Hugging Face's logo

Sai1212
/
swin-finetuned-food101

Image Classification
Transformers
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Sai1212 commited on
Commit
ed57e1a
·
1 Parent(s): 8335640

Model save

Browse files
Files changed (2) hide show
  1. README.md +17 -17
  2. model.safetensors +1 -1
README.md CHANGED
@@ -20,18 +20,18 @@ model-index:
20
  name: imagefolder
21
  type: imagefolder
22
  config: default
23
- split: test
24
  args: default
25
  metrics:
26
  - name: Accuracy
27
  type: accuracy
28
- value: 0.5189873417721519
29
  - name: F1
30
  type: f1
31
- value: 0.6833333333333332
32
  - name: Precision
33
  type: precision
34
- value: 0.5189873417721519
35
  - name: Recall
36
  type: recall
37
  value: 1.0
@@ -44,12 +44,12 @@ should probably proofread and complete it, then remove this comment. -->
44
 
45
  This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224](https://huggingface.co/microsoft/swin-base-patch4-window7-224) on the imagefolder dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.6925
48
- - Accuracy: 0.5190
49
- - F1: 0.6833
50
- - Precision: 0.5190
51
  - Recall: 1.0
52
- - Auc: 0.3773
53
 
54
  ## Model description
55
 
@@ -69,11 +69,11 @@ More information needed
69
 
70
  The following hyperparameters were used during training:
71
  - learning_rate: 0.001
72
- - train_batch_size: 8
73
- - eval_batch_size: 8
74
  - seed: 42
75
  - gradient_accumulation_steps: 2
76
- - total_train_batch_size: 16
77
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
78
  - lr_scheduler_type: linear
79
  - lr_scheduler_warmup_ratio: 0.06
@@ -83,11 +83,11 @@ The following hyperparameters were used during training:
83
 
84
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Auc |
85
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:------:|
86
- | 0.7016 | 0.99 | 55 | 0.7054 | 0.4810 | 0.0 | 0.0 | 0.0 | 0.4744 |
87
- | 0.6894 | 2.0 | 111 | 0.6948 | 0.5190 | 0.6833 | 0.5190 | 1.0 | 0.4474 |
88
- | 0.6905 | 2.99 | 166 | 0.6924 | 0.5190 | 0.6833 | 0.5190 | 1.0 | 0.6050 |
89
- | 0.6956 | 4.0 | 222 | 0.6925 | 0.5190 | 0.6833 | 0.5190 | 1.0 | 0.3829 |
90
- | 0.6909 | 4.95 | 275 | 0.6925 | 0.5190 | 0.6833 | 0.5190 | 1.0 | 0.3773 |
91
 
92
 
93
  ### Framework versions
 
20
  name: imagefolder
21
  type: imagefolder
22
  config: default
23
+ split: validation
24
  args: default
25
  metrics:
26
  - name: Accuracy
27
  type: accuracy
28
+ value: 0.4166666666666667
29
  - name: F1
30
  type: f1
31
+ value: 0.5882352941176471
32
  - name: Precision
33
  type: precision
34
+ value: 0.4166666666666667
35
  - name: Recall
36
  type: recall
37
  value: 1.0
 
44
 
45
  This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224](https://huggingface.co/microsoft/swin-base-patch4-window7-224) on the imagefolder dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.7046
48
+ - Accuracy: 0.4167
49
+ - F1: 0.5882
50
+ - Precision: 0.4167
51
  - Recall: 1.0
52
+ - Auc: 0.5742
53
 
54
  ## Model description
55
 
 
69
 
70
  The following hyperparameters were used during training:
71
  - learning_rate: 0.001
72
+ - train_batch_size: 32
73
+ - eval_batch_size: 32
74
  - seed: 42
75
  - gradient_accumulation_steps: 2
76
+ - total_train_batch_size: 64
77
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
78
  - lr_scheduler_type: linear
79
  - lr_scheduler_warmup_ratio: 0.06
 
83
 
84
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Auc |
85
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:------:|
86
+ | 0.6978 | 1.0 | 14 | 0.6847 | 0.5833 | 0.0 | 0.0 | 0.0 | 0.5717 |
87
+ | 0.7025 | 2.0 | 28 | 0.7120 | 0.4167 | 0.5882 | 0.4167 | 1.0 | 0.5570 |
88
+ | 0.6946 | 3.0 | 42 | 0.6955 | 0.4167 | 0.5882 | 0.4167 | 1.0 | 0.5662 |
89
+ | 0.6935 | 4.0 | 56 | 0.7047 | 0.4167 | 0.5882 | 0.4167 | 1.0 | 0.5644 |
90
+ | 0.6935 | 5.0 | 70 | 0.7046 | 0.4167 | 0.5882 | 0.4167 | 1.0 | 0.5742 |
91
 
92
 
93
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7e81535cb1ebb2c11fe1b739514bb790c18128fff8ecf6f024ffe30a1bd020f
3
  size 347498816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37cf9640c6f10cc7e911b6dfbe151b70bba5d384259443373156e6ffed08b0f6
3
  size 347498816