Update README.md
Browse files
README.md
CHANGED
@@ -22,17 +22,19 @@ This model is a fine-tuned version of [hustvl/yolos-tiny](https://huggingface.co
|
|
22 |
|
23 |
## Model description
|
24 |
|
25 |
-
|
|
|
|
|
26 |
|
27 |
** If you plan on fine-tuning an Object Detection model on the NFL Helmet detection dataset, I would recommend using (at least) the Yolos-small checkpoint.
|
28 |
|
29 |
## Intended uses & limitations
|
30 |
|
31 |
-
|
32 |
|
33 |
## Training and evaluation data
|
34 |
|
35 |
-
|
36 |
|
37 |
## Training procedure
|
38 |
|
@@ -48,6 +50,22 @@ The following hyperparameters were used during training:
|
|
48 |
- num_epochs: 18
|
49 |
|
50 |
### Training results
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
### Framework versions
|
53 |
|
|
|
22 |
|
23 |
## Model description
|
24 |
|
25 |
+
For more information on how it was created, check out the following link: https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/tree/main/Computer%20Vision/Object%20Detection/Trained%2C%20But%20to%20Standard/NFL%20Object%20Detection/Successful%20Attempt
|
26 |
+
|
27 |
+
* Fine-tuning and evaluation of this model are in separate files.
|
28 |
|
29 |
** If you plan on fine-tuning an Object Detection model on the NFL Helmet detection dataset, I would recommend using (at least) the Yolos-small checkpoint.
|
30 |
|
31 |
## Intended uses & limitations
|
32 |
|
33 |
+
This model is intended to demonstrate my ability to solve a complex problem using technology.
|
34 |
|
35 |
## Training and evaluation data
|
36 |
|
37 |
+
Dataset Source: https://huggingface.co/datasets/keremberke/nfl-object-detection
|
38 |
|
39 |
## Training procedure
|
40 |
|
|
|
50 |
- num_epochs: 18
|
51 |
|
52 |
### Training results
|
53 |
+
|
54 |
+
| Metric Name | IoU | Area | maxDets | Metric Value |
|
55 |
+
|:-----:|:-----:|:-----:|:-----:|:-----:|
|
56 |
+
| Average Precision (AP) | IoU=0.50:0.95 | area= all | maxDets=100 | 0.003 |
|
57 |
+
| Average Precision (AP) | IoU=0.50 | area= all | maxDets=100 | 0.010 |
|
58 |
+
| Average Precision (AP) | IoU=0.75 | area= all | maxDets=100 | 0.000 |
|
59 |
+
| Average Precision (AP) | IoU=0.50:0.95 | area= small | maxDets=100 | 0.002 |
|
60 |
+
| Average Precision (AP) | IoU=0.50:0.95 | area=medium | maxDets=100 | 0.014 |
|
61 |
+
| Average Precision (AP) | IoU=0.50:0.95 | area= large | maxDets=100 | 0.000 |
|
62 |
+
| Average Recall (AR) | IoU=0.50:0.95 | area= all | maxDets= 1 | 0.002 |
|
63 |
+
| Average Recall (AR) | IoU=0.50:0.95 | area= all | maxDets= 10 | 0.014 |
|
64 |
+
| Average Recall (AR) | IoU=0.50:0.95 | area= all | maxDets=100 | 0.029 |
|
65 |
+
| Average Recall (AR) | IoU=0.50:0.95 | area= small | maxDets=100 | 0.026 |
|
66 |
+
| Average Recall (AR) | IoU=0.50:0.95 | area=medium | maxDets=100 | 0.105 |
|
67 |
+
| Average Recall (AR) | IoU=0.50:0.95 | area= large | maxDets=100 | 0.000 |
|
68 |
+
|
69 |
|
70 |
### Framework versions
|
71 |
|