Hugging Face's logo

sbottazzi
/
12-classifier-finetuned-padchest

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
1
Sabrina Bottazzi commited on
Commit
63ae45d
·
1 Parent(s): cf4b8f8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +176 -0
README.md ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ metrics:
8
+ - f1
9
+ model-index:
10
+ - name: 12-classifier-finetuned-padchest
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ config: default
19
+ split: train
20
+ args: default
21
+ metrics:
22
+ - name: F1
23
+ type: f1
24
+ value: 0.7424084315546235
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # 12-classifier-finetuned-padchest
31
+
32
+ This model is a fine-tuned version of [nickmuchi/vit-finetuned-chest-xray-pneumonia](https://huggingface.co/nickmuchi/vit-finetuned-chest-xray-pneumonia) on the imagefolder dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.9215
35
+ - F1: 0.7424
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 5e-05
55
+ - train_batch_size: 32
56
+ - eval_batch_size: 32
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 128
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 100
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
68
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
69
+ | 2.0498 | 1.0 | 18 | 1.9843 | 0.2451 |
70
+ | 1.9376 | 2.0 | 36 | 1.8429 | 0.2757 |
71
+ | 1.7541 | 3.0 | 54 | 1.7097 | 0.2984 |
72
+ | 1.6052 | 4.0 | 72 | 1.5666 | 0.4007 |
73
+ | 1.4372 | 5.0 | 90 | 1.4392 | 0.4857 |
74
+ | 1.3696 | 6.0 | 108 | 1.3127 | 0.4894 |
75
+ | 1.2546 | 7.0 | 126 | 1.2461 | 0.5015 |
76
+ | 1.1526 | 8.0 | 144 | 1.1999 | 0.5683 |
77
+ | 1.092 | 9.0 | 162 | 1.1166 | 0.5704 |
78
+ | 1.0166 | 10.0 | 180 | 1.0568 | 0.6253 |
79
+ | 0.9753 | 11.0 | 198 | 1.0377 | 0.6055 |
80
+ | 0.939 | 12.0 | 216 | 0.9584 | 0.6535 |
81
+ | 0.916 | 13.0 | 234 | 0.9181 | 0.7092 |
82
+ | 0.8834 | 14.0 | 252 | 0.9164 | 0.7056 |
83
+ | 0.8126 | 15.0 | 270 | 0.9044 | 0.6914 |
84
+ | 0.7936 | 16.0 | 288 | 0.8730 | 0.7387 |
85
+ | 0.805 | 17.0 | 306 | 0.8627 | 0.7222 |
86
+ | 0.7146 | 18.0 | 324 | 0.8602 | 0.7136 |
87
+ | 0.7224 | 19.0 | 342 | 0.9320 | 0.6709 |
88
+ | 0.7335 | 20.0 | 360 | 0.9246 | 0.7081 |
89
+ | 0.6566 | 21.0 | 378 | 0.8585 | 0.7321 |
90
+ | 0.6451 | 22.0 | 396 | 0.8339 | 0.7341 |
91
+ | 0.6864 | 23.0 | 414 | 0.8402 | 0.7305 |
92
+ | 0.6683 | 24.0 | 432 | 0.8399 | 0.7450 |
93
+ | 0.6256 | 25.0 | 450 | 0.8209 | 0.7503 |
94
+ | 0.6041 | 26.0 | 468 | 0.8354 | 0.7461 |
95
+ | 0.6229 | 27.0 | 486 | 0.7940 | 0.7659 |
96
+ | 0.5954 | 28.0 | 504 | 0.8654 | 0.7383 |
97
+ | 0.5866 | 29.0 | 522 | 0.8525 | 0.7321 |
98
+ | 0.5895 | 30.0 | 540 | 0.8314 | 0.7510 |
99
+ | 0.5723 | 31.0 | 558 | 0.8777 | 0.7238 |
100
+ | 0.5319 | 32.0 | 576 | 0.8369 | 0.7498 |
101
+ | 0.5307 | 33.0 | 594 | 0.8801 | 0.7181 |
102
+ | 0.5285 | 34.0 | 612 | 0.8198 | 0.7420 |
103
+ | 0.4851 | 35.0 | 630 | 0.8202 | 0.7379 |
104
+ | 0.4827 | 36.0 | 648 | 0.8372 | 0.7481 |
105
+ | 0.4985 | 37.0 | 666 | 0.8032 | 0.7505 |
106
+ | 0.4714 | 38.0 | 684 | 0.8410 | 0.7390 |
107
+ | 0.4907 | 39.0 | 702 | 0.8401 | 0.7394 |
108
