Hugging Face's logo

ZaneHorrible
/
ViTL-32-384-1e4-batch_16_epoch_4_classes_24

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ZaneHorrible commited on
Commit
63eaedb
•
1 Parent(s): 10b7c3c

Model save

Browse files
Files changed (6) hide show
  1. README.md +161 -0
  2. config.json +76 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +36 -0
  5. runs/May30_05-43-38_1cc5b958424b/events.out.tfevents.1717047819.1cc5b958424b.34.0 +3 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-large-patch32-384
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: ViTL-32-384-1e4-batch_16_epoch_4_classes_24
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: imagefolder
18
+ type: imagefolder
19
+ config: default
20
+ split: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.9755747126436781
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # ViTL-32-384-1e4-batch_16_epoch_4_classes_24
32
+
33
+ This model is a fine-tuned version of [google/vit-large-patch32-384](https://huggingface.co/google/vit-large-patch32-384) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.1157
36
+ - Accuracy: 0.9756
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 0.0001
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - num_epochs: 3
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.3336 | 0.03 | 100 | 0.2980 | 0.9325 |
69
+ | 0.0235 | 0.07 | 200 | 0.1580 | 0.9612 |
70
+ | 0.0381 | 0.1 | 300 | 0.2212 | 0.9540 |
71
+ | 0.0507 | 0.14 | 400 | 0.4664 | 0.9037 |
72
+ | 0.0052 | 0.17 | 500 | 0.1737 | 0.9670 |
73
+ | 0.0499 | 0.21 | 600 | 0.2187 | 0.9511 |
74
+ | 0.0454 | 0.24 | 700 | 0.1837 | 0.9569 |
75
+ | 0.0317 | 0.28 | 800 | 0.2616 | 0.9497 |
76
+ | 0.0594 | 0.31 | 900 | 0.1867 | 0.9555 |
77
+ | 0.0583 | 0.35 | 1000 | 0.1817 | 0.9569 |
78
+ | 0.0044 | 0.38 | 1100 | 0.2358 | 0.9497 |
79
+ | 0.0836 | 0.42 | 1200 | 0.2422 | 0.9454 |
80
+ | 0.0712 | 0.45 | 1300 | 0.1943 | 0.9555 |
81
+ | 0.0399 | 0.49 | 1400 | 0.2922 | 0.9440 |
82
+ | 0.0098 | 0.52 | 1500 | 0.3783 | 0.9325 |
83
+ | 0.0414 | 0.56 | 1600 | 0.2583 | 0.9454 |
84
+ | 0.1085 | 0.59 | 1700 | 0.2241 | 0.9511 |
85
+ | 0.0492 | 0.63 | 1800 | 0.2813 | 0.9368 |
86
+ | 0.044 | 0.66 | 1900 | 0.3361 | 0.9353 |
87
+ | 0.0344 | 0.7 | 2000 | 0.2549 | 0.9468 |
88
+ | 0.002 | 0.73 | 2100 | 0.1794 | 0.9641 |
89
+ | 0.0731 | 0.77 | 2200 | 0.2300 | 0.9540 |
90
+ | 0.0151 | 0.8 | 2300 | 0.2050 | 0.9569 |
91
+ | 0.0031 | 0.84 | 2400 | 0.2175 | 0.9454 |
92
+ | 0.1015 | 0.87 | 2500 | 0.1725 | 0.9626 |
93
+ | 0.0383 | 0.91 | 2600 | 0.2104 | 0.9540 |
94
+ | 0.0926 | 0.94 | 2700 | 0.1762 | 0.9540 |
