Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
## Model description
|
| 18 |
This model classifies an image into a fashion collection. It is trained on the [tonyassi/vogue-runway-top15-512px-nobg](https://huggingface.co/datasets/tonyassi/vogue-runway-top15-512px-nobg) dataset and fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k).
|
| 19 |
|
| 20 |
-
|
| 21 |
## Dataset description
|
| 22 |
[tonyassi/vogue-runway-top15-512px-nobg](https://huggingface.co/datasets/tonyassi/vogue-runway-top15-512px-nobg)
|
| 23 |
- 15 fashion houses
|
|
@@ -25,15 +24,26 @@ This model classifies an image into a fashion collection. It is trained on the [
|
|
| 25 |
- 87,547 images
|
| 26 |
- No background
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
## Training and evaluation data
|
| 29 |
It achieves the following results on the evaluation set:
|
| 30 |
- Loss: 0.5880
|
| 31 |
- Accuracy: 0.8403
|
| 32 |
|
| 33 |
-
## Training procedure
|
| 34 |
-
|
| 35 |
### Training hyperparameters
|
| 36 |
-
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 5e-05
|
| 39 |
- train_batch_size: 16
|
|
@@ -46,22 +56,6 @@ The following hyperparameters were used during training:
|
|
| 46 |
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
- num_epochs: 10
|
| 48 |
|
| 49 |
-
### Training results
|
| 50 |
-
|
| 51 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
-
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 53 |
-
| 0.3837 | 1.0 | 1094 | 0.9024 | 0.7864 |
|
| 54 |
-
| 0.3265 | 2.0 | 2189 | 0.8589 | 0.7840 |
|
| 55 |
-
| 0.2869 | 3.0 | 3283 | 0.8385 | 0.7898 |
|
| 56 |
-
| 0.2642 | 4.0 | 4378 | 0.8290 | 0.7913 |
|
| 57 |
-
| 0.2136 | 5.0 | 5472 | 0.7269 | 0.8107 |
|
| 58 |
-
| 0.2273 | 6.0 | 6567 | 0.6998 | 0.8176 |
|
| 59 |
-
| 0.2397 | 7.0 | 7661 | 0.6760 | 0.8218 |
|
| 60 |
-
| 0.1888 | 8.0 | 8756 | 0.6562 | 0.8259 |
|
| 61 |
-
| 0.1783 | 9.0 | 9850 | 0.6174 | 0.8331 |
|
| 62 |
-
| 0.237 | 10.0 | 10940 | 0.5880 | 0.8403 |
|
| 63 |
-
|
| 64 |
-
|
| 65 |
### Framework versions
|
| 66 |
|
| 67 |
- Transformers 4.35.2
|
|
|
|
| 17 |
## Model description
|
| 18 |
This model classifies an image into a fashion collection. It is trained on the [tonyassi/vogue-runway-top15-512px-nobg](https://huggingface.co/datasets/tonyassi/vogue-runway-top15-512px-nobg) dataset and fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k).
|
| 19 |
|
|
|
|
| 20 |
## Dataset description
|
| 21 |
[tonyassi/vogue-runway-top15-512px-nobg](https://huggingface.co/datasets/tonyassi/vogue-runway-top15-512px-nobg)
|
| 22 |
- 15 fashion houses
|
|
|
|
| 24 |
- 87,547 images
|
| 25 |
- No background
|
| 26 |
|
| 27 |
+
### How to use
|
| 28 |
+
```python
|
| 29 |
+
from transformers import pipeline
|
| 30 |
+
|
| 31 |
+
# Initialize image classification pipeline
|
| 32 |
+
pipe = pipeline("image-classification", model="tonyassi/vogue-fashion-collection-15-nobg")
|
| 33 |
+
|
| 34 |
+
# Perform classification
|
| 35 |
+
result = pipe('image.png')
|
| 36 |
+
|
| 37 |
+
# Print results
|
| 38 |
+
print(result)
|
| 39 |
+
```
|
| 40 |
+
|
| 41 |
## Training and evaluation data
|
| 42 |
It achieves the following results on the evaluation set:
|
| 43 |
- Loss: 0.5880
|
| 44 |
- Accuracy: 0.8403
|
| 45 |
|
|
|
|
|
|
|
| 46 |
### Training hyperparameters
|
|
|
|
| 47 |
The following hyperparameters were used during training:
|
| 48 |
- learning_rate: 5e-05
|
| 49 |
- train_batch_size: 16
|
|
|
|
| 56 |
- lr_scheduler_warmup_ratio: 0.1
|
| 57 |
- num_epochs: 10
|
| 58 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
### Framework versions
|
| 60 |
|
| 61 |
- Transformers 4.35.2
|