Commit
•
f880b7c
1
Parent(s):
996259e
Model save
Browse files
README.md
CHANGED
@@ -2,7 +2,6 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: microsoft/swinv2-tiny-patch4-window16-256
|
4 |
tags:
|
5 |
-
- image-classification
|
6 |
- generated_from_trainer
|
7 |
metrics:
|
8 |
- accuracy
|
@@ -16,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# test-seed
|
18 |
|
19 |
-
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window16-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window16-256) on
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Accuracy: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -41,7 +40,7 @@ The following hyperparameters were used during training:
|
|
41 |
- learning_rate: 0.0003
|
42 |
- train_batch_size: 64
|
43 |
- eval_batch_size: 16
|
44 |
-
- seed:
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- num_epochs: 2
|
@@ -50,8 +49,8 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
-
| No log | 1.0 | 10 | 0.
|
54 |
-
| No log | 2.0 | 20 | 0.
|
55 |
|
56 |
|
57 |
### Framework versions
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: microsoft/swinv2-tiny-patch4-window16-256
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- accuracy
|
|
|
15 |
|
16 |
# test-seed
|
17 |
|
18 |
+
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window16-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window16-256) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.6797
|
21 |
+
- Accuracy: 0.75
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
40 |
- learning_rate: 0.0003
|
41 |
- train_batch_size: 64
|
42 |
- eval_batch_size: 16
|
43 |
+
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
- num_epochs: 2
|
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| No log | 1.0 | 10 | 0.6739 | 0.7375 |
|
53 |
+
| No log | 2.0 | 20 | 0.4469 | 0.875 |
|
54 |
|
55 |
|
56 |
### Framework versions
|
runs/May19_14-53-04_262db849d6b2/events.out.tfevents.1716130447.262db849d6b2.34.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c75e032147fb2787406bfdc164e6d56c22b40f677694ba38bf972c11fc210613
|
3 |
+
size 405
|