95
+ | 0.0001 | 0.98 | 2800 | 0.1978 | 0.9612 |
96
+ | 0.1365 | 1.01 | 2900 | 0.1512 | 0.9655 |
97
+ | 0.083 | 1.04 | 3000 | 0.1298 | 0.9641 |
98
+ | 0.0002 | 1.08 | 3100 | 0.1976 | 0.9540 |
99
+ | 0.0042 | 1.11 | 3200 | 0.1719 | 0.9698 |
100
+ | 0.0002 | 1.15 | 3300 | 0.1924 | 0.9583 |
101
+ | 0.0002 | 1.18 | 3400 | 0.1732 | 0.9626 |
102
+ | 0.0978 | 1.22 | 3500 | 0.1902 | 0.9612 |
103
+ | 0.1067 | 1.25 | 3600 | 0.1868 | 0.9612 |
104
+ | 0.0005 | 1.29 | 3700 | 0.2166 | 0.9468 |
105
+ | 0.0007 | 1.32 | 3800 | 0.2293 | 0.9425 |
106
+ | 0.0001 | 1.36 | 3900 | 0.2296 | 0.9626 |
107
+ | 0.0001 | 1.39 | 4000 | 0.1685 | 0.9684 |
108
+ | 0.0001 | 1.43 | 4100 | 0.2106 | 0.9655 |
109
+ | 0.0004 | 1.46 | 4200 | 0.1614 | 0.9670 |
110
+ | 0.0 | 1.5 | 4300 | 0.1311 | 0.9727 |
111
+ | 0.0 | 1.53 | 4400 | 0.1445 | 0.9784 |
112
+ | 0.0433 | 1.57 | 4500 | 0.1544 | 0.9727 |
113
+ | 0.0263 | 1.6 | 4600 | 0.2133 | 0.9626 |
114
+ | 0.0 | 1.64 | 4700 | 0.1903 | 0.9598 |
115
+ | 0.0 | 1.67 | 4800 | 0.1587 | 0.9583 |
116
+ | 0.0 | 1.71 | 4900 | 0.1817 | 0.9655 |
117
+ | 0.1503 | 1.74 | 5000 | 0.2346 | 0.9526 |
118
+ | 0.0699 | 1.78 | 5100 | 0.1143 | 0.9713 |
119
+ | 0.0004 | 1.81 | 5200 | 0.1937 | 0.9626 |
120
+ | 0.0001 | 1.85 | 5300 | 0.2660 | 0.9540 |
121
+ | 0.2208 | 1.88 | 5400 | 0.1500 | 0.9713 |
122
+ | 0.0494 | 1.92 | 5500 | 0.1203 | 0.9698 |
123
+ | 0.0001 | 1.95 | 5600 | 0.1231 | 0.9756 |
124
+ | 0.0001 | 1.99 | 5700 | 0.1254 | 0.9698 |
125
+ | 0.0 | 2.02 | 5800 | 0.1622 | 0.9684 |
126
+ | 0.0001 | 2.06 | 5900 | 0.1464 | 0.9698 |
127
+ | 0.0 | 2.09 | 6000 | 0.1420 | 0.9698 |
128
+ | 0.0 | 2.12 | 6100 | 0.1416 | 0.9698 |
129
+ | 0.0 | 2.16 | 6200 | 0.1408 | 0.9698 |
130
+ | 0.0001 | 2.19 | 6300 | 0.1402 | 0.9698 |
131
+ | 0.0147 | 2.23 | 6400 | 0.1536 | 0.9655 |
132
+ | 0.0 | 2.26 | 6500 | 0.1944 | 0.9612 |
133
+ | 0.0 | 2.3 | 6600 | 0.1724 | 0.9684 |
134
+ | 0.0003 | 2.33 | 6700 | 0.1910 | 0.9612 |
135
+ | 0.0003 | 2.37 | 6800 | 0.1995 | 0.9626 |
136
+ | 0.0004 | 2.4 | 6900 | 0.1563 | 0.9655 |
137
+ | 0.0 | 2.44 | 7000 | 0.1460 | 0.9727 |
138
+ | 0.0 | 2.47 | 7100 | 0.1434 | 0.9727 |
139
+ | 0.0 | 2.51 | 7200 | 0.1242 | 0.9741 |
140
+ | 0.0041 | 2.54 | 7300 | 0.1364 | 0.9713 |
141
+ | 0.0 | 2.58 | 7400 | 0.1396 | 0.9684 |
142
+ | 0.0 | 2.61 | 7500 | 0.1371 | 0.9655 |
143
+ | 0.0 | 2.65 | 7600 | 0.1373 | 0.9684 |
144
+ | 0.0 | 2.68 | 7700 | 0.1230 | 0.9698 |
145
+ | 0.0 | 2.72 | 7800 | 0.1225 | 0.9698 |
146
+ | 0.0 | 2.75 | 7900 | 0.1223 | 0.9698 |
147
+ | 0.0001 | 2.79 | 8000 | 0.1218 | 0.9698 |
148
+ | 0.0 | 2.82 | 8100 | 0.1186 | 0.9756 |
149
