Hugging Face's logo

jhoppanne
/
Dogs-Breed-Image-Classification-V2

Image Classification
Transformers
Safetensors
resnet
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
jhoppanne commited on
Commit
e7cb0f8
•
1 Parent(s): 418133b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +121 -94
README.md CHANGED
@@ -1,94 +1,121 @@
1
- ---
2
- license: apache-2.0
3
- base_model: microsoft/resnet-152
4
- tags:
5
- - generated_from_trainer
6
- datasets:
7
- - imagefolder
8
- metrics:
9
- - accuracy
10
- model-index:
11
- - name: Dogs-Breed-Image-Classification-V2
12
- results:
13
- - task:
14
- name: Image Classification
15
- type: image-classification
16
- dataset:
17
- name: imagefolder
18
- type: imagefolder
19
- config: default
20
- split: train
21
- args: default
22
- metrics:
23
- - name: Accuracy
24
- type: accuracy
25
- value: 0.8408163265306122
26
- ---
27
-
28
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
- should probably proofread and complete it, then remove this comment. -->
30
-
31
- # Dogs-Breed-Image-Classification-V2
32
-
33
- This model is a fine-tuned version of [microsoft/resnet-152](https://huggingface.co/microsoft/resnet-152) on the imagefolder dataset.
34
- It achieves the following results on the evaluation set:
35
- - Loss: 1.0115
36
- - Accuracy: 0.8408
37
-
38
- ## Model description
39
-
40
- More information needed
41
-
42
- ## Intended uses & limitations
43
-
44
- More information needed
45
-
46
- ## Training and evaluation data
47
-
48
- More information needed
49
-
50
- ## Training procedure
51
-
52
- ### Training hyperparameters
53
-
54
- The following hyperparameters were used during training:
55
- - learning_rate: 5e-06
56
- - train_batch_size: 32
57
- - eval_batch_size: 32
58
- - seed: 42
59
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
- - lr_scheduler_type: linear
61
- - num_epochs: 20
62
-
63
- ### Training results
64
-
65
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 483 | 4.6525 | 0.7382 |
68
- | 4.7329 | 2.0 | 966 | 4.3558 | 0.7298 |
69
- | 4.5033 | 3.0 | 1449 | 3.9568 | 0.7471 |
70
- | 4.1405 | 4.0 | 1932 | 3.5160 | 0.7782 |
71
- | 3.7176 | 5.0 | 2415 | 3.0805 | 0.7946 |
72
- | 3.293 | 6.0 | 2898 | 2.6907 | 0.8021 |
73
- | 2.8898 | 7.0 | 3381 | 2.3044 | 0.8126 |
74
- | 2.5343 | 8.0 | 3864 | 2.0091 | 0.8177 |
75
- | 2.2188 | 9.0 | 4347 | 1.7910 | 0.8126 |
76
- | 1.9698 | 10.0 | 4830 | 1.6015 | 0.8194 |
77
- | 1.7532 | 11.0 | 5313 | 1.4383 | 0.8220 |
78
- | 1.586 | 12.0 | 5796 | 1.3355 | 0.8264 |
79
- | 1.4533 | 13.0 | 6279 | 1.2467 | 0.8260 |
80
- | 1.336 | 14.0 | 6762 | 1.1575 | 0.8313 |
81
- | 1.2641 | 15.0 | 7245 | 1.1038 | 0.8321 |
82
- | 1.185 | 16.0 | 7728 | 1.0606 | 0.8395 |
83
- | 1.1329 | 17.0 | 8211 | 1.0178 | 0.8398 |
84
- | 1.0977 | 18.0 | 8694 | 1.0115 | 0.8408 |
85
- | 1.0732 | 19.0 | 9177 | 0.9945 | 0.8381 |
86
- | 1.0508 | 20.0 | 9660 | 0.9930 | 0.8393 |
87
-
88
-
89
- ### Framework versions
90
-
91
- - Transformers 4.37.2
92
- - Pytorch 2.3.0
93
- - Datasets 2.15.0
94
- - Tokenizers 0.15.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/resnet-152
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: Dogs-Breed-Image-Classification-V2
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: imagefolder
18
+ type: imagefolder
19
+ config: default
20
+ split: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.8408163265306122
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # Dogs-Breed-Image-Classification-V2
32
+
33
+ This model is a fine-tuned version of [microsoft/resnet-152](https://huggingface.co/microsoft/resnet-152) on the [Standford dogs dataset](https://www.kaggle.com/datasets/jessicali9530/stanford-dogs-dataset.).
