Hugging Face's logo

c14kevincardenas
/
swin-base-patch4-window7-224-limb

Image Classification
Transformers
Safetensors
swin
Generated from Trainer
Model card Files Community
c14kevincardenas commited on
Commit
36b5cb4
·
verified ·
1 Parent(s): 9d6b3e1

Model save

Browse files
Files changed (1) hide show
  1. README.md +12 -40
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.1379
21
- - Accuracy: 0.3443
22
 
23
  ## Model description
24
 
@@ -37,51 +37,23 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 5e-05
41
- - train_batch_size: 16
42
  - eval_batch_size: 32
43
  - seed: 2014
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - lr_scheduler_warmup_steps: 500
47
- - num_epochs: 30.0
48
- - mixed_precision_training: Native AMP
49
- - label_smoothing_factor: 0.005
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
55
- | 1.3808 | 1.0 | 430 | 1.3697 | 0.2784 |
56
- | 1.3049 | 2.0 | 860 | 1.3162 | 0.3064 |
57
- | 1.2812 | 3.0 | 1290 | 1.2160 | 0.3542 |
58
- | 1.251 | 4.0 | 1720 | 1.1974 | 0.3888 |
59
- | 1.2299 | 5.0 | 2150 | 1.2131 | 0.3682 |
60
- | 1.1893 | 6.0 | 2580 | 1.1981 | 0.3723 |
61
- | 1.2086 | 7.0 | 3010 | 1.1456 | 0.3888 |
62
- | 1.1446 | 8.0 | 3440 | 1.1768 | 0.3995 |
63
- | 1.1674 | 9.0 | 3870 | 1.2034 | 0.3929 |
64
- | 1.1669 | 10.0 | 4300 | 1.1405 | 0.3814 |
65
- | 1.1222 | 11.0 | 4730 | 1.1754 | 0.4053 |
66
- | 1.0746 | 12.0 | 5160 | 1.1145 | 0.3806 |
67
- | 1.099 | 13.0 | 5590 | 1.1603 | 0.3847 |
68
- | 1.091 | 14.0 | 6020 | 1.2087 | 0.3896 |
69
- | 1.1036 | 15.0 | 6450 | 1.1176 | 0.3789 |
70
- | 1.102 | 16.0 | 6880 | 1.1326 | 0.3962 |
71
- | 1.0636 | 17.0 | 7310 | 1.2310 | 0.3682 |
72
- | 1.0596 | 18.0 | 7740 | 1.1264 | 0.4036 |
73
- | 1.0466 | 19.0 | 8170 | 1.1538 | 0.3888 |
74
- | 1.0871 | 20.0 | 8600 | 1.1214 | 0.3913 |
75
- | 1.0297 | 21.0 | 9030 | 1.1939 | 0.3773 |
76
- | 1.0592 | 22.0 | 9460 | 1.1255 | 0.3797 |
77
- | 0.9917 | 23.0 | 9890 | 1.1393 | 0.3822 |
78
- | 1.0265 | 24.0 | 10320 | 1.1602 | 0.3633 |
79
- | 1.0104 | 25.0 | 10750 | 1.1987 | 0.3904 |
80
- | 0.9815 | 26.0 | 11180 | 1.1445 | 0.3880 |
81
- | 0.9899 | 27.0 | 11610 | 1.1615 | 0.3682 |
82
- | 0.9826 | 28.0 | 12040 | 1.1363 | 0.3567 |
83
- | 1.0595 | 29.0 | 12470 | 1.1339 | 0.3517 |
84
- | 0.995 | 30.0 | 12900 | 1.1379 | 0.3443 |
85
 
86
 
87
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.1854
21
+ - Accuracy: 0.3435
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 3e-05
41
+ - train_batch_size: 32
42
  - eval_batch_size: 32
43
  - seed: 2014
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 5.0
 
 
 
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 1.3555 | 1.0 | 215 | 1.3151 | 0.3196 |
53
+ | 1.275 | 2.0 | 430 | 1.2243 | 0.3756 |
54
+ | 1.2304 | 3.0 | 645 | 1.1982 | 0.3690 |
55
+ | 1.2137 | 4.0 | 860 | 1.1938 | 0.3674 |
56
+ | 1.2153 | 5.0 | 1075 | 1.1854 | 0.3435 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions