Hugging Face's logo

dima806
/
military_aircraft_image_detection

Image Classification
Transformers
Safetensors
vit
Inference Endpoints
Model card Files Community
dima806 commited on
Commit
f7c9bc7
•
1 Parent(s): e4c7653

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-4970/config.json +120 -0
  2. checkpoint-4970/model.safetensors +3 -0
  3. checkpoint-4970/optimizer.pt +3 -0
  4. checkpoint-4970/preprocessor_config.json +22 -0
  5. checkpoint-4970/rng_state.pth +3 -0
  6. checkpoint-4970/scheduler.pt +3 -0
  7. checkpoint-4970/trainer_state.json +136 -0
  8. checkpoint-4970/training_args.bin +3 -0
  9. config.json +120 -0
  10. model.safetensors +3 -0
  11. preprocessor_config.json +22 -0
  12. training_args.bin +3 -0
checkpoint-4970/config.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "A10",
13
+ "1": "A400M",
14
+ "2": "AG600",
15
+ "3": "AV8B",
16
+ "4": "B1",
17
+ "5": "B2",
18
+ "6": "B52",
19
+ "7": "Be200",
20
+ "8": "C130",
21
+ "9": "C17",
22
+ "10": "C2",
23
+ "11": "C5",
24
+ "12": "E2",
25
+ "13": "E7",
26
+ "14": "EF2000",
27
+ "15": "F117",
28
+ "16": "F14",
29
+ "17": "F15",
30
+ "18": "F16",
31
+ "19": "F18",
32
+ "20": "F22",
33
+ "21": "F35",
34
+ "22": "F4",
35
+ "23": "J10",
36
+ "24": "J20",
37
+ "25": "JAS39",
38
+ "26": "KC135",
39
+ "27": "MQ9",
40
+ "28": "Mig31",
41
+ "29": "Mirage2000",
42
+ "30": "P3",
43
+ "31": "RQ4",
44
+ "32": "Rafale",
45
+ "33": "SR71",
46
+ "34": "Su25",
47
+ "35": "Su34",
48
+ "36": "Su57",
49
+ "37": "Tornado",
50
+ "38": "Tu160",
51
+ "39": "Tu95",
52
+ "40": "U2",
53
+ "41": "US2",
54
+ "42": "V22",
55
+ "43": "Vulcan",
56
+ "44": "XB70",
57
+ "45": "YF23"
58
+ },
59
+ "image_size": 224,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 3072,
62
+ "label2id": {
63
+ "A10": 0,
64
+ "A400M": 1,
65
+ "AG600": 2,
66
+ "AV8B": 3,
67
+ "B1": 4,
68
+ "B2": 5,
69
+ "B52": 6,
70
+ "Be200": 7,
71
+ "C130": 8,
72
+ "C17": 9,
73
+ "C2": 10,
74
+ "C5": 11,
75
+ "E2": 12,
76
+ "E7": 13,
77
+ "EF2000": 14,
78
+ "F117": 15,
79
+ "F14": 16,
80
+ "F15": 17,
81
+ "F16": 18,
82
+ "F18": 19,
83
+ "F22": 20,
84
+ "F35": 21,
85
+ "F4": 22,
86
+ "J10": 23,
87
+ "J20": 24,
88
+ "JAS39": 25,
89
+ "KC135": 26,
90
+ "MQ9": 27,
91
+ "Mig31": 28,
92
+ "Mirage2000": 29,
93
+ "P3": 30,
94
+ "RQ4": 31,
95
+ "Rafale": 32,
96
+ "SR71": 33,
97
+ "Su25": 34,
98
+ "Su34": 35,
99
+ "Su57": 36,
100
+ "Tornado": 37,
101
+ "Tu160": 38,
102
+ "Tu95": 39,
103
+ "U2": 40,
104
+ "US2": 41,
105
+ "V22": 42,
106
+ "Vulcan": 43,
107
+ "XB70": 44,
108
+ "YF23": 45
109
+ },
110
+ "layer_norm_eps": 1e-12,
111
+ "model_type": "vit",
112
+ "num_attention_heads": 12,
113
+ "num_channels": 3,
114
+ "num_hidden_layers": 12,
115
+ "patch_size": 16,
116
+ "problem_type": "single_label_classification",
117
+ "qkv_bias": true,
118
+ "torch_dtype": "float32",
119
+ "transformers_version": "4.35.2"
120
+ }
checkpoint-4970/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af40e536dabba4cf68373b0410d69fec7dd2df706bed255aeaf09c1d51ad4b8
3
+ size 343359328
checkpoint-4970/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a26ace676cf44667320bcf36106a31462cd0c04a6e1db47081348ea376dfde
