Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-DMAE-ex

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results
Model card Files Metrics Community
Augusto777 commited on
Commit
d49d7b8
·
verified ·
1 Parent(s): 4398e6b

Model save

Browse files
Files changed (3) hide show
  1. README.md +112 -0
  2. model.safetensors +1 -1
  3. runs/Dec02_14-13-10_DESKTOP-SKBE9FB/events.out.tfevents.1733170391.DESKTOP-SKBE9FB.15300.0 +2 -2
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-ex
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-ex
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: 1.2065
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: 0.09
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: 0.1
64
+ - num_epochs: 40
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.86 | 3 | 4.4331 | 0.1087 |
71
+ | No log | 2.0 | 7 | 39.1621 | 0.1087 |
72
+ | 9.3798 | 2.86 | 10 | 7.2709 | 0.1087 |
73
+ | 9.3798 | 4.0 | 14 | 4.3326 | 0.3261 |
74
+ | 9.3798 | 4.86 | 17 | 6.9651 | 0.1087 |
75
+ | 6.904 | 6.0 | 21 | 4.2935 | 0.4565 |
76
+ | 6.904 | 6.86 | 24 | 3.3138 | 0.1087 |
77
+ | 6.904 | 8.0 | 28 | 3.5144 | 0.4565 |
78
+ | 2.7643 | 8.86 | 31 | 4.4606 | 0.3261 |
79
+ | 2.7643 | 10.0 | 35 | 1.6489 | 0.4565 |
80
+ | 2.7643 | 10.86 | 38 | 1.3025 | 0.4565 |
81
+ | 2.4694 | 12.0 | 42 | 1.4724 | 0.3261 |
82
+ | 2.4694 | 12.86 | 45 | 1.3597 | 0.4565 |
83
+ | 2.4694 | 14.0 | 49 | 1.2715 | 0.3261 |
84
+ | 1.3638 | 14.86 | 52 | 1.2385 | 0.4565 |
85
+ | 1.3638 | 16.0 | 56 | 1.2178 | 0.4565 |
86
+ | 1.3638 | 16.86 | 59 | 1.2284 | 0.4565 |
87
+ | 1.2334 | 18.0 | 63 | 1.2211 | 0.4565 |
88
+ | 1.2334 | 18.86 | 66 | 1.2434 | 0.4565 |
89
+ | 1.2262 | 20.0 | 70 | 1.2209 | 0.4565 |
90
+ | 1.2262 | 20.86 | 73 | 1.2130 | 0.4565 |
91
+ | 1.2262 | 22.0 | 77 | 1.2384 | 0.4565 |
92
+ | 1.2038 | 22.86 | 80 | 1.2313 | 0.4565 |
93
+ | 1.2038 | 24.0 | 84 | 1.2086 | 0.4565 |
94
+ | 1.2038 | 24.86 | 87 | 1.2107 | 0.4565 |
95
+ | 1.1975 | 26.0 | 91 | 1.2075 | 0.4565 |
96
+ | 1.1975 | 26.86 | 94 | 1.2106 | 0.4565 |
97
+ | 1.1975 | 28.0 | 98 | 1.2140 | 0.4565 |
98
+ | 1.2005 | 28.86 | 101 | 1.2094 | 0.4565 |
99
+ | 1.2005 | 30.0 | 105 | 1.2090 | 0.4565 |
100
+ | 1.2005 | 30.86 | 108 | 1.2084 | 0.4565 |
101
+ | 1.2012 | 32.0 | 112 | 1.2072 | 0.4565 |
102
+ | 1.2012 | 32.86 | 115 | 1.2067 | 0.4565 |
103
+ | 1.2012 | 34.0 | 119 | 1.2065 | 0.4565 |
104
+ | 1.1985 | 34.29 | 120 | 1.2065 | 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
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54508839dffb9d743bc347572f6ca52480328cc5a05738690d8c333f70617f8c
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc3a770c3cbd56e9112ab94f90f0627d95d00305b81e82b49d5822b162b7f6b
3
  size 110356296
runs/Dec02_14-13-10_DESKTOP-SKBE9FB/events.out.tfevents.1733170391.DESKTOP-SKBE9FB.15300.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:783c195f030999377901610e995d7edf3dc08e3d76c6f744cbda51c9fb4af97e
3
- size 16954
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d1ff8c8be99009d33cf292970c72c3ecdc057f86f646404f8b6a07d12256306
3
+ size 18090