Hugging Face's logo

adhityamw11
/
facial_emotions_image_detection_rafdb_microsoft_vit

Image Classification
Transformers
Safetensors
swin
Inference Endpoints
Model card Files Community
adhityamw11 commited on
Commit
c65d2b7
•
1 Parent(s): 387b1f1

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-5016/config.json +71 -0
  2. checkpoint-5016/model.safetensors +3 -0
  3. checkpoint-5016/optimizer.pt +3 -0
  4. checkpoint-5016/preprocessor_config.json +36 -0
  5. checkpoint-5016/rng_state.pth +3 -0
  6. checkpoint-5016/scheduler.pt +3 -0
  7. checkpoint-5016/trainer_state.json +163 -0
  8. checkpoint-5016/training_args.bin +3 -0
  9. config.json +71 -0
  10. model.safetensors +3 -0
  11. preprocessor_config.json +36 -0
  12. training_args.bin +3 -0
checkpoint-5016/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
3
+ "architectures": [
4
+ "SwinForImageClassification"
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": "disguist",
21
+ "1": "anger",
22
+ "2": "fear",
23
+ "3": "happy",
24
+ "4": "surprise",
25
+ "5": "neutral",
26
+ "6": "sad"
27
+ },
28
+ "image_size": 224,
29
+ "initializer_range": 0.02,
30
+ "label2id": {
31
+ "anger": 1,
32
+ "disguist": 0,
33
+ "fear": 2,
34
+ "happy": 3,
35
+ "neutral": 5,
36
+ "sad": 6,
37
+ "surprise": 4
38
+ },
39
+ "layer_norm_eps": 1e-05,
40
+ "mlp_ratio": 4.0,
41
+ "model_type": "swin",
42
+ "num_channels": 3,
43
+ "num_heads": [
44
+ 3,
45
+ 6,
46
+ 12,
47
+ 24
48
+ ],
49
+ "num_layers": 4,
50
+ "out_features": [
51
+ "stage4"
52
+ ],
53
+ "out_indices": [
54
+ 4
55
+ ],
56
+ "patch_size": 4,
57
+ "path_norm": true,
58
+ "problem_type": "single_label_classification",
59
+ "qkv_bias": true,
60
+ "stage_names": [
61
+ "stem",
62
+ "stage1",
63
+ "stage2",
64
+ "stage3",
65
+ "stage4"
66
+ ],
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.39.3",
69
+ "use_absolute_embeddings": false,
70
+ "window_size": 7
71
+ }
checkpoint-5016/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d505a5f4380041d56c6d4fcaddd1f62d3cfcd67336d931a4a3873d3d268e0f
3
+ size 110358212
checkpoint-5016/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43f784adc789c67247e8240ac3849c529c0f01da1e6b438908d4d897fe75d40c
3
+ size 220381306
checkpoint-5016/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
+ 0.485,
21
+ 0.456,
22
+ 0.406
23
+ ],
24
+ "image_processor_type": "ViTImageProcessor",
25
+ "image_std": [
26
+ 0.229,
27
+ 0.224,
28
+ 0.225
29
+ ],
30
+ "resample": 3,
31
+ "rescale_factor": 0.00392156862745098,
32
+ "size": {
33
+ "height": 224,
34
+ "width": 224
35
+ }
36
+ }
checkpoint-5016/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030da0584d20e315f9aa67c926f3107b40ec72399c8ba93b8f27e3c730a7397
3
+ size 14244
checkpoint-5016/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:812e50465a81e654ea13d4deb90969f0d8aa1e1b5ed3e9c3ad08b39d9b48da64
3
+ size 1064
checkpoint-5016/trainer_state.json ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9192785620689392,
3
+ "best_model_checkpoint": "facial_emotions_image_detection_rafdb_microsoft_vit/checkpoint-5016",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5016,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.8,
13
+ "grad_norm": 14.677521705627441,
14
+ "learning_rate": 2.7281514297221103e-06,
15
+ "loss": 1.7706,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.45075587486903157,
21
+ "eval_loss": 1.4894078969955444,
22
+ "eval_runtime": 69.9167,
23
+ "eval_samples_per_second": 191.113,
24
+ "eval_steps_per_second": 11.957,
25
+ "step": 627
26
+ },
27
+ {
28
+ "epoch": 1.59,
29
+ "grad_norm": 17.35078239440918,
30
+ "learning_rate": 2.4260974627466776e-06,
31
+ "loss": 1.4285,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.5424337674000899,
37
+ "eval_loss": 1.2471543550491333,
38
+ "eval_runtime": 65.1157,
39
+ "eval_samples_per_second": 205.204,
40
+ "eval_steps_per_second": 12.839,
41
+ "step": 1254
42
+ },
43
+ {
44
+ "epoch": 2.39,
45
+ "grad_norm": 15.841980934143066,
46
+ "learning_rate": 2.1240434957712445e-06,
47
+ "loss": 1.2563,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.5873372249663225,
53
+ "eval_loss": 1.1151762008666992,
54
+ "eval_runtime": 65.1132,
55
+ "eval_samples_per_second": 205.212,
56
+ "eval_steps_per_second": 12.839,
57
+ "step": 1881
58
+ },
59
+ {
60
+ "epoch": 3.19,
61
+ "grad_norm": 24.84258270263672,
