Hugging Face's logo

Woleek
/
camera-type

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
Woleek commited on
Commit
4529d64
·
1 Parent(s): 6ca43d4

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -15
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: microsoft/resnet-50
4
  tags:
5
  - image-classification
6
  - generated_from_trainer
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.9382716049382716
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  # camera-type
33
 
34
- This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.1654
37
- - Accuracy: 0.9383
38
 
39
  ## Model description
40
 
@@ -65,16 +65,18 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.4597 | 0.5 | 200 | 0.2801 | 0.9242 |
69
- | 0.1375 | 0.99 | 400 | 0.1654 | 0.9383 |
70
- | 0.0795 | 1.49 | 600 | 0.1904 | 0.9383 |
71
- | 0.0686 | 1.98 | 800 | 0.1810 | 0.9453 |
72
- | 0.026 | 2.48 | 1000 | 0.2216 | 0.9400 |
73
- | 0.0495 | 2.97 | 1200 | 0.2096 | 0.9453 |
74
- | 0.0487 | 3.47 | 1400 | 0.2174 | 0.9436 |
75
- | 0.0268 | 3.96 | 1600 | 0.2304 | 0.9453 |
76
- | 0.0254 | 4.46 | 1800 | 0.2574 | 0.9400 |
77
- | 0.0186 | 4.95 | 2000 | 0.3212 | 0.9383 |
 
 
78
 
79
 
80
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: google/vit-base-patch16-224
4
  tags:
5
  - image-classification
6
  - generated_from_trainer
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.9915611814345991
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  # camera-type
33
 
34
+ This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.0235
37
+ - Accuracy: 0.9916
38
 
39
  ## Model description
40
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.0064 | 0.4 | 200 | 0.0235 | 0.9916 |
69
+ | 0.0034 | 0.79 | 400 | 0.0392 | 0.9941 |
70
+ | 0.0066 | 1.19 | 600 | 0.1011 | 0.9840 |
71
+ | 0.0 | 1.58 | 800 | 0.1227 | 0.9840 |
72
+ | 0.0 | 1.98 | 1000 | 0.1232 | 0.9840 |
73
+ | 0.0 | 2.37 | 1200 | 0.1433 | 0.9840 |
74
+ | 0.0 | 2.77 | 1400 | 0.1416 | 0.9840 |
75
+ | 0.0 | 3.16 | 1600 | 0.1408 | 0.9840 |
76
+ | 0.0 | 3.56 | 1800 | 0.1401 | 0.9840 |
77
+ | 0.0 | 3.95 | 2000 | 0.1394 | 0.9840 |
78
+ | 0.0 | 4.35 | 2200 | 0.1390 | 0.9840 |
79
+ | 0.0 | 4.74 | 2400 | 0.1389 | 0.9840 |
80
 
81
 
82
  ### Framework versions