Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-DMAE-4e-3

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
Augusto777 commited on
Commit
24e935d
·
verified ·
1 Parent(s): c0c6cfe

Model save

Browse files
Files changed (3) hide show
  1. README.md +115 -112
  2. model.safetensors +1 -1
  3. runs/Dec02_22-32-38_7729759f1625/events.out.tfevents.1733178767.7729759f1625.609.2 +2 -2
README.md CHANGED
@@ -1,112 +1,115 @@
1
- ---
2
- license: apache-2.0
3
- base_model: microsoft/swinv2-tiny-patch4-window8-256
4
- tags:
5
- - generated_from_trainer
6
- datasets:
7
- - imagefolder
8
- metrics:
9
- - accuracy
10
- model-index:
11
- - name: swinv2-tiny-patch4-window8-256-DMAE-4e-3
12
- results:
13
- - task:
14
- name: Image Classification
15
- type: image-classification
16
- dataset:
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: 0.45652173913043476
26
- ---
27
-
28
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
- should probably proofread and complete it, then remove this comment. -->
30
-
31
- # swinv2-tiny-patch4-window8-256-DMAE-4e-3
32
-
33
- This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
34
- It achieves the following results on the evaluation set:
35
- - Loss: 2.2674
36
- - Accuracy: 0.4565
37
-
38
- ## Model description
39
-
40
- More information needed
41
-
42
- ## Intended uses & limitations
43
-
44
- More information needed
45
-
46
- ## Training and evaluation data
47
-
48
- More information needed
49
-
50
- ## Training procedure
51
-
52
- ### Training hyperparameters
53
-
54
- The following hyperparameters were used during training:
55
- - learning_rate: 0.004
56
- - train_batch_size: 16
57
- - eval_batch_size: 16
58
- - seed: 42
59
- - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 64
61
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
- - lr_scheduler_type: linear
63
- - lr_scheduler_warmup_ratio: 0.05
64
- - num_epochs: 40
65
-
66
- ### Training results
67
-
68
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 0.86 | 3 | 4.5991 | 0.1087 |
71
- | No log | 2.0 | 7 | 2.3525 | 0.3261 |
72
- | 4.6082 | 2.86 | 10 | 2.1275 | 0.1522 |
73
- | 4.6082 | 4.0 | 14 | 2.1729 | 0.3261 |
74
- | 4.6082 | 4.86 | 17 | 1.7247 | 0.3261 |
75
- | 2.6299 | 6.0 | 21 | 2.2674 | 0.4565 |
76
- | 2.6299 | 6.86 | 24 | 1.7188 | 0.4565 |
77
- | 2.6299 | 8.0 | 28 | 1.3022 | 0.4565 |
78
- | 2.0766 | 8.86 | 31 | 1.2425 | 0.4565 |
79
- | 2.0766 | 10.0 | 35 | 1.2855 | 0.3261 |
80
- | 2.0766 | 10.86 | 38 | 1.2310 | 0.4565 |
81
- | 1.2802 | 12.0 | 42 | 1.3593 | 0.3261 |
82
- | 1.2802 | 12.86 | 45 | 1.2867 | 0.4565 |
83
- | 1.2802 | 14.0 | 49 | 1.2527 | 0.4565 |
84
- | 1.3414 | 14.86 | 52 | 1.2312 | 0.4565 |
85
- | 1.3414 | 16.0 | 56 | 1.2118 | 0.4565 |
86
- | 1.3414 | 16.86 | 59 | 1.2191 | 0.4565 |
87
- | 1.2764 | 18.0 | 63 | 1.2414 | 0.4565 |
88
- | 1.2764 | 18.86 | 66 | 1.2397 | 0.4565 |
89
- | 1.2236 | 20.0 | 70 | 1.2237 | 0.4565 |
90
- | 1.2236 | 20.86 | 73 | 1.2179 | 0.4565 |
91
- | 1.2236 | 22.0 | 77 | 1.2234 | 0.4565 |
92
- | 1.2294 | 22.86 | 80 | 1.2495 | 0.3261 |
93
- | 1.2294 | 24.0 | 84 | 1.2092 | 0.4565 |
94
- | 1.2294 | 24.86 | 87 | 1.2177 | 0.3261 |
95
- | 1.2147 | 26.0 | 91 | 1.2105 | 0.4565 |
96
- | 1.2147 | 26.86 | 94 | 1.2271 | 0.4565 |
97
- | 1.2147 | 28.0 | 98 | 1.2263 | 0.4565 |
98
- | 1.2097 | 28.86 | 101 | 1.2108 | 0.4565 |
99
- | 1.2097 | 30.0 | 105 | 1.2069 | 0.4565 |
100
- | 1.2097 | 30.86 | 108 | 1.2096 | 0.4565 |
101
- | 1.2038 | 32.0 | 112 | 1.2106 | 0.4565 |
102
- | 1.2038 | 32.86 | 115 | 1.2102 | 0.4565 |
103
- | 1.2038 | 34.0 | 119 | 1.2119 | 0.4565 |
104
- | 1.2038 | 34.29 | 120 | 1.2118 | 0.4565 |
105
-
106
-
107
- ### Framework versions
108
-
109
- - Transformers 4.36.2
110
- - Pytorch 2.1.2+cu118
111
- - Datasets 2.16.1
112
