Hugging Face's logo

djbp
/
swin-tiny-patch4-window7-224-MM_Classification

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
djbp commited on
Commit
633ca15
·
verified ·
1 Parent(s): ccec340

Model save

Browse files
Files changed (2) hide show
  1. README.md +27 -17
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,12 +17,12 @@ model-index:
17
  name: imagefolder
18
  type: imagefolder
19
  config: default
20
- split: train
21
  args: default
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8947939262472885
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: 0.2758
36
- - Accuracy: 0.8948
37
 
38
  ## Model description
39
 
@@ -61,22 +61,32 @@ 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
- | 1.0041 | 0.9846 | 16 | 0.6399 | 0.7082 |
71
- | 0.4441 | 1.9692 | 32 | 0.3671 | 0.8688 |
72
- | 0.3563 | 2.9538 | 48 | 0.3454 | 0.8688 |
73
- | 0.3071 | 4.0 | 65 | 0.3100 | 0.8861 |
74
- | 0.2933 | 4.9846 | 81 | 0.2900 | 0.8894 |
75
- | 0.2841 | 5.9692 | 97 | 0.2917 | 0.8829 |
76
- | 0.2715 | 6.9538 | 113 | 0.2846 | 0.8894 |
77
- | 0.2564 | 8.0 | 130 | 0.2835 | 0.8926 |
78
- | 0.2639 | 8.9846 | 146 | 0.2799 | 0.8926 |
79
- | 0.2505 | 9.8462 | 160 | 0.2758 | 0.8948 |
 
 
 
 
 
 
 
 
 
 
80
 
81
 
82
  ### Framework versions
 
17
  name: imagefolder
18
  type: imagefolder
19
  config: default
20
+ split: validation
21
  args: default
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8693982074263764
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: 0.3455
36
+ - Accuracy: 0.8694
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: 20
65
 
66
  ### Training results
67
 
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.0476 | 1.0 | 19 | 0.7707 | 0.6530 |
71
+ | 0.6226 | 2.0 | 38 | 0.4743 | 0.8105 |
72
+ | 0.4477 | 3.0 | 57 | 0.4133 | 0.8323 |
73
+ | 0.3963 | 4.0 | 76 | 0.3813 | 0.8476 |
74
+ | 0.3694 | 5.0 | 95 | 0.3753 | 0.8540 |
75
+ | 0.3451 | 6.0 | 114 | 0.3587 | 0.8489 |
76
+ | 0.3382 | 7.0 | 133 | 0.3531 | 0.8451 |
77
+ | 0.3253 | 8.0 | 152 | 0.3498 | 0.8579 |
78
+ | 0.3121 | 9.0 | 171 | 0.3437 | 0.8579 |
79
+ | 0.2855 | 10.0 | 190 | 0.3447 | 0.8656 |
80
+ | 0.2961 | 11.0 | 209 | 0.3350 | 0.8617 |
81
+ | 0.273 | 12.0 | 228 | 0.3484 | 0.8566 |
82
+ | 0.2745 | 13.0 | 247 | 0.3433 | 0.8604 |
83
+ | 0.2613 | 14.0 | 266 | 0.3498 | 0.8643 |
84
+ | 0.2527 | 15.0 | 285 | 0.3365 | 0.8579 |
85
+ | 0.2619 | 16.0 | 304 | 0.3450 | 0.8617 |
86
+ | 0.2436 | 17.0 | 323 | 0.3454 | 0.8681 |
87
+ | 0.2518 | 18.0 | 342 | 0.3437 | 0.8681 |
88
+ | 0.243 | 19.0 | 361 | 0.3468 | 0.8694 |
89
+ | 0.2415 | 20.0 | 380 | 0.3455 | 0.8694 |
90
 
91
 
92
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bb80e155de0ad0ed2bddf877bad3db21620bc0bce1934d4c5eef063491b1692
3
  size 110345908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7616e2e97f031c3de68830913175e112f92106a038d70598bd83fdaff78743e1
3
  size 110345908