Hugging Face's logo

nandyc
/
swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2

Image Classification
Transformers
PyTorch
swin
Generated from Trainer
Inference Endpoints
Model card Files Community
nandyc commited on
Commit
2586483
•
1 Parent(s): 13ba7b6

Model save

Browse files
Files changed (3) hide show
  1. README.md +49 -22
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -2,7 +2,6 @@
2
  license: apache-2.0
3
  base_model: microsoft/swin-tiny-patch4-window7-224
4
  tags:
5
- - image-classification
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
@@ -16,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2
18
 
19
- 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 ASL_Isolated_Swin_dataset dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.0784
22
  - Accuracy: 0.9846
23
 
24
  ## Model description
@@ -44,30 +43,58 @@ The following hyperparameters were used during training:
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 20
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 1.7296 | 1.09 | 100 | 1.2288 | 0.6115 |
54
- | 1.0961 | 2.17 | 200 | 0.6633 | 0.8115 |
55
- | 0.5971 | 3.26 | 300 | 0.2989 | 0.8846 |
56
- | 0.5663 | 4.35 | 400 | 0.2658 | 0.9538 |
57
- | 0.6431 | 5.43 | 500 | 0.3100 | 0.8846 |
58
- | 0.49 | 6.52 | 600 | 0.2457 | 0.9192 |
59
- | 0.4639 | 7.61 | 700 | 0.2958 | 0.9154 |
60
- | 0.2436 | 8.7 | 800 | 0.2147 | 0.9192 |
61
- | 0.2652 | 9.78 | 900 | 0.1822 | 0.9615 |
62
- | 0.2346 | 10.87 | 1000 | 0.2716 | 0.9385 |
63
- | 0.3326 | 11.96 | 1100 | 0.0930 | 0.9692 |
64
- | 0.4255 | 13.04 | 1200 | 0.1565 | 0.95 |
65
- | 0.3486 | 14.13 | 1300 | 0.0881 | 0.9808 |
66
- | 0.2801 | 15.22 | 1400 | 0.1083 | 0.9577 |
67
- | 0.164 | 16.3 | 1500 | 0.0994 | 0.9731 |
68
- | 0.2892 | 17.39 | 1600 | 0.0784 | 0.9846 |
69
- | 0.1033 | 18.48 | 1700 | 0.0933 | 0.9808 |
70
- | 0.1612 | 19.57 | 1800 | 0.0834 | 0.9846 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: microsoft/swin-tiny-patch4-window7-224
4
  tags:
 
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
 
15
 
16
  # swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2
17
 
18
+ This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0605
21
  - Accuracy: 0.9846
22
 
23
  ## Model description
 
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 50
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 1.5603 | 1.09 | 100 | 1.0931 | 0.6423 |
53
+ | 0.9055 | 2.17 | 200 | 0.5069 | 0.8615 |
54
+ | 0.4254 | 3.26 | 300 | 0.5634 | 0.8154 |
55
+ | 0.5814 | 4.35 | 400 | 0.2883 | 0.9154 |
56
+ | 0.4953 | 5.43 | 500 | 0.2710 | 0.9154 |
57
+ | 0.4456 | 6.52 | 600 | 0.2451 | 0.9346 |
58
+ | 0.4524 | 7.61 | 700 | 0.2625 | 0.9308 |
59
+ | 0.3095 | 8.7 | 800 | 0.2397 | 0.9462 |
60
+ | 0.3224 | 9.78 | 900 | 0.1787 | 0.9385 |
61
+ | 0.4069 | 10.87 | 1000 | 0.3376 | 0.9231 |
62
+ | 0.3467 | 11.96 | 1100 | 0.1603 | 0.9538 |
63
+ | 0.469 | 13.04 | 1200 | 0.2247 | 0.9423 |
64
+ | 0.4523 | 14.13 | 1300 | 0.1552 | 0.9538 |
65
+ | 0.2923 | 15.22 | 1400 | 0.3376 | 0.9346 |
66
+ | 0.3139 | 16.3 | 1500 | 0.1449 | 0.9577 |
67
+ | 0.3873 | 17.39 | 1600 | 0.1495 | 0.9654 |
68
+ | 0.2994 | 18.48 | 1700 | 0.1821 | 0.9654 |
69
+ | 0.2611 | 19.57 | 1800 | 0.1294 | 0.9769 |
70
+ | 0.1883 | 20.65 | 1900 | 0.0879 | 0.9731 |
71
+ | 0.2076 | 21.74 | 2000 | 0.1969 | 0.95 |
72
+ | 0.3531 | 22.83 | 2100 | 0.2135 | 0.9538 |
73
+ | 0.4339 | 23.91 | 2200 | 0.1030 | 0.9615 |
74
+ | 0.2959 | 25.0 | 2300 | 0.1579 | 0.9731 |
75
+ | 0.1546 | 26.09 | 2400 | 0.1648 | 0.9692 |
76
+ | 0.1315 | 27.17 | 2500 | 0.1514 | 0.9577 |
77
+ | 0.2191 | 28.26 | 2600 | 0.1257 | 0.9538 |
78
+ | 0.16 | 29.35 | 2700 | 0.1162 | 0.9692 |
79
+ | 0.1567 | 30.43 | 2800 | 0.1252 | 0.9731 |
80
+ | 0.1147 | 31.52 | 2900 | 0.2642 | 0.9577 |
81
+ | 0.1434 | 32.61 | 3000 | 0.1371 | 0.9769 |
82
+ | 0.2488 | 33.7 | 3100 | 0.1161 | 0.9769 |
83
+ | 0.1646 | 34.78 | 3200 | 0.2052 | 0.9615 |
84
+ | 0.1326 | 35.87 | 3300 | 0.1995 | 0.9769 |
85
+ | 0.137 | 36.96 | 3400 | 0.1124 | 0.9731 |
86
+ | 0.1633 | 38.04 | 3500 | 0.1620 | 0.9692 |
87
+ | 0.1593 | 39.13 | 3600 | 0.1838 | 0.9731 |
88
+ | 0.2192 | 40.22 | 3700 | 0.1331 | 0.9769 |
89
+ | 0.1495 | 41.3 | 3800 | 0.1291 | 0.9731 |
90
+ | 0.226 | 42.39 | 3900 | 0.1090 | 0.9692 |
91
+ | 0.1383 | 43.48 | 4000 | 0.0994 | 0.9654 |
92
+ | 0.0491 | 44.57 | 4100 | 0.0660 | 0.9769 |
93
+ | 0.1034 | 45.65 | 4200 | 0.0698 | 0.9808 |
94
+ | 0.0893 | 46.74 | 4300 | 0.0439 | 0.9846 |
95
+ | 0.1789 | 47.83 | 4400 | 0.0577 | 0.9808 |
96
+ | 0.0569 | 48.91 | 4500 | 0.0547 | 0.9846 |
97
+ | 0.1113 | 50.0 | 4600 | 0.0605 | 0.9846 |
98
 
99
 
100
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec6a78cd654476882fbee75d43c0509c6800ef3c2b9fe1b581ccdb664a1ad6b6
3
  size 110469102
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc1826a905750075599f8edc5081b0c40ac4882acc80f9c784f86d69b301caff
3
  size 110469102
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4d9536cf5f34a11f56970ba02928df763400cec3b96f1d60ca79c4b5cdd2355
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cea9d13d79688f99889c58ecf69ebb5fc829a28e58e361dff66c1724a96506c
3
  size 4600