Hugging Face's logo

MichalGas
/
swin-tiny-patch4-window7-224-finetuned-mgasior-2024

Image Classification
Transformers
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
MichalGas commited on
Commit
0883900
•
1 Parent(s): a12be0c

Model save

Browse files
Files changed (1) hide show
  1. README.md +8 -16
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.2047244094488189
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 [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 9249980871081984.0
36
- - Accuracy: 0.2047
37
 
38
  ## Model description
39
 
@@ -61,22 +61,14 @@ 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: 10
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
- |:----------------------:|:-----:|:----:|:----------------------:|:--------:|
70
- | No log | 1.0 | 9 | 12739158615261184.0000 | 0.2047 |
71
- | 49989753141356136.0000 | 2.0 | 18 | 16698140283371520.0000 | 0.2047 |
72
- | 33409942428214888.0000 | 3.0 | 27 | 20547361914748928.0000 | 0.2283 |
73
- | 17126365917400268.0000 | 4.0 | 36 | 11163631467102208.0000 | 0.2047 |
74
- | 11563202153073868.0000 | 5.0 | 45 | 12371938911453184.0000 | 0.2283 |
75
- | 10920572825370624.0000 | 6.0 | 54 | 9788674996699136.0 | 0.2047 |
76
- | 9718191576894668.0 | 7.0 | 63 | 9368427479171072.0 | 0.2047 |
77
- | 10115938190255718.0000 | 8.0 | 72 | 9327990362079232.0 | 0.2047 |
78
- | 9208841097340518.0 | 9.0 | 81 | 9341989807980544.0 | 0.2047 |
79
- | 9442684027745076.0 | 10.0 | 90 | 9249980871081984.0 | 0.2047 |
80
 
81
 
82
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.2283464566929134
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 [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: nan
36
+ - Accuracy: 0.2283
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: 2
65
 
66
  ### Training results
67
 
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 1.0 | 9 | nan | 0.2283 |
71
+ | 0.0 | 2.0 | 18 | nan | 0.2283 |
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions