Hugging Face's logo

ERO26
/
FP_Classifcation-V1

Transformers
Safetensors
Generated from Trainer
Model card Files
xet
 Community
ERO26 commited on
Commit
ac52a9d
·
verified ·
1 Parent(s): 4cc2267

Upload fetal planes classification model

Browse files
Files changed (5) hide show
  1. README.md +103 -0
  2. classification_report.txt +12 -0
  3. confusion_matrix.csv +7 -0
  4. model.safetensors +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: FP_Classifcation-V1
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # FP_Classifcation-V1
16
+
17
+ This model was trained from scratch on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2940
20
+ - Accuracy: 0.9026
21
+ - Precision Macro: 0.8742
22
+ - Recall Macro: 0.9098
23
+ - F1 Macro: 0.8895
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 0.001
43
+ - train_batch_size: 4
44
+ - eval_batch_size: 16
45
+ - seed: 42
46
+ - gradient_accumulation_steps: 4
47
+ - total_train_batch_size: 16
48
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - num_epochs: 50
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision Macro | Recall Macro | F1 Macro |
56
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|
57
+ | 1.0869 | 1.0 | 483 | 0.7657 | 0.6792 | 0.6837 | 0.7053 | 0.6710 |
58
+ | 0.9801 | 2.0 | 966 | 0.7458 | 0.7507 | 0.7370 | 0.7004 | 0.7055 |
59
+ | 0.9227 | 3.0 | 1449 | 0.6545 | 0.7143 | 0.7075 | 0.7831 | 0.6999 |
60
+ | 0.7036 | 4.0 | 1932 | 0.5989 | 0.7733 | 0.7476 | 0.8058 | 0.7593 |
61
+ | 0.6729 | 5.0 | 2415 | 0.5175 | 0.7830 | 0.7617 | 0.8409 | 0.7753 |
62
+ | 0.8200 | 6.0 | 2898 | 0.4929 | 0.7863 | 0.7541 | 0.8398 | 0.7735 |
63
+ | 0.7750 | 7.0 | 3381 | 0.4570 | 0.8154 | 0.7830 | 0.8476 | 0.8038 |
64
+ | 0.8015 | 8.0 | 3864 | 0.4494 | 0.8384 | 0.8090 | 0.8493 | 0.8243 |
65
+ | 0.6326 | 9.0 | 4347 | 0.4928 | 0.8263 | 0.8066 | 0.8151 | 0.8039 |
66
+ | 0.7675 | 10.0 | 4830 | 0.4397 | 0.8347 | 0.8021 | 0.8591 | 0.8175 |
67
+ | 0.6092 | 11.0 | 5313 | 0.4220 | 0.8554 | 0.8220 | 0.8603 | 0.8352 |
68
+ | 0.4704 | 12.0 | 5796 | 0.5017 | 0.8489 | 0.8190 | 0.8564 | 0.8321 |
69
+ | 0.6863 | 13.0 | 6279 | 0.4050 | 0.8533 | 0.8123 | 0.8687 | 0.8313 |
70
+ | 0.5217 | 14.0 | 6762 | 0.3839 | 0.8473 | 0.8123 | 0.8753 | 0.8296 |
71
+ | 0.4879 | 15.0 | 7245 | 0.4319 | 0.8687 | 0.8556 | 0.8531 | 0.8527 |
72
+ | 0.5894 | 16.0 | 7728 | 0.4071 | 0.8339 | 0.8098 | 0.8596 | 0.8245 |
73
+ | 0.4710 | 17.0 | 8211 | 0.3890 | 0.8622 | 0.8350 | 0.8626 | 0.8453 |
74
+ | 0.6325 | 18.0 | 8694 | 0.3555 | 0.8768 | 0.8425 | 0.8848 | 0.8589 |
75
+ | 0.6084 | 19.0 | 9177 | 0.3408 | 0.8865 | 0.8524 | 0.8901 | 0.8680 |
76
+ | 0.5211 | 20.0 | 9660 | 0.3399 | 0.8812 | 0.8484 | 0.8828 | 0.8627 |
