Hugging Face's logo

jaimin
/
swinv2-small-patch4-window8-256-finetuned-eurosat

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
jaimin commited on
Commit
6591979
•
1 Parent(s): 310ad00

Model save

Browse files
Files changed (2) hide show
  1. README.md +24 -23
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.6818181818181818
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [microsoft/swinv2-small-patch4-window8-256](https://huggingface.co/microsoft/swinv2-small-patch4-window8-256) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.2850
36
- - Accuracy: 0.6818
37
 
38
  ## Model description
39
 
@@ -67,30 +67,31 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 0.91 | 5 | 0.5918 | 0.7338 |
71
- | 0.6689 | 2.0 | 11 | 0.6330 | 0.7013 |
72
- | 0.6689 | 2.91 | 16 | 0.6016 | 0.7013 |
73
- | 0.5503 | 4.0 | 22 | 0.6296 | 0.7143 |
74
- | 0.5503 | 4.91 | 27 | 0.7059 | 0.5455 |
75
- | 0.3911 | 6.0 | 33 | 0.8002 | 0.5260 |
76
- | 0.3911 | 6.91 | 38 | 0.7831 | 0.7013 |
77
- | 0.2624 | 8.0 | 44 | 0.7862 | 0.6429 |
78
- | 0.2624 | 8.91 | 49 | 1.0588 | 0.5649 |
79
- | 0.1057 | 10.0 | 55 | 0.9249 | 0.6429 |
80
- | 0.0644 | 10.91 | 60 | 1.0545 | 0.6558 |
81
- | 0.0644 | 12.0 | 66 | 1.0990 | 0.6494 |
82
- | 0.0265 | 12.91 | 71 | 1.1942 | 0.6234 |
83
- | 0.0265 | 14.0 | 77 | 1.2192 | 0.6429 |
84
- | 0.0152 | 14.91 | 82 | 1.2414 | 0.6623 |
85
- | 0.0152 | 16.0 | 88 | 1.3708 | 0.6299 |
86
- | 0.0146 | 16.91 | 93 | 1.3162 | 0.6558 |
87
- | 0.0146 | 18.0 | 99 | 1.2849 | 0.6818 |
88
- | 0.0204 | 18.18 | 100 | 1.2850 | 0.6818 |
 
89
 
90
 
91
  ### Framework versions
92
 
93
  - Transformers 4.39.3
94
- - Pytorch 2.2.1+cpu
95
  - Datasets 2.18.0
96
  - Tokenizers 0.15.2
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6875
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [microsoft/swinv2-small-patch4-window8-256](https://huggingface.co/microsoft/swinv2-small-patch4-window8-256) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.2717
36
+ - Accuracy: 0.6875
37
 
38
  ## Model description
39
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 1.0 | 4 | 0.6579 | 0.6339 |
71
+ | No log | 2.0 | 8 | 0.7129 | 0.5 |
72
+ | 0.6364 | 3.0 | 12 | 0.6774 | 0.5982 |
73
+ | 0.6364 | 4.0 | 16 | 0.6584 | 0.6786 |
74
+ | 0.3486 | 5.0 | 20 | 0.6864 | 0.6786 |
75
+ | 0.3486 | 6.0 | 24 | 0.8473 | 0.6429 |
76
+ | 0.3486 | 7.0 | 28 | 0.9735 | 0.6339 |
77
+ | 0.1224 | 8.0 | 32 | 0.8121 | 0.6964 |
78
+ | 0.1224 | 9.0 | 36 | 1.2379 | 0.6429 |
79
+ | 0.0424 | 10.0 | 40 | 1.1585 | 0.6875 |
80
+ | 0.0424 | 11.0 | 44 | 1.5274 | 0.6161 |
81
+ | 0.0424 | 12.0 | 48 | 1.1415 | 0.6607 |
82
+ | 0.0353 | 13.0 | 52 | 1.4422 | 0.6518 |
83
+ | 0.0353 | 14.0 | 56 | 1.6677 | 0.625 |
84
+ | 0.0141 | 15.0 | 60 | 1.1960 | 0.6696 |
85
+ | 0.0141 | 16.0 | 64 | 1.5515 | 0.625 |
86
+ | 0.0141 | 17.0 | 68 | 1.7990 | 0.6161 |
87
+ | 0.0135 | 18.0 | 72 | 1.4437 | 0.6607 |
88
+ | 0.0135 | 19.0 | 76 | 1.2816 | 0.7054 |
89
+ | 0.0073 | 20.0 | 80 | 1.2717 | 0.6875 |
90
 
91
 
92
  ### Framework versions
93
 
94
  - Transformers 4.39.3
95
+ - Pytorch 2.2.2+cu121
96
  - Datasets 2.18.0
97
  - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a26204b88edd65c82099c4d4a6f98e943ed43e653807e353f96c597bfdda4920
3
  size 195905448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5dfa19068370ec49bb330f4ea589fa2b4d120fd0a08d9e87162829ca88b959f
3
  size 195905448