Hugging Face's logo

egujr001
/
egujr001-swim2-base-model

Image Classification
Transformers
PyTorch
swinv2
Generated from Trainer
Inference Endpoints
Model card Files Community
egujr001 commited on
Commit
2a61a2f
•
1 Parent(s): a9f218d

egujr001/egujr001-AquaAnalyser-model

Browse files
Files changed (10) hide show
  1. README.md +137 -0
  2. all_results.json +13 -0
  3. config.json +54 -0
  4. preprocessor_config.json +23 -0
  5. pytorch_model.bin +3 -0
  6. test_results.json +8 -0
  7. train_results.json +8 -0
  8. trainer_state.json +0 -0
  9. training_args.bin +3 -0
  10. val_results.json +8 -0
README.md ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/swinv2-tiny-patch4-window8-256
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: egujr001-swim2-base-model
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # egujr001-swim2-base-model
17
+
18
+ This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.1969
21
+ - Accuracy: 0.9457
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 64
42
+ - eval_batch_size: 64
43
+ - seed: 56
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - num_epochs: 3
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 0.6254 | 0.04 | 100 | 0.5840 | 0.7050 |
54
+ | 0.3998 | 0.08 | 200 | 0.3525 | 0.8507 |
55
+ | 0.2796 | 0.12 | 300 | 0.2710 | 0.8975 |
56
+ | 0.23 | 0.15 | 400 | 0.2660 | 0.9012 |
57
+ | 0.2372 | 0.19 | 500 | 0.1678 | 0.9401 |
58
+ | 0.1944 | 0.23 | 600 | 0.1437 | 0.9437 |
59
+ | 0.1635 | 0.27 | 700 | 0.1231 | 0.9503 |
60
+ | 0.1463 | 0.31 | 800 | 0.1353 | 0.9551 |
61
+ | 0.1287 | 0.35 | 900 | 0.1216 | 0.9523 |
62
+ | 0.1208 | 0.39 | 1000 | 0.1695 | 0.9351 |
63
+ | 0.1204 | 0.42 | 1100 | 0.1221 | 0.9557 |
64
+ | 0.1064 | 0.46 | 1200 | 0.1605 | 0.9432 |
65
+ | 0.1114 | 0.5 | 1300 | 0.0998 | 0.9613 |
66
+ | 0.1324 | 0.54 | 1400 | 0.0888 | 0.9650 |
67
+ | 0.0997 | 0.58 | 1500 | 0.0810 | 0.9686 |
68
+ | 0.0904 | 0.62 | 1600 | 0.0945 | 0.9655 |
69
+ | 0.0975 | 0.66 | 1700 | 0.0978 | 0.9635 |
70
+ | 0.0859 | 0.69 | 1800 | 0.0858 | 0.9696 |
71
+ | 0.0785 | 0.73 | 1900 | 0.0749 | 0.9722 |
72
+ | 0.0743 | 0.77 | 2000 | 0.0763 | 0.9727 |
73
+ | 0.0815 | 0.81 | 2100 | 0.0765 | 0.9728 |
74
+ | 0.0674 | 0.85 | 2200 | 0.0881 | 0.9703 |
75
+ | 0.0726 | 0.89 | 2300 | 0.0875 | 0.9716 |
76
+ | 0.0633 | 0.93 | 2400 | 0.0912 | 0.9721 |
77
+ | 0.0501 | 0.96 | 2500 | 0.0743 | 0.9750 |
78
+ | 0.0927 | 1.0 | 2600 | 0.0695 | 0.9759 |
79
+ | 0.0766 | 1.04 | 2700 | 0.0788 | 0.9733 |
80
+ | 0.0934 | 1.08 | 2800 | 0.0699 | 0.9753 |
81
+ | 0.0714 | 1.12 | 2900 | 0.0756 | 0.9762 |
82
+ | 0.069 | 1.16 | 3000 | 0.0859 | 0.9706 |
83