3
+ size 686839045
checkpoint-4970/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-4970/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9636d306c60c2c319dd5b1c0dab7f33361fc8ad6dd2b4fcb64297b4ab0298759
3
+ size 14575
checkpoint-4970/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4eaccf58bce76a08aac435347caed15110c5d79b9d82c53158fffc49f2818ef
3
+ size 627
checkpoint-4970/trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.8745768070220947,
3
+ "best_model_checkpoint": "military_aircraft_image_detection/checkpoint-4970",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4970,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7,
13
+ "learning_rate": 3.6341463414634146e-06,
14
+ "loss": 3.77,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.22267242138641768,
20
+ "eval_loss": 3.634404182434082,
21
+ "eval_runtime": 170.34,
22
+ "eval_samples_per_second": 66.649,
23
+ "eval_steps_per_second": 2.084,
24
+ "step": 710
25
+ },
26
+ {
27
+ "epoch": 1.41,
28
+ "learning_rate": 3.227642276422764e-06,
29
+ "loss": 3.5786,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.4188320267770633,
35
+ "eval_loss": 3.3628058433532715,
36
+ "eval_runtime": 170.8422,
37
+ "eval_samples_per_second": 66.453,
38
+ "eval_steps_per_second": 2.078,
39
+ "step": 1420
40
+ },
41
+ {
42
+ "epoch": 2.11,
43
+ "learning_rate": 2.8211382113821137e-06,
44
+ "loss": 3.3536,
45
+ "step": 1500
46
+ },
47
+ {
48
+ "epoch": 2.82,
49
+ "learning_rate": 2.4146341463414632e-06,
50
+ "loss": 3.169,
51
+ "step": 2000
52
+ },
53
+ {
54
+ "epoch": 3.0,
55
+ "eval_accuracy": 0.4806659032854752,
56
+ "eval_loss": 3.168663501739502,
57
+ "eval_runtime": 169.9814,
58
+ "eval_samples_per_second": 66.79,
59
+ "eval_steps_per_second": 2.088,
60
+ "step": 2130
61
+ },
62
+ {
63
+ "epoch": 3.52,
64
+ "learning_rate": 2.0081300813008132e-06,
65
+ "loss": 3.0224,
66
+ "step": 2500
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "eval_accuracy": 0.518189024927332,
71
+ "eval_loss": 3.0338284969329834,
72
+ "eval_runtime": 169.3404,
73
+ "eval_samples_per_second": 67.042,
74
+ "eval_steps_per_second": 2.096,
75
+ "step": 2840
76
+ },
77
+ {
78
+ "epoch": 4.23,
79
+ "learning_rate": 1.6016260162601625e-06,
80
+ "loss": 2.9138,
81
+ "step": 3000
82
+ },
83
+ {
84
+ "epoch": 4.93,
85
+ "learning_rate": 1.195121951219512e-06,
86
+ "loss": 2.8289,
87
+ "step": 3500
88
+ },
89
+ {
90
+ "epoch": 5.0,
91
+ "eval_accuracy": 0.5321060512639831,
92
+ "eval_loss": 2.9448235034942627,
93
+ "eval_runtime": 168.8601,
94
+ "eval_samples_per_second": 67.233,
95
+ "eval_steps_per_second": 2.102,
96
+ "step": 3550
97
+ },
98
+ {
99
+ "epoch": 5.63,
100
+ "learning_rate": 7.886178861788617e-07,
101
+ "loss": 2.7671,
102
+ "step": 4000
103
+ },
104
+ {
105
+ "epoch": 6.0,
106
+ "eval_accuracy": 0.5462873249361402,
107
+ "eval_loss": 2.8909528255462646,
108
+ "eval_runtime": 166.9701,
109
+ "eval_samples_per_second": 67.994,
110
+ "eval_steps_per_second": 2.126,
111
+ "step": 4260
112
+ },
113
+ {
114
+ "epoch": 6.34,
