Hugging Face's logo

luciagil
/
Human_action_classifier

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
luciagil commited on
Commit
1e43038
•
1 Parent(s): a8d1ceb

Model save

Browse files
Files changed (6) hide show
  1. README.md +104 -0
  2. config.json +58 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +36 -0
  5. runs/Apr05_17-06-15_44569c9ac571/events.out.tfevents.1712336799.44569c9ac571.8281.0 +3 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224-in21K
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: Human_action_classifier
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
+ # Human_action_classifier
17
+
18
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21K](https://huggingface.co/google/vit-base-patch16-224-in21K) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.5316
21
+ - Accuracy: 0.8492
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: 0.0002
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 7
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 1.4545 | 0.16 | 100 | 1.3145 | 0.6706 |
54
+ | 1.2568 | 0.32 | 200 | 1.0387 | 0.7179 |
55
+ | 1.3145 | 0.48 | 300 | 1.0027 | 0.7135 |
56
+ | 1.0866 | 0.63 | 400 | 0.8883 | 0.7377 |
57
+ | 1.0036 | 0.79 | 500 | 0.8973 | 0.7321 |
58
+ | 1.1811 | 0.95 | 600 | 0.8048 | 0.7571 |
59
+ | 0.9242 | 1.11 | 700 | 0.9095 | 0.7274 |
60
+ | 0.9477 | 1.27 | 800 | 0.8037 | 0.7619 |
61
+ | 0.8634 | 1.43 | 900 | 0.7938 | 0.7643 |
62
+ | 1.0098 | 1.59 | 1000 | 0.7328 | 0.7766 |
63
+ | 0.8176 | 1.75 | 1100 | 0.8065 | 0.7516 |
64
+ | 0.8072 | 1.9 | 1200 | 0.7768 | 0.7694 |
65
+ | 0.7739 | 2.06 | 1300 | 0.7624 | 0.7726 |
66
+ | 0.6851 | 2.22 | 1400 | 0.6687 | 0.7940 |
67
+ | 0.7496 | 2.38 | 1500 | 0.6806 | 0.7948 |
68
+ | 0.7352 | 2.54 | 1600 | 0.6943 | 0.7897 |
69
+ | 0.7311 | 2.7 | 1700 | 0.7353 | 0.7714 |
70
+ | 0.7181 | 2.86 | 1800 | 0.6831 | 0.7921 |
71
+ | 0.5986 | 3.02 | 1900 | 0.6930 | 0.7897 |
72
+ | 0.5716 | 3.17 | 2000 | 0.6685 | 0.8048 |
73
+ | 0.5218 | 3.33 | 2100 | 0.7152 | 0.7917 |
74
+ | 0.8469 | 3.49 | 2200 | 0.6405 | 0.8020 |
75
+ | 0.5783 | 3.65 | 2300 | 0.6728 | 0.7956 |
76
+ | 0.7202 | 3.81 | 2400 | 0.6007 | 0.8155 |
77
+ | 0.5525 | 3.97 | 2500 | 0.6559 | 0.8056 |
78
+ | 0.519 | 4.13 | 2600 | 0.5868 | 0.8222 |
79
+ | 0.6171 | 4.29 | 2700 | 0.6157 | 0.8103 |
80
+ | 0.5401 | 4.44 | 2800 | 0.6120 | 0.8083 |
81
+ | 0.6105 | 4.6 | 2900 | 0.5619 | 0.8325 |
82
+ | 0.7497 | 4.76 | 3000 | 0.5859 | 0.8302 |
83
+ | 0.4856 | 4.92 | 3100 | 0.5833 | 0.8262 |
84
+ | 0.4959 | 5.08 | 3200 | 0.5704 | 0.8329 |
85
+ | 0.4413 | 5.24 | 3300 | 0.6217 | 0.8190 |
86
+ | 0.4513 | 5.4 | 3400 | 0.5750 | 0.8294 |
87
+ | 0.3987 | 5.56 | 3500 | 0.5826 | 0.8341 |
88
+ | 0.4395 | 5.71 | 3600 | 0.5754 | 0.8385 |
89
+ | 0.4669 | 5.87 | 3700 | 0.5653 | 0.8357 |
90
+ | 0.4005 | 6.03 | 3800 | 0.5424 | 0.8377 |
91
+ | 0.4457 | 6.19 | 3900 | 0.5620 | 0.8393 |
92
+ | 0.3693 | 6.35 | 4000 | 0.5411 | 0.8413 |
93
+ | 0.2933 | 6.51 | 4100 | 0.5325 | 0.8484 |
94
+ | 0.2603 | 6.67 | 4200 | 0.5360 | 0.8476 |
95
+ | 0.3364 | 6.83 | 4300 | 0.5303 | 0.8496 |
96
+ | 0.3639 | 6.98 | 4400 | 0.5316 | 0.8492 |
97
+
98
+
99
+ ### Framework versions
100
+
101
+ - Transformers 4.39.3
102
+ - Pytorch 2.2.1+cu121
103
+ - Datasets 2.18.0
104
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21K",
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": "texting",
13
+ "1": "sleeping",
14
+ "2": "hugging",
15
+ "3": "laughing",
16
+ "4": "using_laptop",
17
+ "5": "cycling",
18
+ "6": "clapping",
19
+ "7": "calling",
20
+ "8": "listening_to_music",
21
+ "9": "drinking",
22
+ "10": "dancing",
23
+ "11": "eating",
24
+ "12": "sitting",
25
+ "13": "running",
26
+ "14": "fighting"
27
+ },
28
+ "image_size": 224,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 3072,
31
+ "label2id": {
32
+ "calling": 7,
33
+ "clapping": 6,
34
+ "cycling": 5,
35
+ "dancing": 10,
36
+ "drinking": 9,
37
+ "eating": 11,
38
+ "fighting": 14,
39
+ "hugging": 2,
40
+ "laughing": 3,
41
+ "listening_to_music": 8,
42
+ "running": 13,
43
+ "sitting": 12,
44
+ "sleeping": 1,
45
+ "texting": 0,
46
+ "using_laptop": 4
47
+ },
48
+ "layer_norm_eps": 1e-12,
49
+ "model_type": "vit",
50
+ "num_attention_heads": 12,
51
+ "num_channels": 3,
52
+ "num_hidden_layers": 12,
53
+ "patch_size": 16,
54
+ "problem_type": "single_label_classification",
55
+ "qkv_bias": true,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.39.3"
58
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7d365e8fc43b6d4bbcb563cfcfe770262570a649d0e1b591a3cc91047d7503
3
+ size 343263964
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": true,
18
+ "do_resize": true,
19
+ "image_mean": [
20
+ 0.5,
21
+ 0.5,
22
+ 0.5
23
+ ],
24
+ "image_processor_type": "ViTFeatureExtractor",
25
+ "image_std": [
26
+ 0.5,
27
+ 0.5,
28
+ 0.5
29
+ ],
30
+ "resample": 2,
31
+ "rescale_factor": 0.00392156862745098,
32
+ "size": [
33
+ 224,
34
+ 224
35
+ ]
36
+ }
runs/Apr05_17-06-15_44569c9ac571/events.out.tfevents.1712336799.44569c9ac571.8281.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e762223def4cd50f5a8e8f31a7c157b8d29e76908204988b952cacbc861d70
3
+ size 112705
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55b5495202183733cdbca42ec085f00d0b183a38dd23595cfb3423b5eda4a917
3
+ size 4920