Diginsa commited on
Commit
ed89379
·
verified ·
1 Parent(s): 1002d58

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -54
README.md CHANGED
@@ -13,61 +13,9 @@ datasets:
13
  pipeline_tag: image-classification
14
  ---
15
 
16
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
- should probably proofread and complete it, then remove this comment. -->
18
-
19
  # mobilenet_v2_1.0_224-plant-disease-new
20
 
21
  This model is a fine-tuned version of [google/mobilenet_v2_1.0_224](https://huggingface.co/google/mobilenet_v2_1.0_224) on imagenet-1k dataset dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.1287
24
- - Accuracy: 0.9812
25
-
26
- ## Model description
27
-
28
- More information needed
29
-
30
- ## Intended uses & limitations
31
-
32
- More information needed
33
-
34
- ## Training and evaluation data
35
-
36
- More information needed
37
-
38
- ## Training procedure
39
-
40
- ### Training hyperparameters
41
-
42
- The following hyperparameters were used during training:
43
- - learning_rate: 5e-05
44
- - train_batch_size: 110
45
- - eval_batch_size: 110
46
- - seed: 42
47
- - gradient_accumulation_steps: 4
48
- - total_train_batch_size: 500
49
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
- - lr_scheduler_type: linear
51
- - lr_scheduler_warmup_ratio: 0.1
52
- - num_epochs: 8
53
-
54
- ### Training results
55
-
56
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
57
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
58
- | 0.5043 | 1.0 | 366 | 0.4476 | 0.8886 |
59
- | 0.2492 | 2.0 | 733 | 0.2550 | 0.9281 |
60
- | 0.2069 | 3.0 | 1100 | 0.2332 | 0.9247 |
61
- | 0.1716 | 4.0 | 1467 | 0.3329 | 0.8960 |
62
- | 0.1602 | 5.0 | 1833 | 0.1999 | 0.9388 |
63
- | 0.1633 | 5.99 | 2196 | 0.1287 | 0.9600 |
64
- | 0.1663 | 6.01 | 2410 | 0.1328 | 0.9790 |
65
- | 0.1824 | 6.79 | 2535 | 0.1637 | 0.9812 |
66
-
67
-
68
- ### Framework versions
69
-
70
- - Transformers 4.35.2
71
- - Pytorch 2.1.0+cu121
72
- - Datasets 2.16.0
73
- - Tokenizers 0.15.0
 
13
  pipeline_tag: image-classification
14
  ---
15
 
 
 
 
16
  # mobilenet_v2_1.0_224-plant-disease-new
17
 
18
  This model is a fine-tuned version of [google/mobilenet_v2_1.0_224](https://huggingface.co/google/mobilenet_v2_1.0_224) on imagenet-1k dataset dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.7510
21
+ - Accuracy: 0.24