Instructions to use sillescas/deepforest-dehesa-quercus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- DeepForest
How to use sillescas/deepforest-dehesa-quercus with DeepForest:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Upload training_config.json with huggingface_hub
Browse files- training_config.json +24 -0
training_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_architecture": "RetinaNet (DeepForest v2)",
|
| 3 |
+
"base_checkpoint": "weecology/deepforest-tree (HuggingFace)",
|
| 4 |
+
"num_classes": 2,
|
| 5 |
+
"label_dict": {
|
| 6 |
+
"Healthy": 0,
|
| 7 |
+
"Seca": 1
|
| 8 |
+
},
|
| 9 |
+
"learning_rate": 0.0001,
|
| 10 |
+
"ablation_lr": 0.01,
|
| 11 |
+
"epochs_trained": 30,
|
| 12 |
+
"ablation_epochs": 5,
|
| 13 |
+
"batch_size": 4,
|
| 14 |
+
"iou_threshold": 0.4,
|
| 15 |
+
"seed": 42,
|
| 16 |
+
"device": "cuda",
|
| 17 |
+
"train_csv": "/home/controller/quercus_train/data/train.csv",
|
| 18 |
+
"val_csv": "/home/controller/quercus_train/data/val.csv",
|
| 19 |
+
"test_csv": "/home/controller/quercus_train/data/test.csv",
|
| 20 |
+
"f1_validation": 0.6694,
|
| 21 |
+
"precision_validation": 0.61,
|
| 22 |
+
"recall_validation": 0.7417,
|
| 23 |
+
"f1_ablation_high_lr": 0.0
|
| 24 |
+
}
|