Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-DMAE-da-4e-5

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results
Model card Files Metrics Community
Augusto777 commited on
Commit
70a94d4
·
verified ·
1 Parent(s): 5850ed6

Model save

Browse files
Files changed (3) hide show
  1. README.md +116 -0
  2. model.safetensors +1 -1
  3. runs/Dec02_21-52-11_DESKTOP-SKBE9FB/events.out.tfevents.1733197933.DESKTOP-SKBE9FB.15196.0 +2 -2
README.md ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-da-4e-5
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: 0.6956521739130435
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-da-4e-5
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: 1.0149
36
+ - Accuracy: 0.6957
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: 4e-05
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
+ | 1.446 | 0.96 | 11 | 1.6275 | 0.1087 |
71
+ | 1.4497 | 2.0 | 23 | 1.5550 | 0.1087 |
72
+ | 1.388 | 2.96 | 34 | 1.3769 | 0.3261 |
73
+ | 1.2755 | 4.0 | 46 | 1.2483 | 0.4130 |
74
+ | 1.1574 | 4.96 | 57 | 1.1545 | 0.4565 |
75
+ | 1.0826 | 6.0 | 69 | 1.0429 | 0.5 |
76
+ | 0.9124 | 6.96 | 80 | 0.9318 | 0.5652 |
77
+ | 0.8228 | 8.0 | 92 | 1.0362 | 0.5217 |
78
+ | 0.733 | 8.96 | 103 | 0.9699 | 0.5870 |
79
+ | 0.7086 | 10.0 | 115 | 0.8269 | 0.6522 |
80
+ | 0.6459 | 10.96 | 126 | 0.8168 | 0.6739 |
81
+ | 0.5793 | 12.0 | 138 | 1.0780 | 0.6087 |
82
+ | 0.5904 | 12.96 | 149 | 1.0166 | 0.5870 |
83
+ | 0.5155 | 14.0 | 161 | 0.8489 | 0.6304 |
84
+ | 0.4693 | 14.96 | 172 | 0.8454 | 0.6522 |
85
+ | 0.4928 | 16.0 | 184 | 0.8161 | 0.6739 |
86
+ | 0.4763 | 16.96 | 195 | 0.7666 | 0.7174 |
87
+ | 0.4354 | 18.0 | 207 | 0.8828 | 0.6957 |
88
+ | 0.3661 | 18.96 | 218 | 0.8782 | 0.6739 |
89
+ | 0.3652 | 20.0 | 230 | 0.9418 | 0.6739 |
90
+ | 0.3733 | 20.96 | 241 | 0.8963 | 0.7174 |
91
+ | 0.3473 | 22.0 | 253 | 0.9053 | 0.7174 |
92
+ | 0.2988 | 22.96 | 264 | 0.8318 | 0.7391 |
93
+ | 0.349 | 24.0 | 276 | 1.1129 | 0.6087 |
94
+ | 0.2963 | 24.96 | 287 | 1.0557 | 0.6304 |
95
+ | 0.3025 | 26.0 | 299 | 0.9567 | 0.7391 |
96
+ | 0.2676 | 26.96 | 310 | 1.0131 | 0.6739 |
97
+ | 0.2848 | 28.0 | 322 | 0.9576 | 0.6957 |
98
+ | 0.2757 | 28.96 | 333 | 0.9821 | 0.7174 |
99
+ | 0.2564 | 30.0 | 345 | 1.0166 | 0.6522 |
100
+ | 0.2635 | 30.96 | 356 | 0.9664 | 0.7609 |
101
+ | 0.2413 | 32.0 | 368 | 0.9894 | 0.7391 |
102
+ | 0.2321 | 32.96 | 379 | 1.0272 | 0.7391 |
103
+ | 0.2517 | 34.0 | 391 | 1.0312 | 0.7174 |
104
+ | 0.2161 | 34.96 | 402 | 1.0433 | 0.7174 |
105
+ | 0.2304 | 36.0 | 414 | 1.0158 | 0.7174 |
106
+ | 0.2194 | 36.96 | 425 | 1.0120 | 0.6957 |
107
+ | 0.2395 | 38.0 | 437 | 1.0153 | 0.6957 |
108
+ | 0.2199 | 38.26 | 440 | 1.0149 | 0.6957 |
109
+
110
+
111
+ ### Framework versions
112
+
113
+ - Transformers 4.36.2
114
+ - Pytorch 2.1.2+cu118
115
+ - Datasets 2.16.1
116
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fe182a9b1741093fefcf6b06034edaa68eb2a44c802252b8125a479ffbd24d9
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a0206de8d0b268429bdf53e1b68d6489f01fd0c317995e373389269636bad7
3
  size 110356296
runs/Dec02_21-52-11_DESKTOP-SKBE9FB/events.out.tfevents.1733197933.DESKTOP-SKBE9FB.15196.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d9c28ed6de35d28c4157400f7b326555113600c8621692d9ceb27de35af7fb5
3
- size 16224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb790e036b4ad44d21f72e685d93a33eca9e1b167942343f4772cdc087e3ec8
3
+ size 24572