77
+ | 0.3481 | 21.0 | 10143 | 0.3592 | 0.8905 | 0.8673 | 0.8818 | 0.8733 |
78
+ | 0.6450 | 22.0 | 10626 | 0.3644 | 0.8877 | 0.8632 | 0.8799 | 0.8706 |
79
+ | 0.4031 | 23.0 | 11109 | 0.3248 | 0.8962 | 0.8704 | 0.8944 | 0.8813 |
80
+ | 0.4193 | 24.0 | 11592 | 0.3284 | 0.8836 | 0.8587 | 0.8806 | 0.8677 |
81
+ | 0.4325 | 25.0 | 12075 | 0.3051 | 0.8881 | 0.8622 | 0.8958 | 0.8767 |
82
+ | 0.3674 | 26.0 | 12558 | 0.3227 | 0.8861 | 0.8626 | 0.8839 | 0.8713 |
83
+ | 0.3794 | 27.0 | 13041 | 0.3084 | 0.8982 | 0.8777 | 0.8920 | 0.8844 |
84
+ | 0.3150 | 28.0 | 13524 | 0.3058 | 0.8954 | 0.8680 | 0.8913 | 0.8777 |
85
+ | 0.4406 | 29.0 | 14007 | 0.2965 | 0.8877 | 0.8552 | 0.8943 | 0.8700 |
86
+ | 0.5185 | 30.0 | 14490 | 0.2986 | 0.9018 | 0.8768 | 0.8992 | 0.8868 |
87
+ | 0.5979 | 31.0 | 14973 | 0.3107 | 0.8986 | 0.8741 | 0.8921 | 0.8824 |
88
+ | 0.4205 | 32.0 | 15456 | 0.3153 | 0.9018 | 0.8760 | 0.9054 | 0.8882 |
89
+ | 0.3071 | 33.0 | 15939 | 0.2935 | 0.9010 | 0.8774 | 0.8998 | 0.8873 |
90
+ | 0.2884 | 34.0 | 16422 | 0.2940 | 0.9026 | 0.8742 | 0.9098 | 0.8895 |
91
+ | 0.3953 | 35.0 | 16905 | 0.3187 | 0.8970 | 0.8743 | 0.8911 | 0.8808 |
92
+ | 0.2838 | 36.0 | 17388 | 0.3100 | 0.9059 | 0.8814 | 0.8995 | 0.8896 |
93
+ | 0.3631 | 37.0 | 17871 | 0.3186 | 0.9063 | 0.8841 | 0.9014 | 0.8920 |
94
+ | 0.2681 | 38.0 | 18354 | 0.2929 | 0.9087 | 0.8841 | 0.9093 | 0.8951 |
95
+ | 0.2766 | 39.0 | 18837 | 0.2944 | 0.9022 | 0.8793 | 0.9006 | 0.8890 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 5.17.0
101
+ - Pytorch 2.11.0+cu128
102
+ - Datasets 5.0.1
103
+ - Tokenizers 0.23.1
classification_report.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ precision recall f1-score support
2
+
3
+ Fetal abdomen 0.7842 0.8583 0.8195 127
4
+ Fetal brain 0.9882 0.9862 0.9872 509
5
+ Fetal femur 0.7967 0.8788 0.8357 165
6
+ Fetal thorax 0.8467 0.8889 0.8673 261
7
+ Maternal cervix 0.9880 0.9802 0.9841 253
8
+ Other 0.9354 0.8944 0.9144 890
9
+
10
+ accuracy 0.9215 2205
11
+ macro avg 0.8899 0.9145 0.9014 2205
12
+ weighted avg 0.9240 0.9215 0.9223 2205
confusion_matrix.csv ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ ,Fetal abdomen,Fetal brain,Fetal femur,Fetal thorax,Maternal cervix,Other
2
+ Fetal abdomen,109,1,0,7,1,9
3
+ Fetal brain,0,502,3,1,0,3
4
+ Fetal femur,0,1,145,1,1,17
5
+ Fetal thorax,7,0,0,232,0,22
6
+ Maternal cervix,1,0,0,0,248,4
7
+ Other,22,4,34,33,1,796
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:054ed010ad5e75a87c7518176687f1a6aadea3d4352a364f5aa29a71dbd286a4
3
+ size 33938192
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b854077c9a8e262c563959a0bc489842368608123d05f8b384ae9903288cb362
3
+ size 5265