Hugging Face's logo

alkzar90
/
croupier-creature-classifier

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
1
alkzar90 commited on
Commit
b6e15d7
·
1 Parent(s): 3cf2fd1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -30
README.md CHANGED
@@ -1,7 +1,6 @@
1
  ---
2
  license: apache-2.0
3
  tags:
4
- - image-classification
5
  - generated_from_trainer
6
  datasets:
7
  - imagefolder
@@ -14,7 +13,7 @@ model-index:
14
  name: Image Classification
15
  type: image-classification
16
  dataset:
17
- name: croupier-mtg-dataset
18
  type: imagefolder
19
  config: alkzar90--croupier-mtg-dataset
20
  split: train
@@ -22,7 +21,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.6839080459770115
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  # croupier-creature-classifier
32
 
33
- This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the croupier-mtg-dataset dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.1036
36
- - Accuracy: 0.6839
37
 
38
  ## Model description
39
 
@@ -52,41 +51,64 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 0.0002
56
  - train_batch_size: 16
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 25
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 1.1638 | 1.1 | 100 | 1.0564 | 0.5471 |
69
- | 0.8524 | 2.2 | 200 | 0.9403 | 0.6118 |
70
- | 0.8231 | 3.3 | 300 | 0.8282 | 0.7176 |
71
- | 0.7398 | 4.4 | 400 | 0.9056 | 0.6294 |
72
- | 0.41 | 5.49 | 500 | 0.8815 | 0.6235 |
73
- | 0.4849 | 6.59 | 600 | 0.9505 | 0.6294 |
74
- | 0.3894 | 7.69 | 700 | 0.8052 | 0.6882 |
75
- | 0.4678 | 8.79 | 800 | 0.8424 | 0.7059 |
76
- | 0.4279 | 9.89 | 900 | 0.9639 | 0.6706 |
77
- | 0.3461 | 10.99 | 1000 | 0.8497 | 0.7059 |
78
- | 0.2741 | 12.09 | 1100 | 0.9090 | 0.7 |
79
- | 0.1771 | 13.19 | 1200 | 0.8292 | 0.7118 |
80
- | 0.1779 | 14.29 | 1300 | 1.1314 | 0.6294 |
81
- | 0.2044 | 15.38 | 1400 | 0.8349 | 0.7294 |
82
- | 0.1543 | 16.48 | 1500 | 0.8952 | 0.6941 |
83
- | 0.1283 | 17.58 | 1600 | 0.8054 | 0.7353 |
84
- | 0.1721 | 18.68 | 1700 | 0.9094 | 0.7235 |
85
- | 0.1509 | 19.78 | 1800 | 0.9168 | 0.7412 |
86
- | 0.1257 | 20.88 | 1900 | 0.9395 | 0.7412 |
87
- | 0.1747 | 21.98 | 2000 | 0.8746 | 0.7471 |
88
- | 0.1506 | 23.08 | 2100 | 0.7992 | 0.7353 |
89
- | 0.1021 | 24.18 | 2200 | 0.7446 | 0.7706 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
90
 
91
 
92
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
  tags:
 
4
  - generated_from_trainer
5
  datasets:
6
  - imagefolder
 
13
  name: Image Classification
14
  type: image-classification
15
  dataset:
16
+ name: imagefolder
17
  type: imagefolder
18
  config: alkzar90--croupier-mtg-dataset
19
  split: train
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.7764705882352941
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  # croupier-creature-classifier
31
 
32
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.7248
35
+ - Accuracy: 0.7765
36
 
