Hugging Face's logo

HorcruxNo13
/
swin-tiny-patch4-window7-224

Image Classification
Transformers
PyTorch
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
HorcruxNo13 commited on
Commit
230b866
•
1 Parent(s): df9c617

Model save

Browse files
Files changed (2) hide show
  1. README.md +27 -22
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -24,13 +24,13 @@ model-index:
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.76
28
  - name: Precision
29
  type: precision
30
- value: 0.7692631578947368
31
  - name: Recall
32
  type: recall
33
- value: 0.76
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,11 +40,11 @@ should probably proofread and complete it, then remove this comment. -->
40
 
41
  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.
42
  It achieves the following results on the evaluation set:
43
- - Loss: 0.5138
44
- - Accuracy: 0.76
45
- - Precision: 0.7693
46
- - Recall: 0.76
47
- - F1 Score: 0.6932
48
 
49
  ## Model description
50
 
@@ -64,30 +64,35 @@ More information needed
64
 
65
  The following hyperparameters were used during training:
66
  - learning_rate: 5e-05
67
- - train_batch_size: 32
68
- - eval_batch_size: 32
69
  - seed: 42
70
  - gradient_accumulation_steps: 4
71
- - total_train_batch_size: 128
72
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
  - lr_scheduler_type: linear
74
  - lr_scheduler_warmup_ratio: 0.1
75
- - num_epochs: 10
76
 
77
  ### Training results
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
80
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
81
- | No log | 1.0 | 8 | 0.5844 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
82
- | 0.6556 | 2.0 | 16 | 0.5703 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
83
- | 0.5707 | 3.0 | 24 | 0.5585 | 0.7417 | 0.8090 | 0.7417 | 0.6397 |
84
- | 0.5383 | 4.0 | 32 | 0.6247 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
85
- | 0.5149 | 5.0 | 40 | 0.5308 | 0.7792 | 0.7885 | 0.7792 | 0.7281 |
86
- | 0.5149 | 6.0 | 48 | 0.5445 | 0.7833 | 0.8155 | 0.7833 | 0.7274 |
87
- | 0.4879 | 7.0 | 56 | 0.5620 | 0.7667 | 0.7709 | 0.7667 | 0.7064 |
88
- | 0.453 | 8.0 | 64 | 0.5384 | 0.7708 | 0.7695 | 0.7708 | 0.7178 |
89
- | 0.4249 | 9.0 | 72 | 0.5377 | 0.7542 | 0.7276 | 0.7542 | 0.7054 |
90
- | 0.4001 | 10.0 | 80 | 0.5417 | 0.7667 | 0.7575 | 0.7667 | 0.7147 |
 
 
 
 
 
91
 
92
 
93
  ### Framework versions
 
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
+ value: 0.7133333333333334
28
  - name: Precision
29
  type: precision
30
+ value: 0.6732516172965611
31
  - name: Recall
32
  type: recall
33
+ value: 0.7133333333333334
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
40
 
41
  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.
42
  It achieves the following results on the evaluation set:
43
+ - Loss: 0.5797
44
+ - Accuracy: 0.7133
45
+ - Precision: 0.6733
46
+ - Recall: 0.7133
47
+ - F1 Score: 0.6650
48
 
49
  ## Model description
50
 
 
64
 
65
  The following hyperparameters were used during training:
66
  - learning_rate: 5e-05
67
+ - train_batch_size: 64
68
+ - eval_batch_size: 64
69
  - seed: 42
70
  - gradient_accumulation_steps: 4
71
+ - total_train_batch_size: 256
72
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
  - lr_scheduler_type: linear
74
  - lr_scheduler_warmup_ratio: 0.1
75
+ - num_epochs: 15
76
 
77
  ### Training results
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
80
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
81
+ | No log | 1.0 | 4 | 0.5965 | 0.725 | 0.5256 | 0.725 | 0.6094 |
82
+ | No log | 2.0 | 8 | 0.6045 | 0.7125 | 0.5795 | 0.7125 | 0.6104 |
83
+ | No log | 3.0 | 12 | 0.5910 | 0.725 | 0.6645 | 0.725 | 0.6169 |
84
+ | 0.6165 | 4.0 | 16 | 0.5865 | 0.7333 | 0.7162 | 0.7333 | 0.6418 |
85
+ | 0.6165 | 5.0 | 20 | 0.5789 | 0.7292 | 0.6846 | 0.7292 | 0.6562 |
86
+ | 0.6165 | 6.0 | 24 | 0.5649 | 0.725 | 0.6702 | 0.725 | 0.6427 |
87
+ | 0.6165 | 7.0 | 28 | 0.5660 | 0.7375 | 0.7090 | 0.7375 | 0.6668 |
88
+ | 0.5966 | 8.0 | 32 | 0.5972 | 0.7375 | 0.7108 | 0.7375 | 0.7132 |
89
+ | 0.5966 | 9.0 | 36 | 0.5666 | 0.7417 | 0.7134 | 0.7417 | 0.6835 |
90
+ | 0.5966 | 10.0 | 40 | 0.5781 | 0.7417 | 0.7124 | 0.7417 | 0.7084 |
91
+ | 0.5966 | 11.0 | 44 | 0.6009 | 0.7083 | 0.6900 | 0.7083 | 0.6967 |
92
+ | 0.5921 | 12.0 | 48 | 0.5678 | 0.75 | 0.7244 | 0.75 | 0.7118 |
93
+ | 0.5921 | 13.0 | 52 | 0.5581 | 0.7583 | 0.7429 | 0.7583 | 0.7115 |
94
+ | 0.5921 | 14.0 | 56 | 0.5587 | 0.7542 | 0.7340 | 0.7542 | 0.7083 |
95
+ | 0.5847 | 15.0 | 60 | 0.5589 | 0.7542 | 0.7340 | 0.7542 | 0.7083 |
96
 
97
 
98
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e9cee0ba977ee09f797950bd854afbf6e2602169b674edda2c8ef14236251f1
3
  size 110394865
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b68c2bc6ebd608c3e0b55615cb3efbcd383f6472eed82b93280df5c3c35d5b
3
  size 110394865