Hugging Face's logo

gcperk20
/
deit-base-patch16-224-finetuned-piid

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
gcperk20 commited on
Commit
21a622e
•
1 Parent(s): 23b3c78

Model save

Browse files
Files changed (2) hide show
  1. README.md +9 -24
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.7671232876712328
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.6517
36
- - Accuracy: 0.7671
37
 
38
  ## Model description
39
 
@@ -61,32 +61,17 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 20
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 1.2042 | 0.98 | 20 | 1.0729 | 0.5205 |
71
- | 0.6598 | 2.0 | 41 | 0.8122 | 0.6347 |
72
- | 0.5258 | 2.98 | 61 | 0.7352 | 0.6575 |
73
- | 0.4436 | 4.0 | 82 | 0.5681 | 0.7534 |
74
- | 0.357 | 4.98 | 102 | 0.5911 | 0.7489 |
75
- | 0.2805 | 6.0 | 123 | 0.4971 | 0.7671 |
76
- | 0.2265 | 6.98 | 143 | 0.5661 | 0.7671 |
77
- | 0.2144 | 8.0 | 164 | 0.5481 | 0.7717 |
78
- | 0.1835 | 8.98 | 184 | 0.5900 | 0.7580 |
79
- | 0.1843 | 10.0 | 205 | 0.5127 | 0.7808 |
80
- | 0.1671 | 10.98 | 225 | 0.6573 | 0.7808 |
81
- | 0.1492 | 12.0 | 246 | 0.6162 | 0.7534 |
82
- | 0.1155 | 12.98 | 266 | 0.5823 | 0.7854 |
83
- | 0.1268 | 14.0 | 287 | 0.6223 | 0.7626 |
84
- | 0.1405 | 14.98 | 307 | 0.6135 | 0.7580 |
85
- | 0.0656 | 16.0 | 328 | 0.6013 | 0.7671 |
86
- | 0.0494 | 16.98 | 348 | 0.6420 | 0.7717 |
87
- | 0.1022 | 18.0 | 369 | 0.6567 | 0.7671 |
88
- | 0.0539 | 18.98 | 389 | 0.6491 | 0.7626 |
89
- | 0.0656 | 19.51 | 400 | 0.6517 | 0.7671 |
90
 
91
 
92
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.776255707762557
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.6370
36
+ - Accuracy: 0.7763
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 5
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.1097 | 0.98 | 20 | 0.7891 | 0.7352 |
71
+ | 0.1546 | 2.0 | 41 | 0.6625 | 0.7991 |
72
+ | 0.0808 | 2.98 | 61 | 0.6878 | 0.7945 |
73
+ | 0.0698 | 4.0 | 82 | 0.6370 | 0.7854 |
74
+ | 0.0861 | 4.88 | 100 | 0.6370 | 0.7763 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d6312d2ed4b71cf0cda8262ddf12f04bce641e47af18c34afb2219498d631d7
3
  size 343230128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:489a19b36822e95adcde8352abb64ef32282d2772a7802bc6d7b162f15cb9337
3
  size 343230128