Hugging Face's logo

jayanta
/
google-vit-base-patch16-224-cartoon-emotion-detection

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
3
paul commited on
Commit
872b113
•
1 Parent(s): aa3ec22

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -32
README.md CHANGED
@@ -18,20 +18,22 @@ model-index:
18
  dataset:
19
  name: imagefolder
20
  type: imagefolder
 
 
21
  args: default
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8715596330275229
26
  - name: Precision
27
  type: precision
28
- value: 0.8725197999744695
29
  - name: Recall
30
  type: recall
31
- value: 0.8715596330275229
32
  - name: F1
33
  type: f1
34
- value: 0.871683140929764
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,11 +43,11 @@ should probably proofread and complete it, then remove this comment. -->
41
 
42
  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.
43
  It achieves the following results on the evaluation set:
44
- - Loss: 0.4170
45
- - Accuracy: 0.8716
46
- - Precision: 0.8725
47
- - Recall: 0.8716
48
- - F1: 0.8717
49
 
50
  ## Model description
51
 
@@ -73,37 +75,27 @@ The following hyperparameters were used during training:
73
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
  - lr_scheduler_type: linear
75
  - lr_scheduler_warmup_ratio: 0.1
76
- - num_epochs: 20
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
81
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
82
- | No log | 0.97 | 8 | 1.0942 | 0.5780 | 0.6102 | 0.5780 | 0.5496 |
83
- | 1.3198 | 1.97 | 16 | 0.6914 | 0.7615 | 0.7498 | 0.7615 | 0.7493 |
84
- | 0.6694 | 2.97 | 24 | 0.4702 | 0.7890 | 0.7808 | 0.7890 | 0.7781 |
85
- | 0.2725 | 3.97 | 32 | 0.3957 | 0.8532 | 0.8514 | 0.8532 | 0.8522 |
86
- | 0.1116 | 4.97 | 40 | 0.3428 | 0.8716 | 0.8697 | 0.8716 | 0.8693 |
87
- | 0.1116 | 5.97 | 48 | 0.3865 | 0.8532 | 0.8514 | 0.8532 | 0.8522 |
88
- | 0.0486 | 6.97 | 56 | 0.3445 | 0.8532 | 0.8495 | 0.8532 | 0.8507 |
89
- | 0.0346 | 7.97 | 64 | 0.3554 | 0.8807 | 0.8921 | 0.8807 | 0.8831 |
90
- | 0.0304 | 8.97 | 72 | 0.3100 | 0.8624 | 0.8592 | 0.8624 | 0.8605 |
91
- | 0.0215 | 9.97 | 80 | 0.3718 | 0.8716 | 0.8700 | 0.8716 | 0.8707 |
92
- | 0.0215 | 10.97 | 88 | 0.3946 | 0.8899 | 0.8901 | 0.8899 | 0.8896 |
93
- | 0.0201 | 11.97 | 96 | 0.4505 | 0.8532 | 0.8558 | 0.8532 | 0.8524 |
94
- | 0.02 | 12.97 | 104 | 0.4543 | 0.8716 | 0.8734 | 0.8716 | 0.8718 |
95
- | 0.0181 | 13.97 | 112 | 0.3837 | 0.8899 | 0.8878 | 0.8899 | 0.8884 |
96
- | 0.0158 | 14.97 | 120 | 0.3904 | 0.8716 | 0.8676 | 0.8716 | 0.8691 |
97
- | 0.0158 | 15.97 | 128 | 0.3881 | 0.9083 | 0.9078 | 0.9083 | 0.9077 |
98
- | 0.0147 | 16.97 | 136 | 0.4233 | 0.8807 | 0.8773 | 0.8807 | 0.8785 |
99
- | 0.0138 | 17.97 | 144 | 0.4335 | 0.8716 | 0.8700 | 0.8716 | 0.8707 |
100
- | 0.0166 | 18.97 | 152 | 0.4492 | 0.8716 | 0.8690 | 0.8716 | 0.8701 |
101
- | 0.016 | 19.97 | 160 | 0.4170 | 0.8716 | 0.8725 | 0.8716 | 0.8717 |
102
 
103
 
104
  ### Framework versions
105
 
106
- - Transformers 4.18.0
107
  - Pytorch 1.13.1+cu117
108
- - Datasets 2.6.1
109
  - Tokenizers 0.11.0
 
18
  dataset:
19
  name: imagefolder
20
  type: imagefolder
21
+ config: default
22
+ split: train
23
  args: default
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
+ value: 0.8807339449541285
28
  - name: Precision
29
  type: precision
30
+ value: 0.8768597487153273
31
  - name: Recall
32
  type: recall
33
+ value: 0.8807339449541285
34
  - name: F1
35
  type: f1
36
+ value: 0.8782945902988435
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
43
 
44
  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.
45
  It achieves the following results on the evaluation set:
46
+ - Loss: 0.3706
47
+ - Accuracy: 0.8807
48
+ - Precision: 0.8769
49
+ - Recall: 0.8807
50
+ - F1: 0.8783
51
 
52
  ## Model description
53
 
 
75
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
76
  - lr_scheduler_type: linear
77
  - lr_scheduler_warmup_ratio: 0.1
78
+ - num_epochs: 10
79
 
80
  ### Training results
81
 
82
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
83
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
84
+ | No log | 0.97 | 8 | 0.9902 | 0.5596 | 0.5506 | 0.5596 | 0.5360 |
85
+ | 1.242 | 1.97 | 16 | 0.5157 | 0.8165 | 0.8195 | 0.8165 | 0.8132 |
86
+ | 0.4438 | 2.97 | 24 | 0.3871 | 0.8440 | 0.8516 | 0.8440 | 0.8446 |
87
+ | 0.1768 | 3.97 | 32 | 0.3531 | 0.8624 | 0.8653 | 0.8624 | 0.8585 |
88
+ | 0.0661 | 4.97 | 40 | 0.3780 | 0.8716 | 0.8693 | 0.8716 | 0.8674 |
89
+ | 0.0661 | 5.97 | 48 | 0.3747 | 0.8624 | 0.8649 | 0.8624 | 0.8632 |
90
+ | 0.0375 | 6.97 | 56 | 0.3760 | 0.8991 | 0.8961 | 0.8991 | 0.8971 |
91
+ | 0.0362 | 7.97 | 64 | 0.4092 | 0.8716 | 0.8684 | 0.8716 | 0.8681 |
92
+ | 0.0322 | 8.97 | 72 | 0.3499 | 0.8899 | 0.8880 | 0.8899 | 0.8888 |
93
+ | 0.029 | 9.97 | 80 | 0.3706 | 0.8807 | 0.8769 | 0.8807 | 0.8783 |
 
 
 
 
 
 
 
 
 
 
94
 
95
 
96
  ### Framework versions
97
 
98
+ - Transformers 4.25.1
99
  - Pytorch 1.13.1+cu117
100
+ - Datasets 2.8.0
101
  - Tokenizers 0.11.0