Hugging Face's logo

dpaul93
/
face_emotions_image_detection-v2

Image Classification
Transformers
Safetensors
vit
Model card Files
xet
Community
dpaul93 commited on
Commit
86f6b46
·
verified ·
1 Parent(s): e32f7f6

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-2270/config.json +40 -0
  2. checkpoint-2270/model.safetensors +3 -0
  3. checkpoint-2270/optimizer.pt +3 -0
  4. checkpoint-2270/preprocessor_config.json +36 -0
  5. checkpoint-2270/rng_state.pth +3 -0
  6. checkpoint-2270/scheduler.pt +3 -0
  7. checkpoint-2270/trainer_state.json +151 -0
  8. checkpoint-2270/training_args.bin +3 -0
  9. config.json +40 -0
  10. model.safetensors +3 -0
  11. preprocessor_config.json +36 -0
  12. training_args.bin +3 -0
checkpoint-2270/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "Ahegao",
13
+ "1": "Angry",
14
+ "2": "Happy",
15
+ "3": "Neutral",
16
+ "4": "Sad",
17
+ "5": "Surprise"
18
+ },
19
+ "image_size": 224,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "Ahegao": 0,
24
+ "Angry": 1,
25
+ "Happy": 2,
26
+ "Neutral": 3,
27
+ "Sad": 4,
28
+ "Surprise": 5
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "model_type": "vit",
32
+ "num_attention_heads": 12,
33
+ "num_channels": 3,
34
+ "num_hidden_layers": 12,
35
+ "patch_size": 16,
36
+ "problem_type": "single_label_classification",
37
+ "qkv_bias": true,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.41.2"
40
+ }
checkpoint-2270/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e97cc05cfbb702b4b4cd44a8ae058fb562c62af87a221bbd319bc0bd65a614
3
+ size 343236280
checkpoint-2270/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc80e5eceef6a3d135d6ae5df077efaf464c11d8f6a34be6526640737925d48
3
+ size 686593029
checkpoint-2270/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": "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
+ }
checkpoint-2270/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf8e4f218bb754b916a914202b0ee9d7b564a2680e4c9ebb94242c65e46d718
3
+ size 14575
checkpoint-2270/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d6e3930d94bfb10cc89a1681c816fb95e3c684a269bc45891111892ea115d3c
3
+ size 627
checkpoint-2270/trainer_state.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.34681785106658936,
3
+ "best_model_checkpoint": "face_emotions_image_detection/checkpoint-2270",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2270,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.6153129849974134,
14
+ "eval_loss": 0.9683436155319214,
15
+ "eval_runtime": 143.2253,
16
+ "eval_samples_per_second": 67.481,
17
+ "eval_steps_per_second": 2.116,
18
+ "step": 227
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.6957061562338335,
23
+ "eval_loss": 0.7972901463508606,
24
+ "eval_runtime": 139.4154,
25
+ "eval_samples_per_second": 69.325,
26
+ "eval_steps_per_second": 2.173,
27
+ "step": 454
28
+ },
29
+ {
30
+ "epoch": 2.202643171806167,
31
+ "grad_norm": 1.4710227251052856,
32
+ "learning_rate": 0.0007972972972972973,
33
+ "loss": 1.0017,
34
+ "step": 500
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.7072943610967408,
39
+ "eval_loss": 0.7344829440116882,
40
+ "eval_runtime": 139.2714,
41
+ "eval_samples_per_second": 69.397,
42
+ "eval_steps_per_second": 2.176,
43
+ "step": 681
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_accuracy": 0.7410243145369891,
48
+ "eval_loss": 0.6506872773170471,
49
+ "eval_runtime": 139.9422,
50
+ "eval_samples_per_second": 69.064,
51
+ "eval_steps_per_second": 2.165,
52
+ "step": 908
53
+ },
54
+ {
55
+ "epoch": 4.405286343612334,
56
+ "grad_norm": 1.9541560411453247,
57
