Hugging Face's logo

prakhardixit24
/
urinary_carcinoma_classifier_g001

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
prakhardixit24 commited on
Commit
943833c
•
1 Parent(s): ff14c11

End of training

Browse files
Files changed (2) hide show
  1. README.md +25 -55
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,12 +17,12 @@ model-index:
17
  name: imagefolder
18
  type: imagefolder
19
  config: default
20
- split: train[:34]
21
  args: default
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8571428571428571
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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.1765
36
- - Accuracy: 0.8571
37
 
38
  ## Model description
39
 
@@ -61,62 +61,32 @@ The following hyperparameters were used during training:
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: 50
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 1.0 | 1 | 0.6758 | 0.5714 |
71
- | No log | 2.0 | 2 | 0.6747 | 0.5714 |
72
- | No log | 3.0 | 3 | 0.6558 | 0.5714 |
73
- | No log | 4.0 | 4 | 0.6576 | 0.5714 |
74
- | No log | 5.0 | 5 | 0.6297 | 0.5714 |
75
- | No log | 6.0 | 6 | 0.6131 | 0.5714 |
76
- | No log | 7.0 | 7 | 0.5552 | 0.5714 |
77
- | No log | 8.0 | 8 | 0.5017 | 0.7143 |
78
- | No log | 9.0 | 9 | 0.4695 | 0.8571 |
79
- | 0.2846 | 10.0 | 10 | 0.4277 | 0.8571 |
80
- | 0.2846 | 11.0 | 11 | 0.4228 | 0.8571 |
81
- | 0.2846 | 12.0 | 12 | 0.4115 | 0.8571 |
82
- | 0.2846 | 13.0 | 13 | 0.3575 | 1.0 |
83
- | 0.2846 | 14.0 | 14 | 0.4240 | 0.8571 |
84
- | 0.2846 | 15.0 | 15 | 0.3832 | 1.0 |
85
- | 0.2846 | 16.0 | 16 | 0.3363 | 1.0 |
86
- | 0.2846 | 17.0 | 17 | 0.3375 | 0.8571 |
87
- | 0.2846 | 18.0 | 18 | 0.3222 | 1.0 |
88
- | 0.2846 | 19.0 | 19 | 0.2372 | 1.0 |
89
- | 0.141 | 20.0 | 20 | 0.2795 | 1.0 |
90
- | 0.141 | 21.0 | 21 | 0.2726 | 1.0 |
91
- | 0.141 | 22.0 | 22 | 0.2010 | 1.0 |
92
- | 0.141 | 23.0 | 23 | 0.1791 | 1.0 |
93
- | 0.141 | 24.0 | 24 | 0.1794 | 1.0 |
94
- | 0.141 | 25.0 | 25 | 0.2308 | 1.0 |
95
- | 0.141 | 26.0 | 26 | 0.1686 | 1.0 |
96
- | 0.141 | 27.0 | 27 | 0.2678 | 0.8571 |
97
- | 0.141 | 28.0 | 28 | 0.3142 | 0.8571 |
98
- | 0.141 | 29.0 | 29 | 0.1509 | 1.0 |
99
- | 0.072 | 30.0 | 30 | 0.1522 | 1.0 |
100
- | 0.072 | 31.0 | 31 | 0.1862 | 1.0 |
101
- | 0.072 | 32.0 | 32 | 0.1927 | 1.0 |
102
- | 0.072 | 33.0 | 33 | 0.1600 | 1.0 |
103
- | 0.072 | 34.0 | 34 | 0.1520 | 1.0 |
104
- | 0.072 | 35.0 | 35 | 0.1377 | 1.0 |
105
- | 0.072 | 36.0 | 36 | 0.2727 | 0.8571 |
106
- | 0.072 | 37.0 | 37 | 0.1470 | 1.0 |
107
- | 0.072 | 38.0 | 38 | 0.2727 | 0.8571 |
108
- | 0.072 | 39.0 | 39 | 0.2244 | 0.8571 |
109
- | 0.0444 | 40.0 | 40 | 0.1122 | 1.0 |
110
- | 0.0444 | 41.0 | 41 | 0.2727 | 0.8571 |
111
- | 0.0444 | 42.0 | 42 | 0.2733 | 0.8571 |
112
- | 0.0444 | 43.0 | 43 | 0.2109 | 0.8571 |
113
- | 0.0444 | 44.0 | 44 | 0.3147 | 0.8571 |
114
- | 0.0444 | 45.0 | 45 | 0.3256 | 0.8571 |
115
- | 0.0444 | 46.0 | 46 | 0.2474 | 0.8571 |
116
- | 0.0444 | 47.0 | 47 | 0.2670 | 0.8571 |
117
- | 0.0444 | 48.0 | 48 | 0.2003 | 0.8571 |
118
- | 0.0444 | 49.0 | 49 | 0.2966 | 0.8571 |
119
- | 0.0361 | 50.0 | 50 | 0.1765 | 0.8571 |
120
 
121
 
122
  ### Framework versions
 
17
  name: imagefolder
18
  type: imagefolder
19
  config: default
20
+ split: train[:42]
21
  args: default
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.5555555555555556
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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.5640
36
+ - Accuracy: 0.5556
37
 
38
  ## Model description
39
 
 
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: 30
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 1.0 | 1 | 0.6804 | 0.6667 |
71
+ | No log | 2.0 | 3 | 0.6845 | 0.5556 |
72
+ | No log | 3.0 | 5 | 0.6237 | 0.8889 |
73
+ | No log | 4.0 | 6 | 0.6130 | 0.8889 |
74
+ | No log | 5.0 | 7 | 0.6384 | 0.7778 |
75
+ | No log | 6.0 | 9 | 0.6083 | 0.7778 |
76
+ | 0.3049 | 7.0 | 11 | 0.6127 | 0.6667 |
77
+ | 0.3049 | 8.0 | 12 | 0.5927 | 0.7778 |
78
+ | 0.3049 | 9.0 | 13 | 0.5831 | 0.6667 |
79
+ | 0.3049 | 10.0 | 15 | 0.5348 | 0.7778 |
80
+ | 0.3049 | 11.0 | 17 | 0.5355 | 0.7778 |
81
+ | 0.3049 | 12.0 | 18 | 0.5647 | 0.6667 |
82
+ | 0.3049 | 13.0 | 19 | 0.6167 | 0.6667 |
83
+ | 0.1811 | 14.0 | 21 | 0.5312 | 0.6667 |
84
+ | 0.1811 | 15.0 | 23 | 0.5317 | 0.7778 |
85
+ | 0.1811 | 16.0 | 24 | 0.4629 | 0.7778 |
86
+ | 0.1811 | 17.0 | 25 | 0.5841 | 0.7778 |
87
+ | 0.1811 | 18.0 | 27 | 0.5784 | 0.5556 |
88
+ | 0.1811 | 19.0 | 29 | 0.5081 | 0.7778 |
89
+ | 0.1359 | 20.0 | 30 | 0.5640 | 0.5556 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
90
 
91
 
92
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dbdb51b36cdec7fb7f63b50c9889a9428fa948f36dae5c518234c28b75f2d5b
3
  size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e895a4e9539953d5735728adfb81a49793cd130870b4ecd31931cf28f60abbe
3
  size 343223968