics": { | |
| "accuracy": 0.9986979365348816, | |
| "loss": 0.008157269097864628, | |
| "val_accuracy": 0.953125, | |
| "val_loss": 0.2559535801410675, | |
| "learning_rate": 0.009999999776482582 | |
| } | |
| } |