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.0115
36
+ - Accuracy: 0.8408
37
+
38
+ ## Model description
39
+
40
+ [Link to the fine-tuned model using resnet-50](https://huggingface.co/jhoppanne/Dogs-Breed-Image-Classification-V0)
41
+ [Link to the fine-tuned model using resnet-101](https://huggingface.co/jhoppanne/Dogs-Breed-Image-Classification-V1)
42
+ This model was trained using dataset from [Kaggle - Standford dogs dataset](https://www.kaggle.com/datasets/jessicali9530/stanford-dogs-dataset.)
43
+
44
+ Quotes from the website:
45
+ The Stanford Dogs dataset contains images of 120 breeds of dogs from around the world. This dataset has been built using images and annotation from ImageNet for the task of fine-grained image categorization. It was originally collected for fine-grain image categorization, a challenging problem as certain dog breeds have near identical features or differ in colour and age.
46
+
47
+ citation:
48
+ Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao and Li Fei-Fei. Novel dataset for Fine-Grained Image Categorization. First Workshop on Fine-Grained Visual Categorization (FGVC), IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011. [pdf] [poster] [BibTex]
49
+
50
+ Secondary:
51
+ J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li and L. Fei-Fei, ImageNet: A Large-Scale Hierarchical Image Database. IEEE Computer Vision and Pattern Recognition (CVPR), 2009. [pdf] [BibTex]
52
+ ## Intended uses & limitations
53
+
54
+ This model is fined tune solely for classifiying 120 species of dogs.
55
+
56
+ ## Training and evaluation data
57
+
58
+ 75% training data, 25% testing data.
59
+ More information needed
60
+
61
+
62
+ ## Training procedure
63
+
64
+ ### Training hyperparameters
65
+
66
+ The following hyperparameters were used during training:
67
+ - learning_rate: 1e-05
68
+ - train_batch_size: 32
69
+ - eval_batch_size: 32
70
+ - seed: 42
71
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
72
+ - lr_scheduler_type: linear
73
+ - num_epochs: 100
74
+
75
+ ### Training results
76
+
77
+ ## Training procedure
78
+
79
+ ### Training hyperparameters
80
+
81
+ The following hyperparameters were used during training:
82
+ - learning_rate: 5e-06
83
+ - train_batch_size: 32
84
+ - eval_batch_size: 32
85
+ - seed: 42
86
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
87
+ - lr_scheduler_type: linear
88
+ - num_epochs: 20
89
+
90
+ ### Training results
91
+
92
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
93
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
94
+ | No log | 1.0 | 483 | 4.6525 | 0.7382 |
95
+ | 4.7329 | 2.0 | 966 | 4.3558 | 0.7298 |
96
+ | 4.5033 | 3.0 | 1449 | 3.9568 | 0.7471 |
97
+ | 4.1405 | 4.0 | 1932 | 3.5160 | 0.7782 |
98
+ | 3.7176 | 5.0 | 2415 | 3.0805 | 0.7946 |
99
+ | 3.293 | 6.0 | 2898 | 2.6907 | 0.8021 |
100
+ | 2.8898 | 7.0 | 3381 | 2.3044 | 0.8126 |
101
+ | 2.5343 | 8.0 | 3864 | 2.0091 | 0.8177 |
102
+ | 2.2188 | 9.0 | 4347 | 1.7910 | 0.8126 |
103
+ | 1.9698 | 10.0 | 4830 | 1.6015 | 0.8194 |
104
+ | 1.7532 | 11.0 | 5313 | 1.4383 | 0.8220 |
105
+ | 1.586 | 12.0 | 5796 | 1.3355 | 0.8264 |
106
+ | 1.4533 | 13.0 | 6279 | 1.2467 | 0.8260 |
107
+ | 1.336 | 14.0 | 6762 | 1.1575 | 0.8313 |
108
+ | 1.2641 | 15.0 | 7245 | 1.1038 | 0.8321 |
109
+ | 1.185 | 16.0 | 7728 | 1.0606 | 0.8395 |
110
+ | 1.1329 | 17.0 | 8211 | 1.0178 | 0.8398 |
111
+ | 1.0977 | 18.0 | 8694 | 1.0115 | 0.8408 |
112
+ | 1.0732 | 19.0 | 9177 | 0.9945 | 0.8381 |
113
+ | 1.0508 | 20.0 | 9660 | 0.9930 | 0.8393 |
114
+
115
+
116
+ ### Framework versions
117
+
118
+ - Transformers 4.37.2
119
+ - Pytorch 2.3.0
120
+ - Datasets 2.15.0
121
+ - Tokenizers 0.15.1