Hugging Face's logo

Zannatul
/
microsoft_swinv2-tiny-patch4-window8-256-batch_16_epoch_4_classes_24_final_withAug

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Zannatul commited on
Commit
5eacdfb
•
1 Parent(s): 123f483

Model save

Browse files
Files changed (6) hide show
  1. README.md +121 -0
  2. config.json +111 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +36 -0
  5. runs/May09_14-30-54_ed3f40b4fac8/events.out.tfevents.1715265059.ed3f40b4fac8.34.0 +3 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/swinv2-tiny-patch4-window8-256
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: microsoft_swinv2-tiny-patch4-window8-256-batch_16_epoch_4_classes_24_final_withAug
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: 0.9415760869565217
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
+ # microsoft_swinv2-tiny-patch4-window8-256-batch_16_epoch_4_classes_24_final_withAug
32
+
33
+ This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.2491
36
+ - Accuracy: 0.9416
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: 0.0002
56
+ - train_batch_size: 16
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: 4
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.7162 | 0.09 | 100 | 1.4225 | 0.7079 |
69
+ | 1.2286 | 0.17 | 200 | 0.9461 | 0.7935 |
70
+ | 1.0323 | 0.26 | 300 | 0.7366 | 0.8356 |
71
+ | 0.8678 | 0.34 | 400 | 0.6211 | 0.8628 |
72
+ | 0.7849 | 0.43 | 500 | 0.5354 | 0.8655 |
73
+ | 0.7105 | 0.51 | 600 | 0.4793 | 0.8899 |
74
+ | 0.6198 | 0.6 | 700 | 0.4319 | 0.9090 |
75
+ | 0.6276 | 0.68 | 800 | 0.4022 | 0.8981 |
76
+ | 0.5411 | 0.77 | 900 | 0.3816 | 0.9117 |
77
+ | 0.4984 | 0.85 | 1000 | 0.3824 | 0.9022 |
78
+ | 0.5665 | 0.94 | 1100 | 0.3460 | 0.9212 |
79
+ | 0.5741 | 1.02 | 1200 | 0.3336 | 0.9158 |
80
+ | 0.4039 | 1.11 | 1300 | 0.3204 | 0.9130 |
81
+ | 0.4347 | 1.19 | 1400 | 0.3038 | 0.9307 |
82
+ | 0.3639 | 1.28 | 1500 | 0.2955 | 0.9253 |
83
+ | 0.4282 | 1.36 | 1600 | 0.2948 | 0.9293 |
84
+ | 0.4375 | 1.45 | 1700 | 0.2868 | 0.9212 |
85
+ | 0.3063 | 1.53 | 1800 | 0.2861 | 0.9334 |
86
+ | 0.3549 | 1.62 | 1900 | 0.2826 | 0.9293 |
87
+ | 0.4326 | 1.71 | 2000 | 0.2698 | 0.9348 |
88
+ | 0.3697 | 1.79 | 2100 | 0.2602 | 0.9280 |
89
+ | 0.3155 | 1.88 | 2200 | 0.2523 | 0.9361 |
90
+ | 0.3348 | 1.96 | 2300 | 0.2506 | 0.9470 |
91
+ | 0.3854 | 2.05 | 2400 | 0.2565 | 0.9321 |
92
+ | 0.3951 | 2.13 | 2500 | 0.2482 | 0.9402 |
93
+ | 0.3531 | 2.22 | 2600 | 0.2455 | 0.9402 |
94
+ | 0.3643 | 2.3 | 2700 | 0.2513 | 0.9375 |
95
+ | 0.3393 | 2.39 | 2800 | 0.2492 | 0.9429 |
96
+ | 0.3635 | 2.47 | 2900 | 0.2394 | 0.9402 |
97
+ | 0.3624 | 2.56 | 3000 | 0.2425 | 0.9389 |
98
+ | 0.3608 | 2.64 | 3100 | 0.2390 | 0.9457 |
99
+ | 0.3215 | 2.73 | 3200 | 0.2483 | 0.9321 |
100
+ | 0.2971 | 2.81 | 3300 | 0.2455 | 0.9402 |
101
+ | 0.3838 | 2.9 | 3400 | 0.2363 | 0.9470 |
102
+ | 0.3036 | 2.98 | 3500 | 0.2422 | 0.9402 |
103
+ | 0.401 | 3.07 | 3600 | 0.2398 | 0.9429 |
104
+ | 0.3458 | 3.15 | 3700 | 0.2517 | 0.9429 |
105
+ | 0.2908 | 3.24 | 3800 | 0.2423 | 0.9457 |
106
+ | 0.3016 | 3.32 | 3900 | 0.2402 | 0.9443 |
107
+ | 0.2961 | 3.41 | 4000 | 0.2414 | 0.9457 |
108
+ | 0.3822 | 3.5 | 4100 | 0.2413 | 0.9416 |
109
+ | 0.2596 | 3.58 | 4200 | 0.2356 | 0.9457 |
110
+ | 0.3064 | 3.67 | 4300 | 0.2324 | 0.9497 |
111
+ | 0.3059 | 3.75 | 4400 | 0.2321 | 0.9457 |
112
+ | 0.42 | 3.84 | 4500 | 0.2556 | 0.9402 |
113
+ | 0.2959 | 3.92 | 4600 | 0.2491 | 0.9416 |
114
+
115
+
116
+ ### Framework versions
117
+
118
+ - Transformers 4.39.3
119
+ - Pytorch 2.1.2
120
+ - Datasets 2.18.0
121
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/swinv2-tiny-patch4-window8-256",
3
+ "architectures": [
4
+ "Swinv2ForImageClassification"
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": "Bhapa Pitha(\u09ad\u09be\u09aa\u09be \u09aa\u09bf\u09a0\u09be)",
21
+ "1": "Biriyani(\u09ac\u09bf\u09b0\u09bf\u09df\u09be\u09a8\u09bf)",
22
+ "10": "Khichuri(\u0996\u09bf\u099a\u09c1\u09a1\u09bc\u09bf)",
23
+ "11": "Malpua Pitha(\u09ae\u09be\u09b2\u09aa\u09c1\u09df\u09be \u09aa\u09bf\u09a0\u09be)",
24
+ "12": "Mustard Hilsa(\u09b8\u09b0\u09b7\u09c7 \u0987\u09b2\u09bf\u09b6)",
25
+ "13": "Nakshi Pitha(\u09a8\u0995\u09b6\u09bf \u09aa\u09bf\u09a0\u09be)",
26
+ "14": "Panta Ilish(\u09aa\u09be\u09a8\u09cd\u09a4\u09be \u0987\u09b2\u09bf\u09b6)",
27
+ "15": "Patishapta Pitha(\u09aa\u09be\u099f\u09bf\u09b8\u09be\u09aa\u099f\u09be)",
28
+ "16": "Prawn Malai Curry(\u099a\u09bf\u0982\u09dc\u09bf \u09ae\u09be\u09b2\u09be\u0987\u0995\u09be\u09b0\u09c0)",
29
+ "17": "Rasgulla(\u09b0\u09b8\u0997\u09cb\u09b2\u09cd\u09b2\u09be)",
30
+ "18": "Rose Cookies(\u09ab\u09c1\u09b2\u099d\u09c1\u09b0\u09bf \u09aa\u09bf\u09a0\u09be)",
31
+ "19": "Roshmalai(\u09b0\u09b8\u09ae\u09be\u09b2\u09be\u0987)",
32
+ "2": "Chicken Pulao(\u09ae\u09cb\u09b0\u0997 \u09aa\u09cb\u09b2\u09be\u0993)",
33
+ "20": "Shahi Tukra(\u09b6\u09be\u09b9\u09bf \u099f\u09c1\u0995\u09b0\u09be)",
34
+ "21": "Shingara(\u09b8\u09bf\u0999\u09cd\u0997\u09be\u09b0\u09be)",
35
+ "22": "Sweet Yogurt(\u09ae\u09bf\u09b7\u09cd\u099f\u09bf \u09a6\u0987)",
36
+ "23": "Tehari(\u09a4\u09c7\u09b9\u09be\u09b0\u09bf)",
37
+ "3": "Chickpease Bhuna(\u099b\u09cb\u09b2\u09be\u09ad\u09c1\u09a8\u09be)",
38
+ "4": "Egg Curry(\u09a1\u09bf\u09ae\u09ad\u09c1\u09a8\u09be)",
39
+ "5": "Falooda(\u09ab\u09be\u09b2\u09c1\u09a6\u09be)",
40
+ "6": "Fuchka(\u09ab\u09c1\u099a\u0995\u09be)",
41
+ "7": "Haleem(\u09b9\u09be\u09b2\u09bf\u09ae)",
42
+ "8": "Jalebi(\u099c\u09bf\u09b2\u09be\u09aa\u09c0)",
43
+ "9": "Kala Bhuna(\u0995\u09be\u09b2\u09be \u09ad\u09c1\u09a8\u09be)"
44
+ },
45
+ "image_size": 256,
46
+ "initializer_range": 0.02,
47
+ "label2id": {
48
+ "Bhapa Pitha(\u09ad\u09be\u09aa\u09be \u09aa\u09bf\u09a0\u09be)": "0",
49
+ "Biriyani(\u09ac\u09bf\u09b0\u09bf\u09df\u09be\u09a8\u09bf)": "1",
50