+ | 0.0702 | 1.2 | 3100 | 0.1001 | 0.9658 |
84
+ | 0.0633 | 1.23 | 3200 | 0.0724 | 0.9756 |
85
+ | 0.0756 | 1.27 | 3300 | 0.0734 | 0.9745 |
86
+ | 0.0617 | 1.31 | 3400 | 0.0704 | 0.9747 |
87
+ | 0.0498 | 1.35 | 3500 | 0.0651 | 0.9788 |
88
+ | 0.0668 | 1.39 | 3600 | 0.0625 | 0.9791 |
89
+ | 0.0441 | 1.43 | 3700 | 0.0714 | 0.9774 |
90
+ | 0.0789 | 1.46 | 3800 | 0.0880 | 0.9722 |
91
+ | 0.0464 | 1.5 | 3900 | 0.0720 | 0.9749 |
92
+ | 0.0532 | 1.54 | 4000 | 0.0681 | 0.9782 |
93
+ | 0.0677 | 1.58 | 4100 | 0.0733 | 0.9736 |
94
+ | 0.0654 | 1.62 | 4200 | 0.0610 | 0.9802 |
95
+ | 0.0554 | 1.66 | 4300 | 0.0825 | 0.9740 |
96
+ | 0.0836 | 1.7 | 4400 | 0.0694 | 0.9780 |
97
+ | 0.0688 | 1.73 | 4500 | 0.0599 | 0.9813 |
98
+ | 0.052 | 1.77 | 4600 | 0.0932 | 0.9673 |
99
+ | 0.0515 | 1.81 | 4700 | 0.0785 | 0.9759 |
100
+ | 0.0586 | 1.85 | 4800 | 0.0660 | 0.9787 |
101
+ | 0.056 | 1.89 | 4900 | 0.0612 | 0.9783 |
102
+ | 0.037 | 1.93 | 5000 | 0.0645 | 0.9795 |
103
+ | 0.0541 | 1.97 | 5100 | 0.0600 | 0.9809 |
104
+ | 0.0521 | 2.0 | 5200 | 0.0876 | 0.9737 |
105
+ | 0.0352 | 2.04 | 5300 | 0.0709 | 0.9780 |
106
+ | 0.0498 | 2.08 | 5400 | 0.0610 | 0.9809 |
107
+ | 0.0424 | 2.12 | 5500 | 0.0569 | 0.9830 |
108
+ | 0.0532 | 2.16 | 5600 | 0.0625 | 0.9820 |
109
+ | 0.046 | 2.2 | 5700 | 0.0512 | 0.9842 |
110
+ | 0.0453 | 2.24 | 5800 | 0.0608 | 0.9813 |
111
+ | 0.0577 | 2.27 | 5900 | 0.0697 | 0.9811 |
112
+ | 0.0397 | 2.31 | 6000 | 0.0688 | 0.9816 |
113
+ | 0.0494 | 2.35 | 6100 | 0.0534 | 0.9834 |
114
+ | 0.0158 | 2.39 | 6200 | 0.0860 | 0.9774 |
115
+ | 0.0297 | 2.43 | 6300 | 0.0593 | 0.9836 |
116
+ | 0.055 | 2.47 | 6400 | 0.0579 | 0.9821 |
117
+ | 0.0368 | 2.51 | 6500 | 0.0729 | 0.9796 |
118
+ | 0.0754 | 2.54 | 6600 | 0.0601 | 0.9827 |
119
+ | 0.0523 | 2.58 | 6700 | 0.0597 | 0.9824 |
120
+ | 0.0433 | 2.62 | 6800 | 0.0547 | 0.9841 |
121
+ | 0.0164 | 2.66 | 6900 | 0.0620 | 0.9827 |
122
+ | 0.015 | 2.7 | 7000 | 0.0639 | 0.9822 |
123
+ | 0.0415 | 2.74 | 7100 | 0.0576 | 0.9837 |
124
+ | 0.0257 | 2.78 | 7200 | 0.0620 | 0.9820 |
125
+ | 0.0268 | 2.81 | 7300 | 0.0568 | 0.9837 |
126
+ | 0.043 | 2.85 | 7400 | 0.0558 | 0.9836 |
127
+ | 0.0339 | 2.89 | 7500 | 0.0554 | 0.9839 |
128
+ | 0.0263 | 2.93 | 7600 | 0.0552 | 0.9837 |
129
+ | 0.0428 | 2.97 | 7700 | 0.0535 | 0.9842 |
130
+
131
+
132
+ ### Framework versions
133
+
134
+ - Transformers 4.33.0
135
+ - Pytorch 2.0.0+cu117
136
+ - Datasets 2.19.1
137
+ - Tokenizers 0.13.3
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9456576375314159,
4
+ "eval_loss": 0.19686463475227356,
5
+ "eval_runtime": 99.3891,
6
+ "eval_samples_per_second": 180.151,
7
