Raihan004 commited on
Commit
2437f2b
1 Parent(s): 72c64aa

Model save

Browse files
README.md CHANGED
@@ -1,8 +1,7 @@
1
  ---
2
  license: apache-2.0
3
- base_model: microsoft/swinv2-tiny-patch4-window16-256
4
  tags:
5
- - image-classification
6
  - generated_from_trainer
7
  datasets:
8
  - imagefolder
@@ -15,7 +14,7 @@ model-index:
15
  name: Image Classification
16
  type: image-classification
17
  dataset:
18
- name: agent_action_class
19
  type: imagefolder
20
  config: default
21
  split: train
@@ -23,7 +22,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.7895238095238095
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  # Action_agent
33
 
34
- This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window16-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window16-256) on the agent_action_class dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.6309
37
- - Accuracy: 0.7895
38
 
39
  ## Model description
40
 
@@ -59,43 +58,74 @@ The following hyperparameters were used during training:
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
- - num_epochs: 10
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 2.039 | 0.32 | 100 | 1.7706 | 0.4848 |
69
- | 1.3695 | 0.64 | 200 | 1.0886 | 0.6457 |
70
- | 1.099 | 0.96 | 300 | 0.9092 | 0.68 |
71
- | 1.0011 | 1.27 | 400 | 0.8183 | 0.7171 |
72
- | 0.8437 | 1.59 | 500 | 0.7674 | 0.7190 |
73
- | 0.8613 | 1.91 | 600 | 0.7168 | 0.7410 |
74
- | 0.7427 | 2.23 | 700 | 0.7270 | 0.7352 |
75
- | 0.693 | 2.55 | 800 | 0.6801 | 0.7676 |
76
- | 0.7789 | 2.87 | 900 | 0.6832 | 0.7590 |
77
- | 0.6863 | 3.18 | 1000 | 0.6655 | 0.7752 |
78
- | 0.6437 | 3.5 | 1100 | 0.6382 | 0.7771 |
79
- | 0.6741 | 3.82 | 1200 | 0.6446 | 0.7790 |
80
- | 0.5871 | 4.14 | 1300 | 0.6551 | 0.7838 |
81
- | 0.6051 | 4.46 | 1400 | 0.6970 | 0.7638 |
82
- | 0.5175 | 4.78 | 1500 | 0.6553 | 0.7790 |
83
- | 0.5795 | 5.1 | 1600 | 0.6667 | 0.7771 |
84
- | 0.4919 | 5.41 | 1700 | 0.6317 | 0.7905 |
85
- | 0.4986 | 5.73 | 1800 | 0.6486 | 0.7810 |
86
- | 0.5104 | 6.05 | 1900 | 0.6700 | 0.7743 |
87
- | 0.4919 | 6.37 | 2000 | 0.6528 | 0.7819 |
88
- | 0.5144 | 6.69 | 2100 | 0.6355 | 0.7876 |
89
- | 0.5554 | 7.01 | 2200 | 0.6552 | 0.7771 |
90
- | 0.5389 | 7.32 | 2300 | 0.6361 | 0.7876 |
91
- | 0.5751 | 7.64 | 2400 | 0.6377 | 0.7905 |
92
- | 0.4743 | 7.96 | 2500 | 0.6417 | 0.7867 |
93
- | 0.4519 | 8.28 | 2600 | 0.6309 | 0.7895 |
94
- | 0.5058 | 8.6 | 2700 | 0.6453 | 0.7867 |
95
- | 0.4754 | 8.92 | 2800 | 0.6414 | 0.7905 |
96
- | 0.4637 | 9.24 | 2900 | 0.6330 | 0.7905 |
97
- | 0.5028 | 9.55 | 3000 | 0.6418 | 0.7857 |
98
- | 0.4227 | 9.87 | 3100 | 0.6412 | 0.7914 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99
 
100
 
101
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: google/vit-base-patch16-224-in21k
4
  tags:
 
5
  - generated_from_trainer
6
  datasets:
7
  - imagefolder
 
14
  name: Image Classification
15
  type: image-classification
16
  dataset:
17
+ name: imagefolder
18
  type: imagefolder
19
  config: default
20
  split: train
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8019047619047619
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # Action_agent
32
 
33
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.6758
36
+ - Accuracy: 0.8019
37
 
