Hugging Face's logo

HorcruxNo13
/
pvt-tiny-224

Image Classification
Transformers
PyTorch
pvt
Generated from Trainer
Eval Results
Model card Files
xet
Community
1
HorcruxNo13 commited on
Commit
55e5627
·
1 Parent(s): 2b5d289

Model save

Browse files
Files changed (2) hide show
  1. README.md +40 -25
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -24,13 +24,13 @@ model-index:
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.8866666666666667
28
  - name: Precision
29
  type: precision
30
- value: 0.8696446479180292
31
  - name: Recall
32
  type: recall
33
- value: 0.8866666666666667
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,11 +40,11 @@ should probably proofread and complete it, then remove this comment. -->
40
 
41
  This model is a fine-tuned version of [Zetatech/pvt-tiny-224](https://huggingface.co/Zetatech/pvt-tiny-224) on the imagefolder dataset.
42
  It achieves the following results on the evaluation set:
43
- - Loss: 0.3101
44
- - Accuracy: 0.8867
45
- - Precision: 0.8696
46
- - Recall: 0.8867
47
- - F1 Score: 0.8732
48
 
49
  ## Model description
50
 
@@ -72,32 +72,47 @@ The following hyperparameters were used during training:
72
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
  - lr_scheduler_type: linear
74
  - lr_scheduler_warmup_ratio: 0.1
75
- - num_epochs: 15
76
 
77
  ### Training results
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
80
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
81
- | No log | 1.0 | 4 | 0.3871 | 0.8708 | 0.7584 | 0.8708 | 0.8107 |
82
- | No log | 2.0 | 8 | 0.3643 | 0.8708 | 0.7584 | 0.8708 | 0.8107 |
83
- | No log | 3.0 | 12 | 0.3967 | 0.8708 | 0.7584 | 0.8708 | 0.8107 |
84
- | 0.4822 | 4.0 | 16 | 0.3791 | 0.8708 | 0.8256 | 0.8708 | 0.8183 |
85
- | 0.4822 | 5.0 | 20 | 0.5400 | 0.7583 | 0.8645 | 0.7583 | 0.7929 |
86
- | 0.4822 | 6.0 | 24 | 0.3422 | 0.8958 | 0.8835 | 0.8958 | 0.8859 |
87
- | 0.4822 | 7.0 | 28 | 0.3987 | 0.8583 | 0.8782 | 0.8583 | 0.8664 |
88
- | 0.3927 | 8.0 | 32 | 0.2988 | 0.9125 | 0.9059 | 0.9125 | 0.9077 |
89
- | 0.3927 | 9.0 | 36 | 0.2899 | 0.9083 | 0.9005 | 0.9083 | 0.9024 |
90
- | 0.3927 | 10.0 | 40 | 0.2881 | 0.9083 | 0.9005 | 0.9083 | 0.9024 |
91
- | 0.3927 | 11.0 | 44 | 0.2787 | 0.9125 | 0.9059 | 0.9125 | 0.9077 |
92
- | 0.3561 | 12.0 | 48 | 0.2923 | 0.8958 | 0.8973 | 0.8958 | 0.8965 |
93
- | 0.3561 | 13.0 | 52 | 0.2960 | 0.9042 | 0.9055 | 0.9042 | 0.9048 |
94
- | 0.3561 | 14.0 | 56 | 0.3073 | 0.8958 | 0.9003 | 0.8958 | 0.8979 |
95
- | 0.3382 | 15.0 | 60 | 0.3018 | 0.9 | 0.9028 | 0.9 | 0.9013 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96
 
97
 
98
  ### Framework versions
99
 
100
- - Transformers 4.33.2
101
  - Pytorch 2.0.1+cu118
102
  - Datasets 2.14.5
103
  - Tokenizers 0.13.3
 
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
+ value: 0.7833333333333333
28
  - name: Precision
29
  type: precision
30
+ value: 0.7680555555555556
31
  - name: Recall
32
  type: recall
33
+ value: 0.7833333333333333
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
40
 
41
  This model is a fine-tuned version of [Zetatech/pvt-tiny-224](https://huggingface.co/Zetatech/pvt-tiny-224) on the imagefolder dataset.
42
  It achieves the following results on the evaluation set:
43
+ - Loss: 0.4869
44
+ - Accuracy: 0.7833
45
+ - Precision: 0.7681
46
+ - Recall: 0.7833
47
+ - F1 Score: 0.7632
48
 
49
  ## Model description
50
 
 
72
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
  - lr_scheduler_type: linear
74
  - lr_scheduler_warmup_ratio: 0.1
75
+ - num_epochs: 30
76
 
