Hugging Face's logo

LuGot16
/
spermatogenesis-classifier

Image Classification
Transformers
TensorBoard
Safetensors
dinov2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
LuGot16 commited on
Commit
14908ad
·
verified ·
1 Parent(s): 4fe4ac2

DINOv2-base fine-tuned for seminiferous tubule staging

Browse files
Files changed (9) hide show
  1. README.md +109 -0
  2. config.json +63 -0
  3. eval_results.json +14 -0
  4. model.safetensors +3 -0
  5. preprocessor_config.json +27 -0
  6. runs/Apr24_00-33-24_r-lugot16-sandbox-4d31a98d-wsln9re9-a5c05-kj65p/events.out.tfevents.1776990804.r-lugot16-sandbox-4d31a98d-wsln9re9-a5c05-kj65p.1372.0 +3 -0
  7. runs/Apr24_00-35-16_r-lugot16-sandbox-4d31a98d-wsln9re9-a5c05-kj65p/events.out.tfevents.1776990916.r-lugot16-sandbox-4d31a98d-wsln9re9-a5c05-kj65p.1425.0 +3 -0
  8. runs/Apr24_00-35-16_r-lugot16-sandbox-4d31a98d-wsln9re9-a5c05-kj65p/events.out.tfevents.1777002526.r-lugot16-sandbox-4d31a98d-wsln9re9-a5c05-kj65p.1425.1 +3 -0
  9. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: facebook/dinov2-base
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - imagefolder
9
+ metrics:
10
+ - accuracy
11
+ - f1
12
+ model-index:
13
+ - name: spermatogenesis-classifier
14
+ results:
15
+ - task:
16
+ name: Image Classification
17
+ type: image-classification
18
+ dataset:
19
+ name: imagefolder
20
+ type: imagefolder
21
+ config: default
22
+ split: train
23
+ args: default
24
+ metrics:
25
+ - name: Accuracy
26
+ type: accuracy
27
+ value: 0.8910256410256411
28
+ - name: F1
29
+ type: f1
30
+ value: 0.8896300082346593
31
+ ---
32
+
33
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
34
+ should probably proofread and complete it, then remove this comment. -->
35
+
36
+ # spermatogenesis-classifier
37
+
38
+ This model is a fine-tuned version of [facebook/dinov2-base](https://huggingface.co/facebook/dinov2-base) on the imagefolder dataset.
39
+ It achieves the following results on the evaluation set:
40
+ - Loss: 0.3150
41
+ - Accuracy: 0.8910
42
+ - F1: 0.8896
43
+ - Acc I-iv: 0.8710
44
+ - Acc Ix-x: 0.9048
45
+ - Acc V-vi: 0.8511
46
+ - Acc Vii-vii: 0.9714
47
+ - Acc Xi- xii: 0.8636
48
+
49
+ ## Model description
50
+
51
+ More information needed
52
+
53
+ ## Intended uses & limitations
54
+
55
+ More information needed
56
+
57
+ ## Training and evaluation data
58
+
59
+ More information needed
60
+
61
+ ## Training procedure
62
+
63
+ ### Training hyperparameters
64
+
65
+ The following hyperparameters were used during training:
66
+ - learning_rate: 2e-05
67
+ - train_batch_size: 16
68
+ - eval_batch_size: 16
69
+ - seed: 42
70
+ - gradient_accumulation_steps: 2
71
+ - total_train_batch_size: 32
72
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
73
+ - lr_scheduler_type: cosine
74
+ - lr_scheduler_warmup_steps: 50
