Model save
Browse files
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
| 3 |
base_model: microsoft/swinv2-base-patch4-window12-192-22k
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: SWIN_finetuned_frozen_v5_cont
|
| 8 |
results: []
|
|
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# SWIN_finetuned_frozen_v5_cont
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window12-192-22k](https://huggingface.co/microsoft/swinv2-base-patch4-window12-192-22k) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -40,6 +45,27 @@ The following hyperparameters were used during training:
|
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
- num_epochs: 15.0
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
### Framework versions
|
| 44 |
|
| 45 |
- Transformers 4.33.3
|
|
|
|
| 3 |
base_model: microsoft/swinv2-base-patch4-window12-192-22k
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: SWIN_finetuned_frozen_v5_cont
|
| 10 |
results: []
|
|
|
|
| 16 |
# SWIN_finetuned_frozen_v5_cont
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window12-192-22k](https://huggingface.co/microsoft/swinv2-base-patch4-window12-192-22k) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.1793
|
| 21 |
+
- Accuracy: 0.7000
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- num_epochs: 15.0
|
| 47 |
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:--------:|:---------------:|
|
| 52 |
+
| 0.6306 | 1.0 | 2625 | 0.6565 | 1.9169 |
|
| 53 |
+
| 0.5977 | 2.0 | 5250 | 0.6614 | 1.9120 |
|
| 54 |
+
| 0.5472 | 3.0 | 7875 | 0.6635 | 1.9410 |
|
| 55 |
+
| 0.513 | 4.0 | 10500 | 0.6679 | 1.9818 |
|
| 56 |
+
| 0.4714 | 5.0 | 13125 | 0.6711 | 1.9428 |
|
| 57 |
+
| 0.4378 | 6.0 | 15750 | 0.6727 | 2.0051 |
|
| 58 |
+
| 0.4105 | 7.0 | 18375 | 0.6778 | 1.9917 |
|
| 59 |
+
| 0.3837 | 8.0 | 21000 | 0.6792 | 2.0413 |
|
| 60 |
+
| 0.3602 | 9.0 | 23625 | 0.6870 | 2.0738 |
|
| 61 |
+
| 0.336 | 10.0 | 26250 | 2.0872 | 0.6876 |
|
| 62 |
+
| 0.3057 | 11.0 | 28875 | 2.1163 | 0.6894 |
|
| 63 |
+
| 0.2856 | 12.0 | 31500 | 2.1105 | 0.6936 |
|
| 64 |
+
| 0.2704 | 13.0 | 34125 | 2.1685 | 0.6965 |
|
| 65 |
+
| 0.2503 | 14.0 | 36750 | 2.1627 | 0.6994 |
|
| 66 |
+
| 0.2362 | 15.0 | 39375 | 2.1793 | 0.7000 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
### Framework versions
|
| 70 |
|
| 71 |
- Transformers 4.33.3
|