Hugging Face's logo

peter881122
/
road_vit_Model

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Community
peter881122 commited on
Commit
11b0cf0
•
1 Parent(s): 0313e3c

Training in progress, step 500

Browse files
Files changed (5) hide show
  1. README.md +125 -0
  2. config.json +32 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +36 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/convnext-tiny-224
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: swinModel
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
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/huangyangyu/huggingface/runs/mqnke3pt)
17
+ # swinModel
18
+
19
+ This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.4645
22
+ - Accuracy: 0.7823
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
+ - train_batch_size: 64
43
+ - eval_batch_size: 64
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 15
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
53
+ | 0.5524 | 0.2278 | 100 | 0.3380 | 0.9845 |
54
+ | 0.4727 | 0.4556 | 200 | 0.3134 | 0.9439 |
55
+ | 0.3821 | 0.6834 | 300 | 0.3179 | 0.8939 |
56
+ | 0.2765 | 0.9112 | 400 | 0.3308 | 0.8603 |
57
+ | 0.1905 | 1.1390 | 500 | 0.4489 | 0.8069 |
58
+ | 0.1258 | 1.3667 | 600 | 0.5830 | 0.7731 |
59
+ | 0.0846 | 1.5945 | 700 | 0.4515 | 0.8439 |
60
+ | 0.064 | 1.8223 | 800 | 0.5274 | 0.8248 |
61
+ | 0.0494 | 2.0501 | 900 | 0.6575 | 0.7969 |
62
+ | 0.0378 | 2.2779 | 1000 | 0.6267 | 0.8261 |
63
+ | 0.0284 | 2.5057 | 1100 | 0.8875 | 0.7677 |
64
+ | 0.023 | 2.7335 | 1200 | 1.0218 | 0.7502 |
65
+ | 0.0225 | 2.9613 | 1300 | 0.8597 | 0.7930 |
66
+ | 0.0158 | 3.1891 | 1400 | 0.9559 | 0.7875 |
67
+ | 0.0134 | 3.4169 | 1500 | 0.7133 | 0.8378 |
68
+ | 0.0146 | 3.6446 | 1600 | 0.8297 | 0.8159 |
69
+ | 0.0116 | 3.8724 | 1700 | 0.9716 | 0.7930 |
70
+ | 0.0099 | 4.1002 | 1800 | 0.8118 | 0.8289 |
71
+ | 0.009 | 4.3280 | 1900 | 0.8361 | 0.8305 |
72
+ | 0.0059 | 4.5558 | 2000 | 0.9536 | 0.8127 |
73
+ | 0.009 | 4.7836 | 2100 | 1.0436 | 0.8003 |
74
+ | 0.0107 | 5.0114 | 2200 | 1.0988 | 0.7929 |
75
+ | 0.0077 | 5.2392 | 2300 | 0.9100 | 0.8344 |
76
+ | 0.007 | 5.4670 | 2400 | 0.9920 | 0.8186 |
77
+ | 0.0037 | 5.6948 | 2500 | 1.0256 | 0.8130 |
78
+ | 0.0073 | 5.9226 | 2600 | 1.5456 | 0.7387 |
79
+ | 0.0055 | 6.1503 | 2700 | 1.2020 | 0.7793 |
80
+ | 0.0039 | 6.3781 | 2800 | 1.1095 | 0.8048 |
81
+ | 0.0022 | 6.6059 | 2900 | 1.2638 | 0.7887 |
82
+ | 0.0042 | 6.8337 | 3000 | 1.0389 | 0.8263 |
83
+ | 0.005 | 7.0615 | 3100 | 1.3570 | 0.7763 |
84
+ | 0.0017 | 7.2893 | 3200 | 1.6866 | 0.7303 |
85
+ | 0.0024 | 7.5171 | 3300 | 1.4244 | 0.7679 |
86
+ | 0.0036 | 7.7449 | 3400 | 1.4379 | 0.7609 |
87
+ | 0.0032 | 7.9727 | 3500 | 1.1855 | 0.8006 |
88
+ | 0.0016 | 8.2005 | 3600 | 1.1089 | 0.8163 |
89
+ | 0.0023 | 8.4282 | 3700 | 0.9546 | 0.8441 |
90