+ "learning_rate": 0.0005720720720720721,
58
+ "loss": 0.6805,
59
+ "step": 1000
60
+ },
61
+ {
62
+ "epoch": 5.0,
63
+ "eval_accuracy": 0.7446456285566477,
64
+ "eval_loss": 0.6626240015029907,
65
+ "eval_runtime": 139.018,
66
+ "eval_samples_per_second": 69.523,
67
+ "eval_steps_per_second": 2.18,
68
+ "step": 1135
69
+ },
70
+ {
71
+ "epoch": 6.0,
72
+ "eval_accuracy": 0.805587170201759,
73
+ "eval_loss": 0.5180516839027405,
74
+ "eval_runtime": 139.8338,
75
+ "eval_samples_per_second": 69.118,
76
+ "eval_steps_per_second": 2.167,
77
+ "step": 1362
78
+ },
79
+ {
80
+ "epoch": 6.607929515418502,
81
+ "grad_norm": 1.185495138168335,
82
+ "learning_rate": 0.00034684684684684687,
83
+ "loss": 0.5017,
84
+ "step": 1500
85
+ },
86
+ {
87
+ "epoch": 7.0,
88
+ "eval_accuracy": 0.8180031039834454,
89
+ "eval_loss": 0.4816831648349762,
90
+ "eval_runtime": 139.0379,
91
+ "eval_samples_per_second": 69.513,
92
+ "eval_steps_per_second": 2.179,
93
+ "step": 1589
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_accuracy": 0.8548370408691154,
98
+ "eval_loss": 0.3922688961029053,
99
+ "eval_runtime": 138.7104,
100
+ "eval_samples_per_second": 69.678,
101
+ "eval_steps_per_second": 2.184,
102
+ "step": 1816
103
+ },
104
+ {
105
+ "epoch": 8.810572687224669,
106
+ "grad_norm": 0.8604665994644165,
107
+ "learning_rate": 0.00012162162162162163,
108
+ "loss": 0.3511,
109
+ "step": 2000
110
+ },
111
+ {
112
+ "epoch": 9.0,
113
+ "eval_accuracy": 0.8634247284014486,
114
+ "eval_loss": 0.3665013015270233,
115
+ "eval_runtime": 138.5811,
116
+ "eval_samples_per_second": 69.743,
117
+ "eval_steps_per_second": 2.186,
118
+ "step": 2043
119
+ },
120
+ {
121
+ "epoch": 10.0,
122
+ "eval_accuracy": 0.87128815312985,
123
+ "eval_loss": 0.34681785106658936,
124
+ "eval_runtime": 138.7644,
125
+ "eval_samples_per_second": 69.65,
126
+ "eval_steps_per_second": 2.184,
127
+ "step": 2270
128
+ }
129
+ ],
130
+ "logging_steps": 500,
131
+ "max_steps": 2270,
132
+ "num_input_tokens_seen": 0,
133
+ "num_train_epochs": 10,
134
+ "save_steps": 500,
135
+ "stateful_callbacks": {
136
+ "TrainerControl": {
137
+ "args": {
138
+ "should_epoch_stop": false,
139
+ "should_evaluate": false,
140
+ "should_log": false,
141
+ "should_save": true,
142
+ "should_training_stop": true
143
+ },
144
+ "attributes": {}
145
+ }
146
+ },
147
+ "total_flos": 1.123441648207442e+19,
148
+ "train_batch_size": 64,
149
+ "trial_name": null,
150
+ "trial_params": null
151
+ }
checkpoint-2270/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2aca3dddd9fcf25baeecd83f08709ca63ee4302be848be41ce14681eaa8f75f
3
+ size 4603
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "Ahegao",
13
+ "1": "Angry",
14
+ "2": "Happy",
15
+ "3": "Neutral",
16
+ "4": "Sad",
17
+ "5": "Surprise"
18
+ },
19
+ "image_size": 224,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "Ahegao": 0,
24
+ "Angry": 1,
25
+ "Happy": 2,
26
+ "Neutral": 3,
27
+ "Sad": 4,
28
+ "Surprise": 5
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "model_type": "vit",
32
+ "num_attention_heads": 12,
33
+ "num_channels": 3,
34
+ "num_hidden_layers": 12,
35
+ "patch_size": 16,
36
+ "problem_type": "single_label_classification",
37
+ "qkv_bias": true,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.41.2"
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e97cc05cfbb702b4b4cd44a8ae058fb562c62af87a221bbd319bc0bd65a614
3
+ size 343236280
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": "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:d2aca3dddd9fcf25baeecd83f08709ca63ee4302be848be41ce14681eaa8f75f
3
+ size 4603