75
+ - num_epochs: 30
76
+ - mixed_precision_training: Native AMP
77
+
78
+ ### Training results
79
+
80
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Acc I-iv | Acc Ix-x | Acc V-vi | Acc Vii-vii | Acc Xi- xii |
81
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:--------:|:--------:|:-----------:|:-----------:|
82
+ | 2.7787 | 1.0 | 20 | 1.2571 | 0.4295 | 0.3860 | 0.0 | 0.4762 | 0.5532 | 0.3143 | 0.9091 |
83
+ | 1.6595 | 2.0 | 40 | 1.5081 | 0.3590 | 0.3372 | 0.0323 | 0.5238 | 0.0426 | 0.5714 | 1.0 |
84
+ | 1.5573 | 3.0 | 60 | 0.8242 | 0.5513 | 0.5636 | 0.3871 | 0.5238 | 0.3830 | 0.6571 | 1.0 |
85
+ | 1.2868 | 4.0 | 80 | 0.7303 | 0.7885 | 0.7570 | 0.5484 | 0.4762 | 0.8723 | 0.9429 | 1.0 |
86
+ | 0.9034 | 5.0 | 100 | 0.4915 | 0.8077 | 0.8036 | 0.7097 | 0.8095 | 0.7660 | 0.8857 | 0.9091 |
87
+ | 1.2132 | 6.0 | 120 | 0.5243 | 0.8013 | 0.7923 | 0.6452 | 0.8095 | 0.9574 | 0.6571 | 0.9091 |
88
+ | 0.8576 | 7.0 | 140 | 0.7115 | 0.7692 | 0.7224 | 0.5806 | 0.2857 | 0.8298 | 1.0 | 1.0 |
89
+ | 0.8557 | 8.0 | 160 | 0.5277 | 0.7692 | 0.7716 | 0.8710 | 0.6667 | 0.5106 | 1.0 | 0.9091 |
90
+ | 0.7294 | 9.0 | 180 | 0.4170 | 0.8333 | 0.8306 | 0.6129 | 0.9048 | 0.8511 | 0.9143 | 0.9091 |
91
+ | 0.6713 | 10.0 | 200 | 0.4585 | 0.8141 | 0.8070 | 0.9032 | 0.9048 | 0.7234 | 0.8571 | 0.7273 |
92
+ | 0.7973 | 11.0 | 220 | 0.4767 | 0.8397 | 0.8241 | 0.7097 | 0.6667 | 0.8936 | 0.8857 | 1.0 |
93
+ | 0.6637 | 12.0 | 240 | 0.4327 | 0.8013 | 0.8057 | 0.9032 | 0.7619 | 0.6170 | 0.9143 | 0.9091 |
94
+ | 0.6284 | 13.0 | 260 | 0.3897 | 0.8462 | 0.8331 | 0.5484 | 0.8571 | 0.9149 | 1.0 | 0.8636 |
95
+ | 0.7981 | 14.0 | 280 | 0.3915 | 0.8654 | 0.8512 | 0.6774 | 0.9524 | 0.9362 | 0.9429 | 0.7727 |
96
+ | 0.5017 | 15.0 | 300 | 0.3150 | 0.8910 | 0.8896 | 0.8710 | 0.9048 | 0.8511 | 0.9714 | 0.8636 |
97
+ | 0.5893 | 16.0 | 320 | 0.3640 | 0.8526 | 0.8485 | 0.8065 | 0.9048 | 0.8298 | 0.9429 | 0.7727 |
98
+ | 0.6591 | 17.0 | 340 | 0.3563 | 0.8718 | 0.8684 | 0.7742 | 0.8571 | 0.8723 | 0.9429 | 0.9091 |
99
+ | 0.4976 | 18.0 | 360 | 0.3648 | 0.8397 | 0.8393 | 0.9355 | 0.8095 | 0.7447 | 0.8857 | 0.8636 |
100
+ | 0.5034 | 19.0 | 380 | 0.3839 | 0.8462 | 0.8389 | 0.6452 | 0.7619 | 0.9149 | 0.9429 | 0.9091 |
101
+ | 0.4612 | 20.0 | 400 | 0.3724 | 0.8654 | 0.8636 | 0.9032 | 0.8571 | 0.8723 | 0.8286 | 0.8636 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - Transformers 5.6.2
107
+ - Pytorch 2.11.0+cu130
108
+ - Datasets 4.8.4
109
+ - Tokenizers 0.22.2
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_layernorm": true,
3
+ "architectures": [
4
+ "Dinov2ForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "drop_path_rate": 0.0,
8
+ "dtype": "float32",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.0,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "I-IV",
14
+ "1": "IX-X",
15
+ "2": "V-VI",
