Instructions to use nonl/dfine-cppe5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nonl/dfine-cppe5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="nonl/dfine-cppe5")# Load model directly from transformers import AutoTokenizer, AutoModelForObjectDetection tokenizer = AutoTokenizer.from_pretrained("nonl/dfine-cppe5") model = AutoModelForObjectDetection.from_pretrained("nonl/dfine-cppe5") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files- README.md +3 -1
- all_results.json +34 -0
- test_results.json +29 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
README.md
CHANGED
|
@@ -3,6 +3,8 @@ library_name: transformers
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: ustc-community/dfine-small-coco
|
| 5 |
tags:
|
|
|
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
- name: dfine-cppe5
|
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# dfine-cppe5
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [ustc-community/dfine-small-coco](https://huggingface.co/ustc-community/dfine-small-coco) on
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
- Loss: 4.3105
|
| 20 |
- Map: 0.1854
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: ustc-community/dfine-small-coco
|
| 5 |
tags:
|
| 6 |
+
- object-detection
|
| 7 |
+
- vision
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: dfine-cppe5
|
|
|
|
| 16 |
|
| 17 |
# dfine-cppe5
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [ustc-community/dfine-small-coco](https://huggingface.co/ustc-community/dfine-small-coco) on the cppe-5 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 4.3105
|
| 22 |
- Map: 0.1854
|
all_results.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 300.0,
|
| 3 |
+
"test_loss": 4.271916389465332,
|
| 4 |
+
"test_map": 0.2447,
|
| 5 |
+
"test_map_50": 0.3449,
|
| 6 |
+
"test_map_75": 0.2657,
|
| 7 |
+
"test_map_Coverall": 0.5564,
|
| 8 |
+
"test_map_Face_Shield": 0.2347,
|
| 9 |
+
"test_map_Gloves": 0.0469,
|
| 10 |
+
"test_map_Goggles": 0.181,
|
| 11 |
+
"test_map_Mask": 0.2045,
|
| 12 |
+
"test_map_large": 0.2457,
|
| 13 |
+
"test_map_medium": 0.1547,
|
| 14 |
+
"test_map_small": 0.288,
|
| 15 |
+
"test_mar_1": 0.2186,
|
| 16 |
+
"test_mar_10": 0.5799,
|
| 17 |
+
"test_mar_100": 0.6928,
|
| 18 |
+
"test_mar_100_Coverall": 0.8051,
|
| 19 |
+
"test_mar_100_Face_Shield": 0.8176,
|
| 20 |
+
"test_mar_100_Gloves": 0.5458,
|
| 21 |
+
"test_mar_100_Goggles": 0.6172,
|
| 22 |
+
"test_mar_100_Mask": 0.6784,
|
| 23 |
+
"test_mar_large": 0.8429,
|
| 24 |
+
"test_mar_medium": 0.5042,
|
| 25 |
+
"test_mar_small": 0.5792,
|
| 26 |
+
"test_runtime": 0.7065,
|
| 27 |
+
"test_samples_per_second": 41.05,
|
| 28 |
+
"test_steps_per_second": 5.662,
|
| 29 |
+
"total_flos": 1.9198779273216e+19,
|
| 30 |
+
"train_loss": 11.328886562834647,
|
| 31 |
+
"train_runtime": 8885.8834,
|
| 32 |
+
"train_samples_per_second": 28.697,
|
| 33 |
+
"train_steps_per_second": 3.612
|
| 34 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 300.0,
|
| 3 |
+
"test_loss": 4.271916389465332,
|
| 4 |
+
"test_map": 0.2447,
|
| 5 |
+
"test_map_50": 0.3449,
|
| 6 |
+
"test_map_75": 0.2657,
|
| 7 |
+
"test_map_Coverall": 0.5564,
|
| 8 |
+
"test_map_Face_Shield": 0.2347,
|
| 9 |
+
"test_map_Gloves": 0.0469,
|
| 10 |
+
"test_map_Goggles": 0.181,
|
| 11 |
+
"test_map_Mask": 0.2045,
|
| 12 |
+
"test_map_large": 0.2457,
|
| 13 |
+
"test_map_medium": 0.1547,
|
| 14 |
+
"test_map_small": 0.288,
|
| 15 |
+
"test_mar_1": 0.2186,
|
| 16 |
+
"test_mar_10": 0.5799,
|
| 17 |
+
"test_mar_100": 0.6928,
|
| 18 |
+
"test_mar_100_Coverall": 0.8051,
|
| 19 |
+
"test_mar_100_Face_Shield": 0.8176,
|
| 20 |
+
"test_mar_100_Gloves": 0.5458,
|
| 21 |
+
"test_mar_100_Goggles": 0.6172,
|
| 22 |
+
"test_mar_100_Mask": 0.6784,
|
| 23 |
+
"test_mar_large": 0.8429,
|
| 24 |
+
"test_mar_medium": 0.5042,
|
| 25 |
+
"test_mar_small": 0.5792,
|
| 26 |
+
"test_runtime": 0.7065,
|
| 27 |
+
"test_samples_per_second": 41.05,
|
| 28 |
+
"test_steps_per_second": 5.662
|
| 29 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 300.0,
|
| 3 |
+
"total_flos": 1.9198779273216e+19,
|
| 4 |
+
"train_loss": 11.328886562834647,
|
| 5 |
+
"train_runtime": 8885.8834,
|
| 6 |
+
"train_samples_per_second": 28.697,
|
| 7 |
+
"train_steps_per_second": 3.612
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|