+ "eval_steps_per_second": 2.817,
8
+ "total_flos": 1.6202290803162218e+19,
9
+ "train_loss": 0.0875718877881773,
10
+ "train_runtime": 10188.5801,
11
+ "train_samples_per_second": 48.879,
12
+ "train_steps_per_second": 0.764
13
+ }
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/swinv2-tiny-patch4-window8-256",
3
+ "architectures": [
4
+ "Swinv2ForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "depths": [
8
+ 2,
9
+ 2,
10
+ 6,
11
+ 2
12
+ ],
13
+ "drop_path_rate": 0.1,
14
+ "embed_dim": 96,
15
+ "encoder_stride": 32,
16
+ "hidden_act": "gelu",
17
+ "hidden_dropout_prob": 0.0,
18
+ "hidden_size": 768,
19
+ "id2label": {
20
+ "0": "Fake",
21
+ "1": "Real"
22
+ },
23
+ "image_size": 256,
24
+ "initializer_range": 0.02,
25
+ "label2id": {
26
+ "Fake": "0",
27
+ "Real": "1"
28
+ },
29
+ "layer_norm_eps": 1e-05,
30
+ "mlp_ratio": 4.0,
31
+ "model_type": "swinv2",
32
+ "num_channels": 3,
33
+ "num_heads": [
34
+ 3,
35
+ 6,
36
+ 12,
37
+ 24
38
+ ],
39
+ "num_layers": 4,
40
+ "patch_size": 4,
41
+ "path_norm": true,
42
+ "pretrained_window_sizes": [
43
+ 0,
44
+ 0,
45
+ 0,
46
+ 0
47
+ ],
48
+ "problem_type": "single_label_classification",
49
+ "qkv_bias": true,
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.33.0",
52
+ "use_absolute_embeddings": false,
53
+ "window_size": 8
54
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": false,
4
+ "do_resize": true,
5
+ "feature_extractor_type": "ViTFeatureExtractor",
6
+ "image_mean": [
7
+ 0.485,
8
+ 0.456,
9
+ 0.406
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.229,
14
+ 0.224,
15
+ 0.225
16
+ ],
17
+ "resample": 3,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 256,
21
+ "width": 256
22
+ }
23
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e33eaf22dd690db2fea474241c529eac64d05a5b0895f84302891ed4152c880
3
+ size 110405153
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9456576375314159,
4
+ "eval_loss": 0.19686463475227356,
5
+ "eval_runtime": 99.3891,
6
+ "eval_samples_per_second": 180.151,
7
+ "eval_steps_per_second": 2.817
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9919278080986976,
4
+ "eval_loss": 0.021632272750139236,
5
+ "eval_runtime": 587.4856,
6
+ "eval_samples_per_second": 282.564,
7
+ "eval_steps_per_second": 4.415
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8729d54942960ecd06b9936519e9947be5bd500635de81e5f9cb330e67af4517
3
+ size 4027
val_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9842183540817451,
4
+ "eval_loss": 0.051206715404987335,
5
+ "eval_runtime": 82.4005,
6
+ "eval_samples_per_second": 440.628,
7
+ "eval_steps_per_second": 6.893
8
+ }