Update README.md
Browse files
README.md
CHANGED
|
@@ -14,25 +14,16 @@ model-index:
|
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
# fashion-clothing-decade
|
|
|
|
|
|
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
|
| 19 |
-
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.8707
|
| 21 |
-
- Accuracy: 0.7505
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
-
|
| 25 |
-
More information needed
|
| 26 |
-
|
| 27 |
-
## Intended uses & limitations
|
| 28 |
-
|
| 29 |
-
More information needed
|
| 30 |
|
| 31 |
## Training and evaluation data
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
## Training procedure
|
| 36 |
|
| 37 |
### Training hyperparameters
|
| 38 |
|
|
@@ -48,22 +39,6 @@ The following hyperparameters were used during training:
|
|
| 48 |
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
- num_epochs: 10
|
| 50 |
|
| 51 |
-
### Training results
|
| 52 |
-
|
| 53 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 54 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 55 |
-
| 0.2495 | 0.98 | 31 | 0.9186 | 0.7305 |
|
| 56 |
-
| 0.2302 | 2.0 | 63 | 0.8839 | 0.7265 |
|
| 57 |
-
| 0.1951 | 2.98 | 94 | 0.9035 | 0.7006 |
|
| 58 |
-
| 0.1658 | 4.0 | 126 | 1.0236 | 0.6986 |
|
| 59 |
-
| 0.1796 | 4.98 | 157 | 0.8573 | 0.7246 |
|
| 60 |
-
| 0.1592 | 6.0 | 189 | 0.9642 | 0.7086 |
|
| 61 |
-
| 0.1523 | 6.98 | 220 | 0.9553 | 0.7046 |
|
| 62 |
-
| 0.1531 | 8.0 | 252 | 0.9164 | 0.7425 |
|
| 63 |
-
| 0.2108 | 8.98 | 283 | 0.8650 | 0.7505 |
|
| 64 |
-
| 0.2468 | 9.84 | 310 | 0.8707 | 0.7505 |
|
| 65 |
-
|
| 66 |
-
|
| 67 |
### Framework versions
|
| 68 |
|
| 69 |
- Transformers 4.35.0
|
|
|
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
# fashion-clothing-decade
|
| 17 |
+
This model predicts what decade clothing is from. It takes an image and outputs one of the following labels:
|
| 18 |
+
**1910s, 1920s, 1930s, 1940s, 1950s, 1960s, 1970s, 1980s, 1990s, 2000s**
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## Training and evaluation data
|
| 25 |
+
- Loss: 0.8707
|
| 26 |
+
- Accuracy: 0.7505
|
|
|
|
|
|
|
| 27 |
|
| 28 |
### Training hyperparameters
|
| 29 |
|
|
|
|
| 39 |
- lr_scheduler_warmup_ratio: 0.1
|
| 40 |
- num_epochs: 10
|
| 41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
### Framework versions
|
| 43 |
|
| 44 |
- Transformers 4.35.0
|