16
+ "3": "VII-VII",
17
+ "4": "XI- XII"
18
+ },
19
+ "image_size": 518,
20
+ "initializer_range": 0.02,
21
+ "label2id": {
22
+ "I-IV": 0,
23
+ "IX-X": 1,
24
+ "V-VI": 2,
25
+ "VII-VII": 3,
26
+ "XI- XII": 4
27
+ },
28
+ "layer_norm_eps": 1e-06,
29
+ "layerscale_value": 1.0,
30
+ "mlp_ratio": 4,
31
+ "model_type": "dinov2",
32
+ "num_attention_heads": 12,
33
+ "num_channels": 3,
34
+ "num_hidden_layers": 12,
35
+ "out_features": [
36
+ "stage12"
37
+ ],
38
+ "out_indices": [
39
+ 12
40
+ ],
41
+ "patch_size": 14,
42
+ "qkv_bias": true,
43
+ "reshape_hidden_states": true,
44
+ "stage_names": [
45
+ "stem",
46
+ "stage1",
47
+ "stage2",
48
+ "stage3",
49
+ "stage4",
50
+ "stage5",
51
+ "stage6",
52
+ "stage7",
53
+ "stage8",
54
+ "stage9",
55
+ "stage10",
56
+ "stage11",
57
+ "stage12"
58
+ ],
59
+ "transformers_version": "5.6.2",
60
+ "use_cache": false,
61
+ "use_mask_token": true,
62
+ "use_swiglu_ffn": false
63
+ }
eval_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_loss": 0.3150061070919037,
3
+ "eval_accuracy": 0.8910256410256411,
4
+ "eval_f1": 0.8896300082346593,
5
+ "eval_acc_I-IV": 0.8709677419354839,
6
+ "eval_acc_IX-X": 0.9047619047619048,
7
+ "eval_acc_V-VI": 0.851063829787234,
8
+ "eval_acc_VII-VII": 0.9714285714285714,
9
+ "eval_acc_XI- XII": 0.8636363636363636,
10
+ "eval_runtime": 47.9961,
11
+ "eval_samples_per_second": 3.25,
12
+ "eval_steps_per_second": 0.208,
13
+ "epoch": 20.0
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea41e8e0e5cc0df97a671da10cf0d93af39ec310397f0aa5f923ebbcda5bf47
3
+ size 346378372
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.485,
13
+ 0.456,
14
+ 0.406
15
+ ],
16
+ "image_processor_type": "BitImageProcessor",
17
+ "image_std": [
18
+ 0.229,
19
+ 0.224,
20
+ 0.225
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 256
26
+ }
27
+ }
runs/Apr24_00-33-24_r-lugot16-sandbox-4d31a98d-wsln9re9-a5c05-kj65p/events.out.tfevents.1776990804.r-lugot16-sandbox-4d31a98d-wsln9re9-a5c05-kj65p.1372.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02c11348ccc221801a5a688b8c99d6297fca9607ee1e83f3434a5579f4282d8b
3
+ size 4900
runs/Apr24_00-35-16_r-lugot16-sandbox-4d31a98d-wsln9re9-a5c05-kj65p/events.out.tfevents.1776990916.r-lugot16-sandbox-4d31a98d-wsln9re9-a5c05-kj65p.1425.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37c776cb6630bbe2572072eb0a53056cf64027b41d39494db569c8b7d7ced712
3
+ size 26481
runs/Apr24_00-35-16_r-lugot16-sandbox-4d31a98d-wsln9re9-a5c05-kj65p/events.out.tfevents.1777002526.r-lugot16-sandbox-4d31a98d-wsln9re9-a5c05-kj65p.1425.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2edfefd3ba8f0effa2faa9a5e409e8f6f996771fe9c30c2edecf19f288bb5498
3
+ size 723
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac4de32838f02787c991dce069e7b299f4861e39990d5e0e700b4d329ecbde2
3
+ size 5905