Hugging Face's logo

ahmedALM1221
/
swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-eurosat-50

Image Classification
Transformers
PyTorch
TensorBoard
swinv2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ahmedALM1221 commited on
Commit
ff97657
·
1 Parent(s): a1d64fa

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +36 -36
README.md CHANGED
@@ -15,13 +15,13 @@ model-index:
15
  dataset:
16
  name: imagefolder
17
  type: imagefolder
18
- config: Skin_Cancer
19
  split: train
20
- args: Skin_Cancer
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.8338983050847457
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft](https://huggingface.co/microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.5108
35
- - Accuracy: 0.8339
36
 
37
  ## Model description
38
 
@@ -59,43 +59,43 @@ The following hyperparameters were used during training:
59
  - total_train_batch_size: 64
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
- - lr_scheduler_warmup_ratio: 0.005
63
  - num_epochs: 30
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | No log | 0.97 | 18 | 1.3358 | 0.5017 |
70
- | 1.7327 | 2.0 | 37 | 0.9711 | 0.6102 |
71
- | 1.1314 | 2.97 | 55 | 0.6877 | 0.7254 |
72
- | 0.7956 | 4.0 | 74 | 0.6924 | 0.7458 |
73
- | 0.6511 | 4.97 | 92 | 0.7236 | 0.6915 |
74
- | 0.5609 | 6.0 | 111 | 0.5625 | 0.8169 |
75
- | 0.4585 | 6.97 | 129 | 0.5356 | 0.8102 |
76
- | 0.3988 | 8.0 | 148 | 0.8137 | 0.7186 |
77
- | 0.35 | 8.97 | 166 | 0.5569 | 0.8136 |
78
- | 0.3431 | 10.0 | 185 | 0.6979 | 0.7729 |
79
- | 0.2888 | 10.97 | 203 | 0.5444 | 0.8 |
80
- | 0.2553 | 12.0 | 222 | 0.6462 | 0.7729 |
81
- | 0.2263 | 12.97 | 240 | 0.5093 | 0.8373 |
82
- | 0.2263 | 14.0 | 259 | 0.5331 | 0.8169 |
83
- | 0.2323 | 14.97 | 277 | 0.5521 | 0.8203 |
84
- | 0.1601 | 16.0 | 296 | 0.5984 | 0.7831 |
85
- | 0.1645 | 16.97 | 314 | 0.6850 | 0.7932 |
86
- | 0.202 | 18.0 | 333 | 0.5786 | 0.8 |
87
- | 0.1762 | 18.97 | 351 | 0.5961 | 0.8305 |
88
- | 0.1546 | 20.0 | 370 | 0.6169 | 0.8373 |
89
- | 0.1583 | 20.97 | 388 | 0.4907 | 0.8373 |
90
- | 0.1168 | 22.0 | 407 | 0.4846 | 0.8508 |
91
- | 0.1193 | 22.97 | 425 | 0.5030 | 0.8475 |
92
- | 0.1275 | 24.0 | 444 | 0.5287 | 0.8373 |
93
- | 0.1214 | 24.97 | 462 | 0.5240 | 0.8407 |
94
- | 0.1107 | 26.0 | 481 | 0.5439 | 0.8407 |
95
- | 0.1107 | 26.97 | 499 | 0.4901 | 0.8305 |
96
- | 0.0921 | 28.0 | 518 | 0.5037 | 0.8407 |
97
- | 0.1105 | 28.97 | 536 | 0.5105 | 0.8305 |
98
- | 0.0883 | 29.19 | 540 | 0.5108 | 0.8339 |
99
 
100
 
101
  ### Framework versions
 
15
  dataset:
16
  name: imagefolder
17
  type: imagefolder
18
+ config: Augmented
19
  split: train
20
+ args: Augmented
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 1.0
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft](https://huggingface.co/microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.0004
35
+ - Accuracy: 1.0
36
 
37
  ## Model description
38
 
 
59
  - total_train_batch_size: 64
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.05
63
  - num_epochs: 30
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 1.5952 | 1.0 | 55 | 0.8490 | 0.6693 |
70
+ | 0.7582 | 2.0 | 110 | 0.4561 | 0.8386 |
71
+ | 0.4359 | 3.0 | 165 | 0.2408 | 0.9227 |
72
+ | 0.318 | 4.0 | 220 | 0.1294 | 0.9568 |
73
+ | 0.2414 | 5.0 | 275 | 0.0346 | 0.9909 |
74
+ | 0.1888 | 6.0 | 330 | 0.0419 | 0.9864 |
75
+ | 0.1717 | 7.0 | 385 | 0.0238 | 0.9943 |
76
+ | 0.1785 | 8.0 | 440 | 0.0230 | 0.9943 |
77
+ | 0.1654 | 9.0 | 495 | 0.0076 | 1.0 |
78
+ | 0.1322 | 10.0 | 550 | 0.0046 | 1.0 |
79
+ | 0.1123 | 11.0 | 605 | 0.0035 | 1.0 |
80
+ | 0.0953 | 12.0 | 660 | 0.0025 | 1.0 |
81
+ | 0.0864 | 13.0 | 715 | 0.0033 | 1.0 |
82
+ | 0.0984 | 14.0 | 770 | 0.0033 | 0.9989 |
83
+ | 0.0952 | 15.0 | 825 | 0.0015 | 1.0 |
84
+ | 0.0678 | 16.0 | 880 | 0.0022 | 1.0 |
85
+ | 0.0592 | 17.0 | 935 | 0.0013 | 1.0 |
86
+ | 0.0729 | 18.0 | 990 | 0.0037 | 0.9989 |
87
+ | 0.0672 | 19.0 | 1045 | 0.0041 | 0.9989 |
88
+ | 0.0615 | 20.0 | 1100 | 0.0010 | 1.0 |
89
+ | 0.058 | 21.0 | 1155 | 0.0009 | 1.0 |
90
+ | 0.0571 | 22.0 | 1210 | 0.0021 | 0.9989 |
91
+ | 0.0755 | 23.0 | 1265 | 0.0022 | 0.9989 |
92
+ | 0.0688 | 24.0 | 1320 | 0.0025 | 0.9989 |
93
+ | 0.0417 | 25.0 | 1375 | 0.0003 | 1.0 |
94
+ | 0.0589 | 26.0 | 1430 | 0.0007 | 1.0 |
95
+ | 0.0563 | 27.0 | 1485 | 0.0007 | 1.0 |
96
+ | 0.0603 | 28.0 | 1540 | 0.0010 | 0.9989 |
97
+ | 0.0469 | 29.0 | 1595 | 0.0005 | 1.0 |
98
+ | 0.0525 | 30.0 | 1650 | 0.0004 | 1.0 |
99
 
100
 
101
  ### Framework versions