38
  ## Model description
39
 
 
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 20
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 2.1987 | 0.32 | 100 | 2.1640 | 0.3914 |
68
+ | 1.9807 | 0.64 | 200 | 1.9169 | 0.6143 |
69
+ | 1.6738 | 0.96 | 300 | 1.6148 | 0.72 |
70
+ | 1.4828 | 1.27 | 400 | 1.3861 | 0.7705 |
71
+ | 1.2768 | 1.59 | 500 | 1.2412 | 0.7590 |
72
+ | 1.1759 | 1.91 | 600 | 1.1169 | 0.7914 |
73
+ | 1.0314 | 2.23 | 700 | 1.0599 | 0.7762 |
74
+ | 0.9702 | 2.55 | 800 | 0.9640 | 0.8105 |
75
+ | 0.9559 | 2.87 | 900 | 0.9138 | 0.8076 |
76
+ | 0.858 | 3.18 | 1000 | 0.8605 | 0.8248 |
77
+ | 0.7858 | 3.5 | 1100 | 0.8164 | 0.8371 |
78
+ | 0.7898 | 3.82 | 1200 | 0.7917 | 0.8333 |
79
+ | 0.6909 | 4.14 | 1300 | 0.7995 | 0.8038 |
80
+ | 0.6619 | 4.46 | 1400 | 0.8194 | 0.7829 |
81
+ | 0.6457 | 4.78 | 1500 | 0.7536 | 0.8086 |
82
+ | 0.6155 | 5.1 | 1600 | 0.7212 | 0.8257 |
83
+ | 0.5511 | 5.41 | 1700 | 0.7274 | 0.8095 |
84
+ | 0.5486 | 5.73 | 1800 | 0.7048 | 0.8286 |
85
+ | 0.5679 | 6.05 | 1900 | 0.7124 | 0.8181 |
86
+ | 0.4914 | 6.37 | 2000 | 0.7277 | 0.8010 |
87
+ | 0.525 | 6.69 | 2100 | 0.6971 | 0.8124 |
88
+ | 0.5081 | 7.01 | 2200 | 0.6869 | 0.8162 |
89
+ | 0.5072 | 7.32 | 2300 | 0.6837 | 0.8076 |
90
+ | 0.4702 | 7.64 | 2400 | 0.6736 | 0.8152 |
91
+ | 0.4303 | 7.96 | 2500 | 0.6693 | 0.8105 |
92
+ | 0.3916 | 8.28 | 2600 | 0.6487 | 0.8238 |
93
+ | 0.4002 | 8.6 | 2700 | 0.6661 | 0.8162 |
94
+ | 0.3965 | 8.92 | 2800 | 0.6611 | 0.8143 |
95
+ | 0.3946 | 9.24 | 2900 | 0.6523 | 0.8143 |
96
+ | 0.3794 | 9.55 | 3000 | 0.6616 | 0.8048 |
97
+ | 0.3257 | 9.87 | 3100 | 0.6717 | 0.8029 |
98
+ | 0.4175 | 10.19 | 3200 | 0.6530 | 0.8057 |
99
+ | 0.3559 | 10.51 | 3300 | 0.6883 | 0.7886 |
100
+ | 0.3824 | 10.83 | 3400 | 0.6611 | 0.8 |
101
+ | 0.3589 | 11.15 | 3500 | 0.6659 | 0.8019 |
102
+ | 0.3299 | 11.46 | 3600 | 0.6819 | 0.7962 |
103
+ | 0.3736 | 11.78 | 3700 | 0.6405 | 0.8114 |
104
+ | 0.3576 | 12.1 | 3800 | 0.6725 | 0.7962 |
105
+ | 0.3454 | 12.42 | 3900 | 0.7025 | 0.7943 |
106
+ | 0.3049 | 12.74 | 4000 | 0.6439 | 0.8133 |
107
+ | 0.3363 | 13.06 | 4100 | 0.6352 | 0.8143 |
108
+ | 0.3273 | 13.38 | 4200 | 0.6795 | 0.7886 |
109
+ | 0.283 | 13.69 | 4300 | 0.6705 | 0.8 |
110
+ | 0.2607 | 14.01 | 4400 | 0.6732 | 0.7914 |
111
+ | 0.3174 | 14.33 | 4500 | 0.6691 | 0.8048 |
112
+ | 0.3189 | 14.65 | 4600 | 0.6602 | 0.8038 |
113
+ | 0.2862 | 14.97 | 4700 | 0.6801 | 0.7933 |
114
+ | 0.2895 | 15.29 | 4800 | 0.6579 | 0.8038 |
115
+ | 0.263 | 15.61 | 4900 | 0.6688 | 0.8 |
116
+ | 0.3214 | 15.92 | 5000 | 0.6547 | 0.8057 |
117
+ | 0.2867 | 16.24 | 5100 | 0.6775 | 0.7924 |
118
+ | 0.2242 | 16.56 | 5200 | 0.6378 | 0.8086 |
119
+ | 0.2839 | 16.88 | 5300 | 0.6761 | 0.7990 |
120
+ | 0.2424 | 17.2 | 5400 | 0.6386 | 0.8124 |
121
+ | 0.2666 | 17.52 | 5500 | 0.6493 | 0.8133 |
122
+ | 0.2259 | 17.83 | 5600 | 0.6514 | 0.8048 |
123
+ | 0.2533 | 18.15 | 5700 | 0.6676 | 0.8 |
124
+ | 0.2697 | 18.47 | 5800 | 0.6705 | 0.8010 |
125
+ | 0.2558 | 18.79 | 5900 | 0.6750 | 0.8076 |
126
+ | 0.2469 | 19.11 | 6000 | 0.6751 | 0.7990 |
127
+ | 0.284 | 19.43 | 6100 | 0.6738 | 0.7981 |
128
+ | 0.2534 | 19.75 | 6200 | 0.6758 | 0.8019 |
129
 
