Hugging Face's logo

LynnKukunda
/
swin-tiny-patch4-window7-224-image-classifier

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
LynnKukunda commited on
Commit
12cc147
•
1 Parent(s): 2747a0e

Model save

Browse files
Files changed (3) hide show
  1. README.md +20 -18
  2. model.safetensors +1 -1
  3. runs/Nov06_07-46-58_21912a04e3af/events.out.tfevents.1730879242.21912a04e3af.4012.0 +2 -2
README.md CHANGED
@@ -26,16 +26,16 @@ model-index:
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
- value: 0.748792270531401
30
  - name: F1
31
  type: f1
32
- value: 0.655421686746988
33
  - name: Precision
34
  type: precision
35
- value: 0.6267281105990783
36
  - name: Recall
37
  type: recall
38
- value: 0.6868686868686869
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,11 +45,11 @@ should probably proofread and complete it, then remove this comment. -->
45
 
46
  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.
47
  It achieves the following results on the evaluation set:
48
- - Loss: 0.4362
49
- - Accuracy: 0.7488
50
- - F1: 0.6554
51
- - Precision: 0.6267
52
- - Recall: 0.6869
53
 
54
  ## Model description
55
 
@@ -75,22 +75,24 @@ The following hyperparameters were used during training:
75
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
76
  - lr_scheduler_type: linear
77
  - lr_scheduler_warmup_ratio: 0.1
78
- - num_epochs: 5
79
 
80
  ### Training results
81
 
82
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
83
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
84
- | 0.5982 | 1.0 | 143 | 0.5693 | 0.6711 | 0.4144 | 0.5441 | 0.3346 |
85
- | 0.4391 | 2.0 | 286 | 0.4924 | 0.7295 | 0.4849 | 0.7178 | 0.3662 |
86
- | 0.3658 | 3.0 | 429 | 0.4332 | 0.7501 | 0.6459 | 0.6368 | 0.6553 |
87
- | 0.3404 | 4.0 | 572 | 0.4202 | 0.7694 | 0.6525 | 0.6857 | 0.6225 |
88
- | 0.3188 | 5.0 | 715 | 0.4362 | 0.7488 | 0.6554 | 0.6267 | 0.6869 |
 
 
89
 
90
 
91
  ### Framework versions
92
 
93
- - Transformers 4.46.0
94
  - Pytorch 2.5.0+cu121
95
- - Datasets 3.0.2
96
- - Tokenizers 0.20.1
 
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
+ value: 0.7167325428194994
30
  - name: F1
31
  type: f1
32
+ value: 0.6734177215189874
33
  - name: Precision
34
  type: precision
35
+ value: 0.5621301775147929
36
  - name: Recall
37
  type: recall
38
+ value: 0.8396464646464646
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
45
 
46
  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.
47
  It achieves the following results on the evaluation set:
48
+ - Loss: 0.5309
49
+ - Accuracy: 0.7167
50
+ - F1: 0.6734
51
+ - Precision: 0.5621
52
+ - Recall: 0.8396
53
 
54
  ## Model description
55
 
 
75
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
76
  - lr_scheduler_type: linear
77
  - lr_scheduler_warmup_ratio: 0.1
78
+ - num_epochs: 30
79
 
80
  ### Training results
81
 
82
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
83
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
84
+ | 0.6658 | 1.0 | 143 | 0.6313 | 0.6421 | 0.0512 | 0.3284 | 0.0278 |
85
+ | 0.5528 | 2.0 | 286 | 0.5433 | 0.6987 | 0.5396 | 0.5759 | 0.5076 |
86
+ | 0.417 | 3.0 | 429 | 0.4806 | 0.7273 | 0.6306 | 0.5962 | 0.6692 |
87
+ | 0.3738 | 4.0 | 572 | 0.4195 | 0.7668 | 0.6849 | 0.6461 | 0.7285 |
88
+ | 0.3385 | 5.0 | 715 | 0.5555 | 0.7141 | 0.6720 | 0.5591 | 0.8422 |
89
+ | 0.3274 | 6.0 | 858 | 0.5506 | 0.7159 | 0.6646 | 0.5638 | 0.8093 |
90
+ | 0.3176 | 7.0 | 1001 | 0.5309 | 0.7167 | 0.6734 | 0.5621 | 0.8396 |
91
 
92
 
93
  ### Framework versions
94
 
95
+ - Transformers 4.46.2
96
  - Pytorch 2.5.0+cu121
97
+ - Datasets 3.1.0
98
+ - Tokenizers 0.20.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c199b2dda004ec78e93045e9e2826956449f4639215fbdde721fb2a6e77dc60f
3
  size 110342832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a07384a2f1a3656b69c0782064617644d24ec8f1b91abad96229cc3b0e2f414c
3
  size 110342832
runs/Nov06_07-46-58_21912a04e3af/events.out.tfevents.1730879242.21912a04e3af.4012.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:759b399a006219d9bf38f13099d65aa7c42ffd95dc531bc2d30e8ff9917f6075
3
- size 9604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d5c9d7fe5bf49d510f766d9a84a4fd4f6370ca5e347ecf5a7611ea51303969
3
+ size 10641