- - Tokenizers 0.15.0
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: microsoft/swinv2-tiny-patch4-window8-256
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - imagefolder
9
+ metrics:
10
+ - accuracy
11
+ model-index:
12
+ - name: swinv2-tiny-patch4-window8-256-DMAE-4e-3
13
+ results:
14
+ - task:
15
+ name: Image Classification
16
+ type: image-classification
17
+ dataset:
18
+ name: imagefolder
19
+ type: imagefolder
20
+ config: default
21
+ split: test
22
+ args: default
23
+ metrics:
24
+ - name: Accuracy
25
+ type: accuracy
26
+ value: 0.7391304347826086
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # swinv2-tiny-patch4-window8-256-DMAE-4e-3
33
+
34
+ This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.7507
37
+ - Accuracy: 0.7391
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 3e-05
57
+ - train_batch_size: 16
58
+ - eval_batch_size: 16
59
+ - seed: 42
60
+ - gradient_accumulation_steps: 4
61
+ - total_train_batch_size: 64
62
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
+ - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_ratio: 0.1
65
+ - num_epochs: 40
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
71
+ | No log | 0.8571 | 3 | 1.3959 | 0.3043 |
72
+ | No log | 1.7857 | 6 | 1.2662 | 0.3913 |
73
+ | No log | 2.7143 | 9 | 1.1960 | 0.4783 |
74
+ | 1.3226 | 3.9286 | 13 | 1.1950 | 0.4565 |
75
+ | 1.3226 | 4.8571 | 16 | 1.1891 | 0.4783 |
76
+ | 1.3226 | 5.7857 | 19 | 1.1898 | 0.4783 |
77
+ | 1.1833 | 6.7143 | 22 | 1.1824 | 0.5435 |
78
+ | 1.1833 | 7.9286 | 26 | 1.1618 | 0.5217 |
79
+ | 1.1833 | 8.8571 | 29 | 1.1359 | 0.5652 |
80
+ | 1.1384 | 9.7857 | 32 | 1.0974 | 0.5870 |
81
+ | 1.1384 | 10.7143 | 35 | 1.0524 | 0.5870 |
82
+ | 1.1384 | 11.9286 | 39 | 1.0083 | 0.6957 |
83
+ | 1.0628 | 12.8571 | 42 | 0.9696 | 0.6739 |
84
+ | 1.0628 | 13.7857 | 45 | 0.9369 | 0.6739 |
85
+ | 1.0628 | 14.7143 | 48 | 0.8825 | 0.7174 |
86
+ | 1.0069 | 15.9286 | 52 | 0.8396 | 0.6957 |
87
+ | 1.0069 | 16.8571 | 55 | 0.8267 | 0.7174 |
88
+ | 1.0069 | 17.7857 | 58 | 0.8275 | 0.7174 |
89
+ | 0.9339 | 18.7143 | 61 | 0.8255 | 0.7174 |
90
+ | 0.9339 | 19.9286 | 65 | 0.7899 | 0.7174 |
91
+ | 0.9339 | 20.8571 | 68 | 0.7604 | 0.7174 |
92
+ | 0.905 | 21.7857 | 71 | 0.7442 | 0.6957 |
93
+ | 0.905 | 22.7143 | 74 | 0.7361 | 0.7391 |
94
+ | 0.905 | 23.9286 | 78 | 0.7598 | 0.6957 |
95
+ | 0.8465 | 24.8571 | 81 | 0.7650 | 0.7174 |
96
+ | 0.8465 | 25.7857 | 84 | 0.7631 | 0.7391 |
97
+ | 0.8465 | 26.7143 | 87 | 0.7561 | 0.7174 |
98
+ | 0.8363 | 27.9286 | 91 | 0.7494 | 0.6957 |
99
+ | 0.8363 | 28.8571 | 94 | 0.7539 | 0.7174 |
100
+ | 0.8363 | 29.7857 | 97 | 0.7497 | 0.7174 |
101
+ | 0.7751 | 30.7143 | 100 | 0.7477 | 0.7174 |
102
+ | 0.7751 | 31.9286 | 104 | 0.7463 | 0.7609 |
103
+ | 0.7751 | 32.8571 | 107 | 0.7507 | 0.7609 |
104
+ | 0.7843 | 33.7857 | 110 | 0.7534 | 0.7391 |
105
+ | 0.7843 | 34.7143 | 113 | 0.7542 | 0.7391 |
106
+ | 0.7843 | 35.9286 | 117 | 0.7519 | 0.7391 |
107
+ | 0.7435 | 36.8571 | 120 | 0.7507 | 0.7391 |
108
+
109
+
110
+ ### Framework versions
111
+
112
+ - Transformers 4.46.2
113
+ - Pytorch 2.5.1+cu121
114
+ - Datasets 3.1.0
115
+ - Tokenizers 0.20.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:547890d41bfd129a4f102656c94dc57a94c676c3485037c31edfdbfb7ee22d2f
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64bbd33eed881e3de251265cf2b99bbeb0948b869c3d2c4501ff096924f742e7
3
  size 110356296
runs/Dec02_22-32-38_7729759f1625/events.out.tfevents.1733178767.7729759f1625.609.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b528d87dbd7cc87703f79dffdb015b9c864c26514adf184081cbbbf877dc788
3
- size 19549
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:372e73e06d6b07b915edf9cf8e9eab6759b21d1c12847919865d2e916d061311
3
+ size 20214