Keras
autonomous-driving
end-to-end
imitation-learning
self-driving
udacity
vision
cnn
gru
recurrent
temporal
Instructions to use maxim-igenbergs/dave2-gru with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use maxim-igenbergs/dave2-gru with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://maxim-igenbergs/dave2-gru") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -45,10 +45,10 @@ Output: [steering, throttle]
|
|
| 45 |
| GenRoads | `genroads_20251215-174930/` |
|
| 46 |
| Jungle | `jungle_20251201-142321/` |
|
| 47 |
### Files per Checkpoint
|
| 48 |
-
- `best_model.h5`
|
| 49 |
-
- `meta.json`
|
| 50 |
-
- `history.csv`
|
| 51 |
-
- `loss_curve.png`
|
| 52 |
## Citation
|
| 53 |
```bibtex
|
| 54 |
@thesis{igenbergs2026dualaxis,
|
|
|
|
| 45 |
| GenRoads | `genroads_20251215-174930/` |
|
| 46 |
| Jungle | `jungle_20251201-142321/` |
|
| 47 |
### Files per Checkpoint
|
| 48 |
+
- `best_model.h5`: Keras model weights
|
| 49 |
+
- `meta.json`: Training configuration and hyperparameters
|
| 50 |
+
- `history.csv`: Training/validation metrics per epoch
|
| 51 |
+
- `loss_curve.png`: Visualization of training progress
|
| 52 |
## Citation
|
| 53 |
```bibtex
|
| 54 |
@thesis{igenbergs2026dualaxis,
|