Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,7 @@ metrics:
|
|
| 6 |
model-index:
|
| 7 |
- name: MobileNetV2-KD-VGGFace
|
| 8 |
results: []
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -13,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# MobileNetV2-KD-VGGFace
|
| 15 |
|
| 16 |
-
This model is
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 0.4919
|
| 19 |
- Accuracy: 0.7836
|
|
@@ -75,4 +76,4 @@ The following hyperparameters were used during training:
|
|
| 75 |
- Transformers 4.42.4
|
| 76 |
- Pytorch 2.3.1+rocm6.0
|
| 77 |
- Datasets 2.20.0
|
| 78 |
-
- Tokenizers 0.19.1
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: MobileNetV2-KD-VGGFace
|
| 8 |
results: []
|
| 9 |
+
license: mit
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 14 |
|
| 15 |
# MobileNetV2-KD-VGGFace
|
| 16 |
|
| 17 |
+
This model is trained via KD from [ViT](https://huggingface.co/skutaada/VIT-VGGFace) on first 50k samples of VGGFace dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
- Loss: 0.4919
|
| 20 |
- Accuracy: 0.7836
|
|
|
|
| 76 |
- Transformers 4.42.4
|
| 77 |
- Pytorch 2.3.1+rocm6.0
|
| 78 |
- Datasets 2.20.0
|
| 79 |
+
- Tokenizers 0.19.1
|