+ | 0.0022 | 8.6560 | 3800 | 1.0083 | 0.8378 |
91
+ | 0.002 | 8.8838 | 3900 | 1.6526 | 0.7368 |
92
+ | 0.0032 | 9.1116 | 4000 | 1.5307 | 0.7619 |
93
+ | 0.0008 | 9.3394 | 4100 | 1.1384 | 0.8191 |
94
+ | 0.002 | 9.5672 | 4200 | 1.2104 | 0.8063 |
95
+ | 0.0031 | 9.7950 | 4300 | 1.5793 | 0.7564 |
96
+ | 0.0024 | 10.0228 | 4400 | 1.3544 | 0.7857 |
97
+ | 0.0035 | 10.2506 | 4500 | 1.5046 | 0.7667 |
98
+ | 0.0009 | 10.4784 | 4600 | 1.8010 | 0.7306 |
99
+ | 0.0007 | 10.7062 | 4700 | 1.2062 | 0.8115 |
100
+ | 0.0025 | 10.9339 | 4800 | 1.2110 | 0.8127 |
101
+ | 0.0016 | 11.1617 | 4900 | 1.3772 | 0.7875 |
102
+ | 0.001 | 11.3895 | 5000 | 1.3586 | 0.7947 |
103
+ | 0.0024 | 11.6173 | 5100 | 1.2359 | 0.8094 |
104
+ | 0.0012 | 11.8451 | 5200 | 0.8793 | 0.8679 |
105
+ | 0.0011 | 12.0729 | 5300 | 1.5563 | 0.7648 |
106
+ | 0.0021 | 12.3007 | 5400 | 1.3154 | 0.8003 |
107
+ | 0.0018 | 12.5285 | 5500 | 1.2115 | 0.8168 |
108
+ | 0.001 | 12.7563 | 5600 | 1.4905 | 0.7773 |
109
+ | 0.0012 | 12.9841 | 5700 | 1.4290 | 0.7868 |
110
+ | 0.0022 | 13.2118 | 5800 | 1.1928 | 0.8214 |
111
+ | 0.0023 | 13.4396 | 5900 | 1.2761 | 0.8077 |
112
+ | 0.0014 | 13.6674 | 6000 | 1.1804 | 0.8211 |
113
+ | 0.0021 | 13.8952 | 6100 | 1.3523 | 0.7965 |
114
+ | 0.0007 | 14.1230 | 6200 | 1.2330 | 0.8128 |
115
+ | 0.0008 | 14.3508 | 6300 | 1.3563 | 0.7955 |
116
+ | 0.0004 | 14.5786 | 6400 | 1.3969 | 0.7903 |
117
+ | 0.0011 | 14.8064 | 6500 | 1.4645 | 0.7823 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.42.0.dev0
123
+ - Pytorch 2.1.1
124
+ - Datasets 2.19.2
125
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "0",
13
+ "1": "1"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "0": 0,
20
+ "1": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "model_type": "vit",
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "problem_type": "single_label_classification",
29
+ "qkv_bias": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.42.0.dev0"
32
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8997051e9693c02c72f5c079e27f87054db641b2640a3e8d400642caf1890130
3
+ size 343223968
preprocessor_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_rescale",
8
+ "rescale_factor",
9
+ "do_normalize",
10
+ "image_mean",
11
+ "image_std",
12
+ "return_tensors",
13
+ "data_format",
14
+ "input_data_format"
15
+ ],
16
+ "do_normalize": true,
17
+ "do_rescale": false,
18
+ "do_resize": true,
19
+ "image_mean": [
20
+ 0.5,
21
+ 0.5,
22
+ 0.5
23
+ ],
24
+ "image_processor_type": "ViTImageProcessor",
25
+ "image_std": [
26
+ 0.5,
27
+ 0.5,
28
+ 0.5
29
+ ],
30
+ "resample": 2,
31
+ "rescale_factor": 0.00392156862745098,
32
+ "size": {
33
+ "height": 224,
34
+ "width": 224
35
+ }
36
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e8a0ed7b253497dceb1d74682fbee109d236199aff2afd1102879d56d6a0b77
3
+ size 5112