62
+ "learning_rate": 1.8219895287958114e-06,
63
+ "loss": 1.1575,
64
+ "step": 2000
65
+ },
66
+ {
67
+ "epoch": 3.99,
68
+ "grad_norm": 14.571057319641113,
69
+ "learning_rate": 1.5199355618203787e-06,
70
+ "loss": 1.0741,
71
+ "step": 2500
72
+ },
73
+ {
74
+ "epoch": 4.0,
75
+ "eval_accuracy": 0.6200419098937285,
76
+ "eval_loss": 1.0384080410003662,
77
+ "eval_runtime": 65.4313,
78
+ "eval_samples_per_second": 204.214,
79
+ "eval_steps_per_second": 12.777,
80
+ "step": 2508
81
+ },
82
+ {
83
+ "epoch": 4.78,
84
+ "grad_norm": 19.834932327270508,
85
+ "learning_rate": 1.2178815948449456e-06,
86
+ "loss": 1.0238,
87
+ "step": 3000
88
+ },
89
+ {
90
+ "epoch": 5.0,
91
+ "eval_accuracy": 0.6430923514443946,
92
+ "eval_loss": 0.981325626373291,
93
+ "eval_runtime": 66.0473,
94
+ "eval_samples_per_second": 202.31,
95
+ "eval_steps_per_second": 12.658,
96
+ "step": 3135
97
+ },
98
+ {
99
+ "epoch": 5.58,
100
+ "grad_norm": 17.73134994506836,
101
+ "learning_rate": 9.158276278695127e-07,
102
+ "loss": 0.9837,
103
+ "step": 3500
104
+ },
105
+ {
106
+ "epoch": 6.0,
107
+ "eval_accuracy": 0.6525969166292471,
108
+ "eval_loss": 0.9464946985244751,
109
+ "eval_runtime": 66.383,
110
+ "eval_samples_per_second": 201.286,
111
+ "eval_steps_per_second": 12.594,
112
+ "step": 3762
113
+ },
114
+ {
115
+ "epoch": 6.38,
116
+ "grad_norm": 14.271998405456543,
117
+ "learning_rate": 6.137736608940798e-07,
118
+ "loss": 0.9694,
119
+ "step": 4000
120
+ },
121
+ {
122
+ "epoch": 7.0,
123
+ "eval_accuracy": 0.6600059871276756,
124
+ "eval_loss": 0.9257609248161316,
125
+ "eval_runtime": 66.6168,
126
+ "eval_samples_per_second": 200.58,
127
+ "eval_steps_per_second": 12.549,
128
+ "step": 4389
129
+ },
130
+ {
131
+ "epoch": 7.18,
132
+ "grad_norm": 26.607189178466797,
133
+ "learning_rate": 3.117196939186468e-07,
134
+ "loss": 0.9391,
135
+ "step": 4500
136
+ },
137
+ {
138
+ "epoch": 7.97,
139
+ "grad_norm": 20.43568992614746,
140
+ "learning_rate": 9.665726943213855e-09,
141
+ "loss": 0.9235,
142
+ "step": 5000
143
+ },
144
+ {
145
+ "epoch": 8.0,
146
+ "eval_accuracy": 0.663897620116749,
147
+ "eval_loss": 0.9192785620689392,
148
+ "eval_runtime": 64.6255,
149
+ "eval_samples_per_second": 206.761,
150
+ "eval_steps_per_second": 12.936,
151
+ "step": 5016
152
+ }
153
+ ],
154
+ "logging_steps": 500,
155
+ "max_steps": 5016,
156
+ "num_input_tokens_seen": 0,
157
+ "num_train_epochs": 8,
158
+ "save_steps": 500,
159
+ "total_flos": 3.98586664581061e+18,
160
+ "train_batch_size": 32,
161
+ "trial_name": null,
162
+ "trial_params": null
163
+ }
checkpoint-5016/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3c326863034444401f26b03268d3083d5e78e526dc54fb1460c0bef3abad88b
3
+ size 4920
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
3
+ "architectures": [
4
+ "SwinForImageClassification"
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": "disguist",
21
+ "1": "anger",
22
+ "2": "fear",
23
+ "3": "happy",
24
+ "4": "surprise",
25
+ "5": "neutral",
26
+ "6": "sad"
27
+ },
28
+ "image_size": 224,
29
+ "initializer_range": 0.02,
30
+ "label2id": {
31
+ "anger": 1,
32
+ "disguist": 0,
33
+ "fear": 2,
34
+ "happy": 3,
35
+ "neutral": 5,
36
+ "sad": 6,
37
+ "surprise": 4
38
+ },
39
+ "layer_norm_eps": 1e-05,
40
+ "mlp_ratio": 4.0,
41
+ "model_type": "swin",
42
+ "num_channels": 3,
43
+ "num_heads": [
44
+ 3,
45
+ 6,
46
+ 12,
47
+ 24
48
+ ],
49
+ "num_layers": 4,
50
+ "out_features": [
51
+ "stage4"
52
+ ],
53
+ "out_indices": [
54
+ 4
55
+ ],
56
+ "patch_size": 4,
57
+ "path_norm": true,
58
+ "problem_type": "single_label_classification",
59
+ "qkv_bias": true,
60
+ "stage_names": [
61
+ "stem",
62
+ "stage1",
63
+ "stage2",
64
+ "stage3",
65
+ "stage4"
66
+ ],
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.39.3",
69
+ "use_absolute_embeddings": false,
70
+ "window_size": 7
71
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d505a5f4380041d56c6d4fcaddd1f62d3cfcd67336d931a4a3873d3d268e0f
3
+ size 110358212
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
+ 0.485,
21
+ 0.456,
22
+ 0.406
23
+ ],
24
+ "image_processor_type": "ViTImageProcessor",
25
+ "image_std": [
26
+ 0.229,
27
+ 0.224,
28
+ 0.225
29
+ ],
30
+ "resample": 3,
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:d3c326863034444401f26b03268d3083d5e78e526dc54fb1460c0bef3abad88b
3
+ size 4920