Hugging Face's logo

dima806
/
man_woman_face_image_detection

Image Classification
Transformers
PyTorch
Safetensors
vit
Inference Endpoints
Model card Files Community
1
dima806 commited on
Commit
945d1a5
•
1 Parent(s): 23e8f44

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-7956/config.json +32 -0
  2. checkpoint-7956/optimizer.pt +3 -0
  3. checkpoint-7956/preprocessor_config.json +22 -0
  4. checkpoint-7956/pytorch_model.bin +3 -0
  5. checkpoint-7956/rng_state.pth +3 -0
  6. checkpoint-7956/scheduler.pt +3 -0
  7. checkpoint-7956/trainer_state.json +190 -0
  8. checkpoint-7956/training_args.bin +3 -0
  9. config.json +32 -0
  10. preprocessor_config.json +22 -0
  11. pytorch_model.bin +3 -0
  12. training_args.bin +3 -0
checkpoint-7956/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "man",
13
+ "1": "woman"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "man": 0,
20
+ "woman": 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": "4.34.0"
32
+ }
checkpoint-7956/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97304930a323e622be45b2ca3d93030db563afc68726fd34179d7bb7abebfbae
3
+ size 686568453
checkpoint-7956/preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
checkpoint-7956/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f4637555585b0aac4f11d30cf37432c4df2b369d5509744cee71c6a98a0d53
3
+ size 343268717
checkpoint-7956/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd1a7d8a232b4286678e5d608981015f80c489118f79f0a4a0f7246e04aadb3
3
+ size 14575
checkpoint-7956/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffbffcf3efbbb7d0a20aef3aed93a06c463c329b351881b3748354deaef876eb
3
+ size 627
checkpoint-7956/trainer_state.json ADDED
@@ -0,0 +1,190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.06790149211883545,
3
+ "best_model_checkpoint": "gender_face_image_detection/checkpoint-7956",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 7956,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.57,
13
+ "learning_rate": 4.744027303754267e-06,
14
+ "loss": 0.2517,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.9735576923076923,
20
+ "eval_loss": 0.09853074699640274,
21
+ "eval_runtime": 70.669,
22
+ "eval_samples_per_second": 100.072,
23
+ "eval_steps_per_second": 12.509,
24
+ "step": 884
25
+ },
26
+ {
27
+ "epoch": 1.13,
28
+ "learning_rate": 4.459613196814562e-06,
29
+ "loss": 0.0926,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 1.7,
34
+ "learning_rate": 4.175199089874858e-06,
35
+ "loss": 0.0831,
36
+ "step": 1500
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.9789309954751131,
41
+ "eval_loss": 0.08093170076608658,
42
+ "eval_runtime": 69.4399,
43
+ "eval_samples_per_second": 101.843,
44
+ "eval_steps_per_second": 12.73,
45
+ "step": 1768
46
+ },
47
+ {
48
+ "epoch": 2.26,
49
+ "learning_rate": 3.890784982935154e-06,
50
+ "loss": 0.0699,
51
+ "step": 2000
52
+ },
53
+ {
54
+ "epoch": 2.83,
55
+ "learning_rate": 3.60637087599545e-06,
56
+ "loss": 0.0628,
57
+ "step": 2500
58
+ },
59
+ {
60
+ "epoch": 3.0,
61
+ "eval_accuracy": 0.9809106334841629,
62
+ "eval_loss": 0.07376975566148758,
63
+ "eval_runtime": 68.4743,
64
+ "eval_samples_per_second": 103.28,
65
+ "eval_steps_per_second": 12.91,
66
+ "step": 2652
67
+ },
68
+ {
69
+ "epoch": 3.39,
70
+ "learning_rate": 3.3219567690557453e-06,
71
+ "loss": 0.057,
72
+ "step": 3000
73
+ },
74
+ {
75
+ "epoch": 3.96,
76