+ | 0.4752 | 40.0 | 720 | 0.8979 | 0.7253 |
109
+ | 0.4604 | 41.0 | 738 | 0.8654 | 0.7276 |
110
+ | 0.4287 | 42.0 | 756 | 0.9682 | 0.7113 |
111
+ | 0.4419 | 43.0 | 774 | 0.8762 | 0.7242 |
112
+ | 0.422 | 44.0 | 792 | 0.8998 | 0.7301 |
113
+ | 0.4432 | 45.0 | 810 | 0.9363 | 0.7024 |
114
+ | 0.4178 | 46.0 | 828 | 0.8751 | 0.7404 |
115
+ | 0.3901 | 47.0 | 846 | 0.8387 | 0.7432 |
116
+ | 0.4066 | 48.0 | 864 | 0.9137 | 0.7184 |
117
+ | 0.3919 | 49.0 | 882 | 0.8873 | 0.7234 |
118
+ | 0.4027 | 50.0 | 900 | 0.8805 | 0.7358 |
119
+ | 0.3593 | 51.0 | 918 | 0.8617 | 0.7332 |
120
+ | 0.3774 | 52.0 | 936 | 0.8781 | 0.7354 |
121
+ | 0.364 | 53.0 | 954 | 0.8993 | 0.7225 |
122
+ | 0.3585 | 54.0 | 972 | 0.9047 | 0.7293 |
123
+ | 0.3539 | 55.0 | 990 | 0.8719 | 0.7462 |
124
+ | 0.3224 | 56.0 | 1008 | 0.8578 | 0.7632 |
125
+ | 0.3486 | 57.0 | 1026 | 0.8934 | 0.7384 |
126
+ | 0.3359 | 58.0 | 1044 | 0.8853 | 0.7428 |
127
+ | 0.288 | 59.0 | 1062 | 0.8655 | 0.7466 |
128
+ | 0.297 | 60.0 | 1080 | 0.8850 | 0.7394 |
129
+ | 0.2875 | 61.0 | 1098 | 0.9405 | 0.7247 |
130
+ | 0.3267 | 62.0 | 1116 | 0.9057 | 0.7222 |
131
+ | 0.2825 | 63.0 | 1134 | 0.9186 | 0.7413 |
132
+ | 0.3129 | 64.0 | 1152 | 0.9200 | 0.7409 |
133
+ | 0.3264 | 65.0 | 1170 | 0.9506 | 0.7404 |
134
+ | 0.3079 | 66.0 | 1188 | 0.9671 | 0.7176 |
135
+ | 0.2915 | 67.0 | 1206 | 0.9504 | 0.7417 |
136
+ | 0.2797 | 68.0 | 1224 | 0.9254 | 0.7424 |
137
+ | 0.2496 | 69.0 | 1242 | 0.8910 | 0.7433 |
138
+ | 0.3063 | 70.0 | 1260 | 0.9178 | 0.7292 |
139
+ | 0.2626 | 71.0 | 1278 | 0.9140 | 0.7415 |
140
+ | 0.2552 | 72.0 | 1296 | 0.9249 | 0.7333 |
141
+ | 0.2655 | 73.0 | 1314 | 0.9000 | 0.7508 |
142
+ | 0.2797 | 74.0 | 1332 | 0.8777 | 0.7400 |
143
+ | 0.2678 | 75.0 | 1350 | 0.9043 | 0.7357 |
144
+ | 0.2464 | 76.0 | 1368 | 0.9432 | 0.7258 |
145
+ | 0.2789 | 77.0 | 1386 | 0.9355 | 0.7356 |
146
+ | 0.2617 | 78.0 | 1404 | 0.9354 | 0.7333 |
147
+ | 0.2381 | 79.0 | 1422 | 0.8852 | 0.7545 |
148
+ | 0.2573 | 80.0 | 1440 | 0.9500 | 0.7384 |
149
+ | 0.2429 | 81.0 | 1458 | 0.9095 | 0.7470 |
150
+ | 0.2513 | 82.0 | 1476 | 0.9898 | 0.7272 |
151
+ | 0.2422 | 83.0 | 1494 | 0.9237 | 0.7487 |
152
+ | 0.2476 | 84.0 | 1512 | 0.9146 | 0.7505 |
153
+ | 0.2399 | 85.0 | 1530 | 0.9386 | 0.7345 |
154
+ | 0.2343 | 86.0 | 1548 | 0.9082 | 0.7414 |
155
+ | 0.2336 | 87.0 | 1566 | 0.9074 | 0.7491 |
156
+ | 0.2176 | 88.0 | 1584 | 0.9291 | 0.7359 |
157
+ | 0.2253 | 89.0 | 1602 | 0.9334 | 0.7331 |
158
+ | 0.2244 | 90.0 | 1620 | 0.9364 | 0.7412 |
159
+ | 0.2215 | 91.0 | 1638 | 0.9617 | 0.7269 |
160
+ | 0.2049 | 92.0 | 1656 | 0.9155 | 0.7562 |
161
+ | 0.2238 | 93.0 | 1674 | 0.9206 | 0.7517 |
162
+ | 0.1761 | 94.0 | 1692 | 0.9312 | 0.7402 |
163
+ | 0.2025 | 95.0 | 1710 | 0.9287 | 0.7444 |
164
+ | 0.214 | 96.0 | 1728 | 0.9215 | 0.7444 |
165
+ | 0.2493 | 97.0 | 1746 | 0.9268 | 0.7489 |
166
+ | 0.2414 | 98.0 | 1764 | 0.9190 | 0.7477 |
167
+ | 0.1971 | 99.0 | 1782 | 0.9221 | 0.7451 |
168
+ | 0.2015 | 100.0 | 1800 | 0.9215 | 0.7424 |
169
+
170
+
171
+ ### Framework versions
172
+
173
+ - Transformers 4.28.0.dev0
174
+ - Pytorch 2.0.0+cu117
175
+ - Datasets 2.19.0
176
+ - Tokenizers 0.12.1