+ "Chicken Pulao(\u09ae\u09cb\u09b0\u0997 \u09aa\u09cb\u09b2\u09be\u0993)": "2",
51
+ "Chickpease Bhuna(\u099b\u09cb\u09b2\u09be\u09ad\u09c1\u09a8\u09be)": "3",
52
+ "Egg Curry(\u09a1\u09bf\u09ae\u09ad\u09c1\u09a8\u09be)": "4",
53
+ "Falooda(\u09ab\u09be\u09b2\u09c1\u09a6\u09be)": "5",
54
+ "Fuchka(\u09ab\u09c1\u099a\u0995\u09be)": "6",
55
+ "Haleem(\u09b9\u09be\u09b2\u09bf\u09ae)": "7",
56
+ "Jalebi(\u099c\u09bf\u09b2\u09be\u09aa\u09c0)": "8",
57
+ "Kala Bhuna(\u0995\u09be\u09b2\u09be \u09ad\u09c1\u09a8\u09be)": "9",
58
+ "Khichuri(\u0996\u09bf\u099a\u09c1\u09a1\u09bc\u09bf)": "10",
59
+ "Malpua Pitha(\u09ae\u09be\u09b2\u09aa\u09c1\u09df\u09be \u09aa\u09bf\u09a0\u09be)": "11",
60
+ "Mustard Hilsa(\u09b8\u09b0\u09b7\u09c7 \u0987\u09b2\u09bf\u09b6)": "12",
61
+ "Nakshi Pitha(\u09a8\u0995\u09b6\u09bf \u09aa\u09bf\u09a0\u09be)": "13",
62
+ "Panta Ilish(\u09aa\u09be\u09a8\u09cd\u09a4\u09be \u0987\u09b2\u09bf\u09b6)": "14",
63
+ "Patishapta Pitha(\u09aa\u09be\u099f\u09bf\u09b8\u09be\u09aa\u099f\u09be)": "15",
64
+ "Prawn Malai Curry(\u099a\u09bf\u0982\u09dc\u09bf \u09ae\u09be\u09b2\u09be\u0987\u0995\u09be\u09b0\u09c0)": "16",
65
+ "Rasgulla(\u09b0\u09b8\u0997\u09cb\u09b2\u09cd\u09b2\u09be)": "17",
66
+ "Rose Cookies(\u09ab\u09c1\u09b2\u099d\u09c1\u09b0\u09bf \u09aa\u09bf\u09a0\u09be)": "18",
67
+ "Roshmalai(\u09b0\u09b8\u09ae\u09be\u09b2\u09be\u0987)": "19",
68
+ "Shahi Tukra(\u09b6\u09be\u09b9\u09bf \u099f\u09c1\u0995\u09b0\u09be)": "20",
69
+ "Shingara(\u09b8\u09bf\u0999\u09cd\u0997\u09be\u09b0\u09be)": "21",
70
+ "Sweet Yogurt(\u09ae\u09bf\u09b7\u09cd\u099f\u09bf \u09a6\u0987)": "22",
71
+ "Tehari(\u09a4\u09c7\u09b9\u09be\u09b0\u09bf)": "23"
72
+ },
73
+ "layer_norm_eps": 1e-05,
74
+ "mlp_ratio": 4.0,
75
+ "model_type": "swinv2",
76
+ "num_channels": 3,
77
+ "num_heads": [
78
+ 3,
79
+ 6,
80
+ 12,
81
+ 24
82
+ ],
83
+ "num_layers": 4,
84
+ "out_features": [
85
+ "stage4"
86
+ ],
87
+ "out_indices": [
88
+ 4
89
+ ],
90
+ "patch_size": 4,
91
+ "path_norm": true,
92
+ "pretrained_window_sizes": [
93
+ 0,
94
+ 0,
95
+ 0,
96
+ 0
97
+ ],
98
+ "problem_type": "single_label_classification",
99
+ "qkv_bias": true,
100
+ "stage_names": [
101
+ "stem",
102
+ "stage1",
103
+ "stage2",
104
+ "stage3",
105
+ "stage4"
106
+ ],
107
+ "torch_dtype": "float32",
108
+ "transformers_version": "4.39.3",
109
+ "use_absolute_embeddings": false,
110
+ "window_size": 8
111
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54fc643e6b53bb2a76af2b17237b26b9f9429e52aceada3dd183a1e637fd49f0
3
+ size 110417832
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
+ }
runs/May09_14-30-54_ed3f40b4fac8/events.out.tfevents.1715265059.ed3f40b4fac8.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:851ab9e3180b04496e85d61c65a6cb118d134e7be519a6cce6f2a018a512891e
3
+ size 122925
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9e494459a4f0fa1651b925314810a89b0d28a180ec69e84c55abb3c2e3387f1
3
+ size 5048