77
  ### Training results
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
80
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
81
+ | No log | 1.0 | 4 | 0.5984 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
82
+ | No log | 2.0 | 8 | 0.6103 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
83
+ | No log | 3.0 | 12 | 0.5861 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
84
+ | No log | 4.0 | 16 | 0.5478 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
85
+ | No log | 5.0 | 20 | 0.5961 | 0.725 | 0.7119 | 0.725 | 0.7171 |
86
+ | No log | 6.0 | 24 | 0.5317 | 0.7542 | 0.7261 | 0.7542 | 0.7159 |
87
+ | No log | 7.0 | 28 | 0.5620 | 0.7458 | 0.7289 | 0.7458 | 0.7342 |
88
+ | 0.5878 | 8.0 | 32 | 0.5281 | 0.7542 | 0.7316 | 0.7542 | 0.6973 |
89
+ | 0.5878 | 9.0 | 36 | 0.5434 | 0.7625 | 0.7395 | 0.7625 | 0.7368 |
90
+ | 0.5878 | 10.0 | 40 | 0.5236 | 0.775 | 0.7658 | 0.775 | 0.7321 |
91
+ | 0.5878 | 11.0 | 44 | 0.5411 | 0.7542 | 0.7382 | 0.7542 | 0.7429 |
92
+ | 0.5878 | 12.0 | 48 | 0.5186 | 0.7708 | 0.7507 | 0.7708 | 0.7460 |
93
+ | 0.5878 | 13.0 | 52 | 0.5194 | 0.7667 | 0.7500 | 0.7667 | 0.7533 |
94
+ | 0.5878 | 14.0 | 56 | 0.5049 | 0.7875 | 0.7739 | 0.7875 | 0.7621 |
95
+ | 0.4973 | 15.0 | 60 | 0.5125 | 0.7833 | 0.7691 | 0.7833 | 0.7709 |
96
+ | 0.4973 | 16.0 | 64 | 0.5000 | 0.7917 | 0.7804 | 0.7917 | 0.7656 |
97
+ | 0.4973 | 17.0 | 68 | 0.5137 | 0.7583 | 0.7560 | 0.7583 | 0.7571 |
98
+ | 0.4973 | 18.0 | 72 | 0.4833 | 0.8 | 0.788 | 0.8 | 0.7833 |
99
+ | 0.4973 | 19.0 | 76 | 0.4929 | 0.7917 | 0.7816 | 0.7917 | 0.7843 |
100
+ | 0.4973 | 20.0 | 80 | 0.4858 | 0.8042 | 0.7930 | 0.8042 | 0.7887 |
101
+ | 0.4973 | 21.0 | 84 | 0.4900 | 0.7917 | 0.7777 | 0.7917 | 0.7743 |
102
+ | 0.4973 | 22.0 | 88 | 0.4886 | 0.7958 | 0.7829 | 0.7958 | 0.7815 |
103
+ | 0.439 | 23.0 | 92 | 0.4841 | 0.7917 | 0.7778 | 0.7917 | 0.7723 |
104
+ | 0.439 | 24.0 | 96 | 0.4855 | 0.8 | 0.7883 | 0.8 | 0.7885 |
105
+ | 0.439 | 25.0 | 100 | 0.4856 | 0.8 | 0.7879 | 0.8 | 0.7869 |
106
+ | 0.439 | 26.0 | 104 | 0.4839 | 0.8 | 0.7879 | 0.8 | 0.7869 |
107
+ | 0.439 | 27.0 | 108 | 0.4811 | 0.8 | 0.7879 | 0.8 | 0.7869 |
108
+ | 0.439 | 28.0 | 112 | 0.4834 | 0.8 | 0.7889 | 0.8 | 0.7901 |
109
+ | 0.439 | 29.0 | 116 | 0.4839 | 0.8 | 0.7889 | 0.8 | 0.7901 |
110
+ | 0.4092 | 30.0 | 120 | 0.4838 | 0.8 | 0.7889 | 0.8 | 0.7901 |
111
 
112
 
113
  ### Framework versions
114
 
115
+ - Transformers 4.33.3
116
  - Pytorch 2.0.1+cu118
117
  - Datasets 2.14.5
118
  - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6176d06af83264871f16e6b1764735f9134b388ed0191852838cffa182e1948f
3
  size 50929233
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b634115061b638cf372f48bb088fe3d94d8afe2c75853ffe16d6cb6855a3169f
3
  size 50929233