+ | 0.0 | 2.86 | 8200 | 0.1183 | 0.9756 |
150
+ | 0.0 | 2.89 | 8300 | 0.1167 | 0.9756 |
151
+ | 0.0 | 2.93 | 8400 | 0.1163 | 0.9756 |
152
+ | 0.0 | 2.96 | 8500 | 0.1162 | 0.9756 |
153
+ | 0.0 | 3.0 | 8600 | 0.1157 | 0.9756 |
154
+
155
+
156
+ ### Framework versions
157
+
158
+ - Transformers 4.39.3
159
+ - Pytorch 2.1.2
160
+ - Datasets 2.18.0
161
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-large-patch32-384",
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": 1024,
11
+ "id2label": {
12
+ "0": "Bhapa Pitha(\u09ad\u09be\u09aa\u09be \u09aa\u09bf\u09a0\u09be)",
13
+ "1": "Biriyani(\u09ac\u09bf\u09b0\u09bf\u09df\u09be\u09a8\u09bf)",
14
+ "10": "Khichuri(\u0996\u09bf\u099a\u09c1\u09a1\u09bc\u09bf)",
15
+ "11": "Malpua Pitha(\u09ae\u09be\u09b2\u09aa\u09c1\u09df\u09be \u09aa\u09bf\u09a0\u09be)",
16
+ "12": "Mustard Hilsa(\u09b8\u09b0\u09b7\u09c7 \u0987\u09b2\u09bf\u09b6)",
17
+ "13": "Nakshi Pitha(\u09a8\u0995\u09b6\u09bf \u09aa\u09bf\u09a0\u09be)",
18
+ "14": "Panta Ilish(\u09aa\u09be\u09a8\u09cd\u09a4\u09be \u0987\u09b2\u09bf\u09b6)",
19
+ "15": "Patishapta Pitha(\u09aa\u09be\u099f\u09bf\u09b8\u09be\u09aa\u099f\u09be)",
20
+ "16": "Prawn Malai Curry(\u099a\u09bf\u0982\u09dc\u09bf \u09ae\u09be\u09b2\u09be\u0987\u0995\u09be\u09b0\u09c0)",
21
+ "17": "Rasgulla(\u09b0\u09b8\u0997\u09cb\u09b2\u09cd\u09b2\u09be)",
22
+ "18": "Rose Cookies(\u09ab\u09c1\u09b2\u099d\u09c1\u09b0\u09bf \u09aa\u09bf\u09a0\u09be)",
23
+ "19": "Roshmalai(\u09b0\u09b8\u09ae\u09be\u09b2\u09be\u0987)",
24
+ "2": "Chicken Pulao(\u09ae\u09cb\u09b0\u0997 \u09aa\u09cb\u09b2\u09be\u0993)",
25
+ "20": "Shahi Tukra(\u09b6\u09be\u09b9\u09bf \u099f\u09c1\u0995\u09b0\u09be)",
26
+ "21": "Shingara(\u09b8\u09bf\u0999\u09cd\u0997\u09be\u09b0\u09be)",
27
+ "22": "Sweet Yogurt(\u09ae\u09bf\u09b7\u09cd\u099f\u09bf \u09a6\u0987)",
28
+ "23": "Tehari(\u09a4\u09c7\u09b9\u09be\u09b0\u09bf)",
29
+ "3": "Chickpease Bhuna(\u099b\u09cb\u09b2\u09be\u09ad\u09c1\u09a8\u09be)",
30
+ "4": "Egg Curry(\u09a1\u09bf\u09ae\u09ad\u09c1\u09a8\u09be)",
31
+ "5": "Falooda(\u09ab\u09be\u09b2\u09c1\u09a6\u09be)",
32
+ "6": "Fuchka(\u09ab\u09c1\u099a\u0995\u09be)",
33
+ "7": "Haleem(\u09b9\u09be\u09b2\u09bf\u09ae)",
34
+ "8": "Jalebi(\u099c\u09bf\u09b2\u09be\u09aa\u09c0)",
35
+ "9": "Kala Bhuna(\u0995\u09be\u09b2\u09be \u09ad\u09c1\u09a8\u09be)"
36
+ },
37
+ "image_size": 384,
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 4096,
40
+ "label2id": {
41
+ "Bhapa Pitha(\u09ad\u09be\u09aa\u09be \u09aa\u09bf\u09a0\u09be)": "0",
42
+ "Biriyani(\u09ac\u09bf\u09b0\u09bf\u09df\u09be\u09a8\u09bf)": "1",