115
+ "learning_rate": 3.821138211382114e-07,
116
+ "loss": 2.7237,
117
+ "step": 4500
118
+ },
119
+ {
120
+ "epoch": 7.0,
121
+ "eval_accuracy": 0.5477847265040078,
122
+ "eval_loss": 2.8745768070220947,
123
+ "eval_runtime": 166.7082,
124
+ "eval_samples_per_second": 68.101,
125
+ "eval_steps_per_second": 2.129,
126
+ "step": 4970
127
+ }
128
+ ],
129
+ "logging_steps": 500,
130
+ "max_steps": 4970,
131
+ "num_train_epochs": 7,
132
+ "save_steps": 500,
133
+ "total_flos": 2.4642635374286254e+19,
134
+ "trial_name": null,
135
+ "trial_params": null
136
+ }
checkpoint-4970/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898d0f338366e9ae5f4d60a230a21fcaa8cad01ad15478ca4c3fc1e36588fdf7
3
+ size 4091
config.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "A10",
13
+ "1": "A400M",
14
+ "2": "AG600",
15
+ "3": "AV8B",
16
+ "4": "B1",
17
+ "5": "B2",
18
+ "6": "B52",
19
+ "7": "Be200",
20
+ "8": "C130",
21
+ "9": "C17",
22
+ "10": "C2",
23
+ "11": "C5",
24
+ "12": "E2",
25
+ "13": "E7",
26
+ "14": "EF2000",
27
+ "15": "F117",
28
+ "16": "F14",
29
+ "17": "F15",
30
+ "18": "F16",
31
+ "19": "F18",
32
+ "20": "F22",
33
+ "21": "F35",
34
+ "22": "F4",
35
+ "23": "J10",
36
+ "24": "J20",
37
+ "25": "JAS39",
38
+ "26": "KC135",
39
+ "27": "MQ9",
40
+ "28": "Mig31",
41
+ "29": "Mirage2000",
42
+ "30": "P3",
43
+ "31": "RQ4",
44
+ "32": "Rafale",
45
+ "33": "SR71",
46
+ "34": "Su25",
47
+ "35": "Su34",
48
+ "36": "Su57",
49
+ "37": "Tornado",
50
+ "38": "Tu160",
51
+ "39": "Tu95",
52
+ "40": "U2",
53
+ "41": "US2",
54
+ "42": "V22",
55
+ "43": "Vulcan",
56
+ "44": "XB70",
57
+ "45": "YF23"
58
+ },
59
+ "image_size": 224,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 3072,
62
+ "label2id": {
63
+ "A10": 0,
64
+ "A400M": 1,
65
+ "AG600": 2,
66
+ "AV8B": 3,
67
+ "B1": 4,
68
+ "B2": 5,
69
+ "B52": 6,
70
+ "Be200": 7,
71
+ "C130": 8,
72
+ "C17": 9,
73
+ "C2": 10,
74
+ "C5": 11,
75
+ "E2": 12,
76
+ "E7": 13,
77
+ "EF2000": 14,
78
+ "F117": 15,
79
+ "F14": 16,
80
+ "F15": 17,
81
+ "F16": 18,
82
+ "F18": 19,
83
+ "F22": 20,
84
+ "F35": 21,
85
+ "F4": 22,
86
+ "J10": 23,
87
+ "J20": 24,
88
+ "JAS39": 25,
89
+ "KC135": 26,
90
+ "MQ9": 27,
91
+ "Mig31": 28,
92
+ "Mirage2000": 29,
93
+ "P3": 30,
94
+ "RQ4": 31,
95
+ "Rafale": 32,
96
+ "SR71": 33,
97
+ "Su25": 34,
98
+ "Su34": 35,
99
+ "Su57": 36,
100
+ "Tornado": 37,
101
+ "Tu160": 38,
102
+ "Tu95": 39,
103
+ "U2": 40,
104
+ "US2": 41,
105
+ "V22": 42,
106
+ "Vulcan": 43,
107
+ "XB70": 44,
108
+ "YF23": 45
109
+ },
110
+ "layer_norm_eps": 1e-12,
111
+ "model_type": "vit",
112
+ "num_attention_heads": 12,
113
+ "num_channels": 3,
114
+ "num_hidden_layers": 12,
115
+ "patch_size": 16,
116
+ "problem_type": "single_label_classification",
117
+ "qkv_bias": true,
118
+ "torch_dtype": "float32",
119
+ "transformers_version": "4.35.2"
120
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af40e536dabba4cf68373b0410d69fec7dd2df706bed255aeaf09c1d51ad4b8
3
+ size 343359328
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898d0f338366e9ae5f4d60a230a21fcaa8cad01ad15478ca4c3fc1e36588fdf7
3
+ size 4091