130
 
131
  ### Framework versions
config.json CHANGED
@@ -1,18 +1,10 @@
1
  {
2
- "_name_or_path": "microsoft/swinv2-tiny-patch4-window16-256",
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,
@@ -28,8 +20,9 @@
28
  "8": "\u09b2\u09c7\u0996\u09be",
29
  "9": "\u09b9\u09be\u0981\u099f\u09be"
30
  },
31
- "image_size": 256,
32
  "initializer_range": 0.02,
 
33
  "label2id": {
34
  "\u0995\u09a5\u09be_\u09ac\u09b2\u09be": "0",
35
  "\u0995\u09ae\u09cd\u09aa\u09bf\u0989\u099f\u09be\u09b0_\u09ac\u09cd\u09af\u09ac\u09b9\u09be\u09b0_\u0995\u09b0\u09be": "1",
@@ -42,42 +35,14 @@
42
  "\u09b2\u09c7\u0996\u09be": "8",
43
  "\u09b9\u09be\u0981\u099f\u09be": "9"
44
  },
45
- "layer_norm_eps": 1e-05,
46
- "mlp_ratio": 4.0,
47
- "model_type": "swinv2",
48
  "num_channels": 3,
49
- "num_heads": [
50
- 3,
51
- 6,
52
- 12,
53
- 24
54
- ],
55
- "num_layers": 4,
56
- "out_features": [
57
- "stage4"
58
- ],
59
- "out_indices": [
60
- 4
61
- ],
62
- "patch_size": 4,
63
- "path_norm": true,
64
- "pretrained_window_sizes": [
65
- 0,
66
- 0,
67
- 0,
68
- 0
69
- ],
70
  "problem_type": "single_label_classification",
71
  "qkv_bias": true,
72
- "stage_names": [
73
- "stem",
74
- "stage1",
75
- "stage2",
76
- "stage3",
77
- "stage4"
78
- ],
79
  "torch_dtype": "float32",
80
- "transformers_version": "4.39.3",
81
- "use_absolute_embeddings": false,
82
- "window_size": 16
83
  }
 
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,
 
20
  "8": "\u09b2\u09c7\u0996\u09be",
21
  "9": "\u09b9\u09be\u0981\u099f\u09be"
22
  },
23
+ "image_size": 224,
24
  "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
  "label2id": {
27
  "\u0995\u09a5\u09be_\u09ac\u09b2\u09be": "0",
28
  "\u0995\u09ae\u09cd\u09aa\u09bf\u0989\u099f\u09be\u09b0_\u09ac\u09cd\u09af\u09ac\u09b9\u09be\u09b0_\u0995\u09b0\u09be": "1",
 
35
  "\u09b2\u09c7\u0996\u09be": "8",
36
  "\u09b9\u09be\u0981\u099f\u09be": "9"
37
  },
38
+ "layer_norm_eps": 1e-12,
39
+ "model_type": "vit",
40
+ "num_attention_heads": 12,
41
  "num_channels": 3,
42
+ "num_hidden_layers": 12,
43
+ "patch_size": 16,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
  "problem_type": "single_label_classification",
45
  "qkv_bias": true,
 
 
 
 
 
 
 
46
  "torch_dtype": "float32",
47
+ "transformers_version": "4.39.3"
 
 
48
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b5cf3b87b343cd43304129258627ec15995b5efe57f624c30058abd1a85104a
3
- size 110374752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31983f56343634d1a566ca12a56db4837634bdeac1d25f16d1410f817d230089
3
+ size 343248584
preprocessor_config.json CHANGED
@@ -17,20 +17,20 @@
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": 256,
34
- "width": 256
35
  }
36
  }
 
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": "ViTImageProcessor",
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": 224,
34
+ "width": 224
35
  }
36
  }
runs/Apr23_06-49-05_ca94fea6a63f/events.out.tfevents.1713854946.ca94fea6a63f.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb73bb9a337d082f649e606b6f76a47a3e8215503c9a86459e3a6f2ab633b08f
3
+ size 114142
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e145019e5e9eb49ac1a9542b4cc2430a5e37f69fa201e50c7d9e96b4bb660be
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad13277320cee32735fa755cc8392846fb447972a0cef9dae2890aaa91beb780
3
  size 4920