43
+ "Chicken Pulao(\u09ae\u09cb\u09b0\u0997 \u09aa\u09cb\u09b2\u09be\u0993)": "2",
44
+ "Chickpease Bhuna(\u099b\u09cb\u09b2\u09be\u09ad\u09c1\u09a8\u09be)": "3",
45
+ "Egg Curry(\u09a1\u09bf\u09ae\u09ad\u09c1\u09a8\u09be)": "4",
46
+ "Falooda(\u09ab\u09be\u09b2\u09c1\u09a6\u09be)": "5",
47
+ "Fuchka(\u09ab\u09c1\u099a\u0995\u09be)": "6",
48
+ "Haleem(\u09b9\u09be\u09b2\u09bf\u09ae)": "7",
49
+ "Jalebi(\u099c\u09bf\u09b2\u09be\u09aa\u09c0)": "8",
50
+ "Kala Bhuna(\u0995\u09be\u09b2\u09be \u09ad\u09c1\u09a8\u09be)": "9",
51
+ "Khichuri(\u0996\u09bf\u099a\u09c1\u09a1\u09bc\u09bf)": "10",
52
+ "Malpua Pitha(\u09ae\u09be\u09b2\u09aa\u09c1\u09df\u09be \u09aa\u09bf\u09a0\u09be)": "11",
53
+ "Mustard Hilsa(\u09b8\u09b0\u09b7\u09c7 \u0987\u09b2\u09bf\u09b6)": "12",
54
+ "Nakshi Pitha(\u09a8\u0995\u09b6\u09bf \u09aa\u09bf\u09a0\u09be)": "13",
55
+ "Panta Ilish(\u09aa\u09be\u09a8\u09cd\u09a4\u09be \u0987\u09b2\u09bf\u09b6)": "14",
56
+ "Patishapta Pitha(\u09aa\u09be\u099f\u09bf\u09b8\u09be\u09aa\u099f\u09be)": "15",
57
+ "Prawn Malai Curry(\u099a\u09bf\u0982\u09dc\u09bf \u09ae\u09be\u09b2\u09be\u0987\u0995\u09be\u09b0\u09c0)": "16",
58
+ "Rasgulla(\u09b0\u09b8\u0997\u09cb\u09b2\u09cd\u09b2\u09be)": "17",
59
+ "Rose Cookies(\u09ab\u09c1\u09b2\u099d\u09c1\u09b0\u09bf \u09aa\u09bf\u09a0\u09be)": "18",
60
+ "Roshmalai(\u09b0\u09b8\u09ae\u09be\u09b2\u09be\u0987)": "19",
61
+ "Shahi Tukra(\u09b6\u09be\u09b9\u09bf \u099f\u09c1\u0995\u09b0\u09be)": "20",
62
+ "Shingara(\u09b8\u09bf\u0999\u09cd\u0997\u09be\u09b0\u09be)": "21",
63
+ "Sweet Yogurt(\u09ae\u09bf\u09b7\u09cd\u099f\u09bf \u09a6\u0987)": "22",
64
+ "Tehari(\u09a4\u09c7\u09b9\u09be\u09b0\u09bf)": "23"
65
+ },
66
+ "layer_norm_eps": 1e-12,
67
+ "model_type": "vit",
68
+ "num_attention_heads": 16,
69
+ "num_channels": 3,
70
+ "num_hidden_layers": 24,
71
+ "patch_size": 32,
72
+ "problem_type": "single_label_classification",
73
+ "qkv_bias": true,
74
+ "torch_dtype": "float32",
75
+ "transformers_version": "4.39.3"
76
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b12658cf51dda578ff486c919747e981a01530b305983df0cae5240373385d0
3
+ size 1222575688
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
+ "height": 384,
34
+ "width": 384
35
+ }
36
+ }
runs/May30_05-43-38_1cc5b958424b/events.out.tfevents.1717047819.1cc5b958424b.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1453fcf43f14455949c5f43352d10d276f11065ff906a8f90a7ed473b1188b3
3
+ size 285213
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e82c20724d089fee86a5504f5076e576aefcec857be40bd9ea8585bcc7e100
3
+ size 4984