Hugging Face's logo

louislu9911
/
convnextv2-base-1k-224-finetuned-cassava-leaf-disease

Image Classification
Transformers
Safetensors
convnextv2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
louislu9911 commited on
Commit
572788c
•
1 Parent(s): 4aae5ec

Model save

Browse files
Files changed (2) hide show
  1. README.md +27 -22
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8845794392523364
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/convnextv2-base-1k-224](https://huggingface.co/facebook/convnextv2-base-1k-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3329
36
- - Accuracy: 0.8846
37
 
38
  ## Model description
39
 
@@ -53,35 +53,40 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
- - train_batch_size: 240
57
- - eval_batch_size: 240
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 960
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 15
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.7644 | 0.99 | 20 | 1.5288 | 0.6140 |
71
- | 0.8358 | 1.98 | 40 | 0.6582 | 0.7584 |
72
- | 0.5367 | 2.96 | 60 | 0.4823 | 0.8229 |
73
- | 0.4645 | 4.0 | 81 | 0.4269 | 0.8556 |
74
- | 0.4218 | 4.99 | 101 | 0.3912 | 0.8659 |
75
- | 0.391 | 5.98 | 121 | 0.3637 | 0.8748 |
76
- | 0.3789 | 6.96 | 141 | 0.3554 | 0.8748 |
77
- | 0.3684 | 8.0 | 162 | 0.3489 | 0.8790 |
78
- | 0.3671 | 8.99 | 182 | 0.3503 | 0.8813 |
79
- | 0.3545 | 9.98 | 202 | 0.3442 | 0.8818 |
80
- | 0.339 | 10.96 | 222 | 0.3369 | 0.8841 |
81
- | 0.3225 | 12.0 | 243 | 0.3424 | 0.8808 |
82
- | 0.3228 | 12.99 | 263 | 0.3386 | 0.8850 |
83
- | 0.3141 | 13.98 | 283 | 0.3344 | 0.8846 |
84
- | 0.3219 | 14.81 | 300 | 0.3329 | 0.8846 |
 
 
 
 
 
85
 
86
 
87
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8841121495327103
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/convnextv2-base-1k-224](https://huggingface.co/facebook/convnextv2-base-1k-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.3624
36
+ - Accuracy: 0.8841
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
+ - train_batch_size: 360
57
+ - eval_batch_size: 360
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 1440
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 20
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 7.5825 | 0.96 | 13 | 2.5252 | 0.4874 |
71
+ | 2.4869 | 2.0 | 27 | 1.0172 | 0.6388 |
72
+ | 0.7793 | 2.96 | 40 | 0.6048 | 0.7925 |
73
+ | 0.5807 | 4.0 | 54 | 0.4873 | 0.8327 |
74
+ | 0.5079 | 4.96 | 67 | 0.4330 | 0.8514 |
75
+ | 0.4363 | 6.0 | 81 | 0.4140 | 0.8668 |
76
+ | 0.4118 | 6.96 | 94 | 0.3962 | 0.8743 |
77
+ | 0.3918 | 8.0 | 108 | 0.3924 | 0.8748 |
78
+ | 0.3669 | 8.96 | 121 | 0.3816 | 0.8822 |
79
+ | 0.3687 | 10.0 | 135 | 0.3784 | 0.8776 |
80
+ | 0.3645 | 10.96 | 148 | 0.3684 | 0.8846 |
81
+ | 0.349 | 12.0 | 162 | 0.3706 | 0.8804 |
82
+ | 0.3341 | 12.96 | 175 | 0.3678 | 0.8813 |
83
+ | 0.3304 | 14.0 | 189 | 0.3618 | 0.8794 |
84
+ | 0.3318 | 14.96 | 202 | 0.3677 | 0.8808 |
85
+ | 0.3178 | 16.0 | 216 | 0.3626 | 0.8818 |
86
+ | 0.3209 | 16.96 | 229 | 0.3606 | 0.8822 |
87
+ | 0.3129 | 18.0 | 243 | 0.3615 | 0.8836 |
88
+ | 0.3013 | 18.96 | 256 | 0.3627 | 0.8841 |
89
+ | 0.3046 | 19.26 | 260 | 0.3624 | 0.8841 |
90
 
91
 
92
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17abe3bf842460e1adf03eb539eb3dd4a001bf425f21312d7b13e9a3ae9eea44
3
  size 354917376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5215b1cb17a06adc87d14731da8aed2d258b40284fbb22a5ca735123282ae395
3
  size 354917376