+ "learning_rate": 3.0375426621160415e-06,
77
+ "loss": 0.0513,
78
+ "step": 3500
79
+ },
80
+ {
81
+ "epoch": 4.0,
82
+ "eval_accuracy": 0.9789309954751131,
83
+ "eval_loss": 0.07511751353740692,
84
+ "eval_runtime": 67.7191,
85
+ "eval_samples_per_second": 104.431,
86
+ "eval_steps_per_second": 13.054,
87
+ "step": 3536
88
+ },
89
+ {
90
+ "epoch": 4.52,
91
+ "learning_rate": 2.753128555176337e-06,
92
+ "loss": 0.0444,
93
+ "step": 4000
94
+ },
95
+ {
96
+ "epoch": 5.0,
97
+ "eval_accuracy": 0.9811934389140271,
98
+ "eval_loss": 0.06916382908821106,
99
+ "eval_runtime": 69.275,
100
+ "eval_samples_per_second": 102.086,
101
+ "eval_steps_per_second": 12.761,
102
+ "step": 4420
103
+ },
104
+ {
105
+ "epoch": 5.09,
106
+ "learning_rate": 2.4687144482366327e-06,
107
+ "loss": 0.043,
108
+ "step": 4500
109
+ },
110
+ {
111
+ "epoch": 5.66,
112
+ "learning_rate": 2.1843003412969285e-06,
113
+ "loss": 0.0396,
114
+ "step": 5000
115
+ },
116
+ {
117
+ "epoch": 6.0,
118
+ "eval_accuracy": 0.9816176470588235,
119
+ "eval_loss": 0.06955502182245255,
120
+ "eval_runtime": 68.4827,
121
+ "eval_samples_per_second": 103.267,
122
+ "eval_steps_per_second": 12.908,
123
+ "step": 5304
124
+ },
125
+ {
126
+ "epoch": 6.22,
127
+ "learning_rate": 1.8998862343572241e-06,
128
+ "loss": 0.0394,
129
+ "step": 5500
130
+ },
131
+ {
132
+ "epoch": 6.79,
133
+ "learning_rate": 1.61547212741752e-06,
134
+ "loss": 0.0369,
135
+ "step": 6000
136
+ },
137
+ {
138
+ "epoch": 7.0,
139
+ "eval_accuracy": 0.9813348416289592,
140
+ "eval_loss": 0.07007041573524475,
141
+ "eval_runtime": 68.4061,
142
+ "eval_samples_per_second": 103.383,
143
+ "eval_steps_per_second": 12.923,
144
+ "step": 6188
145
+ },
146
+ {
147
+ "epoch": 7.35,
148
+ "learning_rate": 1.331058020477816e-06,
149
+ "loss": 0.0326,
150
+ "step": 6500
151
+ },
152
+ {
153
+ "epoch": 7.92,
154
+ "learning_rate": 1.0466439135381116e-06,
155
+ "loss": 0.0324,
156
+ "step": 7000
157
+ },
158
+ {
159
+ "epoch": 8.0,
160
+ "eval_accuracy": 0.9817590497737556,
161
+ "eval_loss": 0.06906911730766296,
162
+ "eval_runtime": 70.5486,
163
+ "eval_samples_per_second": 100.243,
164
+ "eval_steps_per_second": 12.53,
165
+ "step": 7072
166
+ },
167
+ {
168
+ "epoch": 8.48,
169
+ "learning_rate": 7.622298065984074e-07,
170
+ "loss": 0.0318,
171
+ "step": 7500
172
+ },
173
+ {
174
+ "epoch": 9.0,
175
+ "eval_accuracy": 0.9816176470588235,
176
+ "eval_loss": 0.06790149211883545,
177
+ "eval_runtime": 68.1765,
178
+ "eval_samples_per_second": 103.731,
179
+ "eval_steps_per_second": 12.966,
180
+ "step": 7956
181
+ }
182
+ ],
183
+ "logging_steps": 500,
184
+ "max_steps": 8840,
185
+ "num_train_epochs": 10,
186
+ "save_steps": 500,
187
+ "total_flos": 1.972605090833208e+19,
188
+ "trial_name": null,
189
+ "trial_params": null
190
+ }
checkpoint-7956/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c78ef72ea7f3eb2b0ebf057d15a3261a5246b56ad85bf21dee6eb680accb10
3
+ size 4027
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "man",
13
+ "1": "woman"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "man": 0,
20
+ "woman": 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": "4.34.0"
32
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f4637555585b0aac4f11d30cf37432c4df2b369d5509744cee71c6a98a0d53
3
+ size 343268717
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c78ef72ea7f3eb2b0ebf057d15a3261a5246b56ad85bf21dee6eb680accb10
3
+ size 4027