37
  ## Model description
38
 
 
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
+ - learning_rate: 3e-05
55
  - train_batch_size: 16
56
  - eval_batch_size: 8
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
+ - num_epochs: 50
61
  - mixed_precision_training: Native AMP
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 1.1159 | 1.1 | 100 | 1.1144 | 0.6118 |
68
+ | 0.8183 | 2.2 | 200 | 0.9109 | 0.6882 |
69
+ | 0.6829 | 3.3 | 300 | 0.7677 | 0.7235 |
70
+ | 0.5575 | 4.4 | 400 | 0.7670 | 0.6765 |
71
+ | 0.4644 | 5.49 | 500 | 0.8460 | 0.6647 |
72
+ | 0.3096 | 6.59 | 600 | 0.7082 | 0.7529 |
73
+ | 0.305 | 7.69 | 700 | 0.6939 | 0.7647 |
74
+ | 0.3349 | 8.79 | 800 | 0.7285 | 0.7235 |
75
+ | 0.36 | 9.89 | 900 | 0.7664 | 0.7294 |
76
+ | 0.3184 | 10.99 | 1000 | 0.6807 | 0.7588 |
77
+ | 0.2815 | 12.09 | 1100 | 0.7408 | 0.7353 |
78
+ | 0.1745 | 13.19 | 1200 | 0.7528 | 0.7294 |
79
+ | 0.1894 | 14.29 | 1300 | 0.7634 | 0.7471 |
80
+ | 0.1641 | 15.38 | 1400 | 0.7209 | 0.7647 |
81
+ | 0.1932 | 16.48 | 1500 | 0.9091 | 0.7 |
82
+ | 0.1609 | 17.58 | 1600 | 0.7208 | 0.7588 |
83
+ | 0.132 | 18.68 | 1700 | 0.8487 | 0.7588 |
84
+ | 0.1903 | 19.78 | 1800 | 0.7912 | 0.7471 |
85
+ | 0.121 | 20.88 | 1900 | 0.6735 | 0.7471 |
86
+ | 0.1903 | 21.98 | 2000 | 0.6692 | 0.7824 |
87
+ | 0.176 | 23.08 | 2100 | 0.8351 | 0.7176 |
88
+ | 0.1186 | 24.18 | 2200 | 0.7318 | 0.7471 |
89
+ | 0.1424 | 25.27 | 2300 | 0.7860 | 0.7588 |
90
+ | 0.144 | 26.37 | 2400 | 0.7021 | 0.7882 |
91
+ | 0.1088 | 27.47 | 2500 | 0.8109 | 0.7471 |
92
+ | 0.1019 | 28.57 | 2600 | 0.8157 | 0.7471 |
93
+ | 0.0947 | 29.67 | 2700 | 0.8028 | 0.7588 |
94
+ | 0.1715 | 30.77 | 2800 | 0.8345 | 0.7471 |
95
+ | 0.1046 | 31.87 | 2900 | 0.8578 | 0.7412 |
96
+ | 0.1367 | 32.97 | 3000 | 0.7670 | 0.7882 |
97
+ | 0.1339 | 34.07 | 3100 | 0.7763 | 0.7647 |
98
+ | 0.1194 | 35.16 | 3200 | 0.7727 | 0.7706 |
99
+ | 0.151 | 36.26 | 3300 | 0.8272 | 0.7471 |
100
+ | 0.0646 | 37.36 | 3400 | 0.7721 | 0.7765 |
101
+ | 0.0801 | 38.46 | 3500 | 0.8171 | 0.7529 |
102
+ | 0.1038 | 39.56 | 3600 | 0.9464 | 0.7059 |
103
+ | 0.16 | 40.66 | 3700 | 0.8005 | 0.7706 |
104
+ | 0.1151 | 41.76 | 3800 | 0.8784 | 0.7471 |
105
+ | 0.1159 | 42.86 | 3900 | 0.8598 | 0.7471 |
106
+ | 0.0575 | 43.96 | 4000 | 0.8543 | 0.7529 |
107
+ | 0.164 | 45.05 | 4100 | 0.8659 | 0.7588 |
108
+ | 0.1319 | 46.15 | 4200 | 0.8854 | 0.7412 |
109
+ | 0.0489 | 47.25 | 4300 | 0.7508 | 0.7588 |
110
+ | 0.0678 | 48.35 | 4400 | 0.8784 | 0.7353 |
111
+ | 0.0832 | 49.45 | 4500 | 0.7248 | 0.7765 |
112
 
113
 
114
  ### Framework versions