Commit ·
4e14ed0
1
Parent(s): d745411
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,26 +13,16 @@ model-index:
|
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
-
#
|
| 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: 0.4297
|
| 21 |
-
- Accuracy: 0.9435
|
| 22 |
-
|
| 23 |
## Model description
|
|
|
|
| 24 |
|
| 25 |
-
|
| 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 |
|
|
@@ -48,32 +38,6 @@ The following hyperparameters were used during training:
|
|
| 48 |
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
- num_epochs: 20
|
| 50 |
|
| 51 |
-
### Training results
|
| 52 |
-
|
| 53 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 54 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 55 |
-
| 2.5255 | 0.99 | 23 | 2.4636 | 0.1962 |
|
| 56 |
-
| 2.3262 | 1.98 | 46 | 2.1597 | 0.4274 |
|
| 57 |
-
| 2.0029 | 2.97 | 69 | 1.8305 | 0.5403 |
|
| 58 |
-
| 1.558 | 4.0 | 93 | 1.5122 | 0.6640 |
|
| 59 |
-
| 1.3011 | 4.99 | 116 | 1.2433 | 0.7608 |
|
| 60 |
-
| 1.1253 | 5.98 | 139 | 1.0914 | 0.7957 |
|
| 61 |
-
| 0.9237 | 6.97 | 162 | 0.9167 | 0.8575 |
|
| 62 |
-
| 0.8187 | 8.0 | 186 | 0.8292 | 0.8575 |
|
| 63 |
-
| 0.7327 | 8.99 | 209 | 0.7518 | 0.8925 |
|
| 64 |
-
| 0.6148 | 9.98 | 232 | 0.7226 | 0.8737 |
|
| 65 |
-
| 0.5614 | 10.97 | 255 | 0.6537 | 0.9032 |
|
| 66 |
-
| 0.5541 | 12.0 | 279 | 0.5922 | 0.9274 |
|
| 67 |
-
| 0.5033 | 12.99 | 302 | 0.5969 | 0.9140 |
|
| 68 |
-
| 0.4829 | 13.98 | 325 | 0.5295 | 0.9247 |
|
| 69 |
-
| 0.4428 | 14.97 | 348 | 0.4993 | 0.9328 |
|
| 70 |
-
| 0.3965 | 16.0 | 372 | 0.4925 | 0.9382 |
|
| 71 |
-
| 0.3964 | 16.99 | 395 | 0.4996 | 0.9220 |
|
| 72 |
-
| 0.3957 | 17.98 | 418 | 0.4546 | 0.9435 |
|
| 73 |
-
| 0.3868 | 18.97 | 441 | 0.4281 | 0.9382 |
|
| 74 |
-
| 0.3824 | 19.78 | 460 | 0.4297 | 0.9435 |
|
| 75 |
-
|
| 76 |
-
|
| 77 |
### Framework versions
|
| 78 |
|
| 79 |
- Transformers 4.34.0
|
|
|
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
+
# Fashion Model Prediction
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
## Model description
|
| 18 |
+
This model predicts the name of the fashion model in the image. It is trained on [Lucy in the Sky](https://www.lucyinthesky.com/shop) images.
|
| 19 |
|
| 20 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k).
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Training and evaluation data
|
| 23 |
+
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.4297
|
| 25 |
+
- Accuracy: 0.9435
|
|
|
|
| 26 |
|
| 27 |
### Training hyperparameters
|
| 28 |
|
|
|
|
| 38 |
- lr_scheduler_warmup_ratio: 0.1
|
| 39 |
- num_epochs: 20
|
| 40 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
### Framework versions
|
| 42 |
|
| 43 |
- Transformers 4.34.0
|