Hugging Face's logo

clauculus
/
image_classification

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
1
clauculus commited on
Commit
119c4c1
·
1 Parent(s): 773bec2

emotion-classification

Browse files
Files changed (2) hide show
  1. README.md +107 -47
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.49375
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 1.4194
36
- - Accuracy: 0.4938
37
 
38
  ## Model description
39
 
@@ -52,58 +52,118 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 5e-05
56
- - train_batch_size: 16
57
- - eval_batch_size: 16
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 40
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 40 | 1.8274 | 0.325 |
68
- | No log | 2.0 | 80 | 1.5456 | 0.4437 |
69
- | No log | 3.0 | 120 | 1.4503 | 0.425 |
70
- | No log | 4.0 | 160 | 1.3753 | 0.4688 |
71
- | No log | 5.0 | 200 | 1.3046 | 0.4813 |
72
- | No log | 6.0 | 240 | 1.2786 | 0.4875 |
73
- | No log | 7.0 | 280 | 1.4095 | 0.4875 |
74
- | No log | 8.0 | 320 | 1.3636 | 0.4688 |
75
- | No log | 9.0 | 360 | 1.3518 | 0.4562 |
76
- | No log | 10.0 | 400 | 1.4466 | 0.4688 |
77
- | No log | 11.0 | 440 | 1.3533 | 0.5125 |
78
- | No log | 12.0 | 480 | 1.3538 | 0.5125 |
79
- | 1.002 | 13.0 | 520 | 1.3608 | 0.5188 |
80
- | 1.002 | 14.0 | 560 | 1.3736 | 0.55 |
81
- | 1.002 | 15.0 | 600 | 1.4872 | 0.4688 |
82
- | 1.002 | 16.0 | 640 | 1.4549 | 0.525 |
83
- | 1.002 | 17.0 | 680 | 1.4956 | 0.5062 |
84
- | 1.002 | 18.0 | 720 | 1.5431 | 0.475 |
85
- | 1.002 | 19.0 | 760 | 1.5045 | 0.5312 |
86
- | 1.002 | 20.0 | 800 | 1.5330 | 0.525 |
87
- | 1.002 | 21.0 | 840 | 1.4794 | 0.5375 |
88
- | 1.002 | 22.0 | 880 | 1.4762 | 0.5375 |
89
- | 1.002 | 23.0 | 920 | 1.5691 | 0.4813 |
90
- | 1.002 | 24.0 | 960 | 1.5839 | 0.5 |
91
- | 0.2831 | 25.0 | 1000 | 1.6461 | 0.4813 |
92
- | 0.2831 | 26.0 | 1040 | 1.6359 | 0.4813 |
93
- | 0.2831 | 27.0 | 1080 | 1.5603 | 0.525 |
94
- | 0.2831 | 28.0 | 1120 | 1.5738 | 0.5 |
95
- | 0.2831 | 29.0 | 1160 | 1.6534 | 0.4938 |
96
- | 0.2831 | 30.0 | 1200 | 1.7387 | 0.4813 |
97
- | 0.2831 | 31.0 | 1240 | 1.7778 | 0.4562 |
98
- | 0.2831 | 32.0 | 1280 | 1.6399 | 0.525 |
99
- | 0.2831 | 33.0 | 1320 | 1.6575 | 0.5437 |
100
- | 0.2831 | 34.0 | 1360 | 1.6041 | 0.5062 |
101
- | 0.2831 | 35.0 | 1400 | 1.8253 | 0.4813 |
102
- | 0.2831 | 36.0 | 1440 | 1.6909 | 0.4875 |
103
- | 0.2831 | 37.0 | 1480 | 1.6586 | 0.5437 |
104
- | 0.1654 | 38.0 | 1520 | 1.6183 | 0.5125 |
105
- | 0.1654 | 39.0 | 1560 | 1.6045 | 0.5188 |
106
- | 0.1654 | 40.0 | 1600 | 1.6228 | 0.4938 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
 
108
 
109
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.50625
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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: 1.3344
36
+ - Accuracy: 0.5062
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 1e-05
56
+ - train_batch_size: 64
57
+ - eval_batch_size: 64
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 100
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 10 | 2.0716 | 0.1187 |
68
+ | No log | 2.0 | 20 | 2.0629 | 0.1375 |
69
+ | No log | 3.0 | 30 | 2.0521 | 0.1562 |
70
+ | No log | 4.0 | 40 | 2.0437 | 0.2125 |
71
+ | No log | 5.0 | 50 | 2.0276 | 0.25 |
72
+ | No log | 6.0 | 60 | 2.0066 | 0.3063 |
73
+ | No log | 7.0 | 70 | 1.9779 | 0.3 |
74
+ | No log | 8.0 | 80 | 1.9538 | 0.3063 |
75
+ | No log | 9.0 | 90 | 1.9229 | 0.325 |
76
+ | No log | 10.0 | 100 | 1.8739 | 0.3563 |
77
+ | No log | 11.0 | 110 | 1.8404 | 0.3375 |
78
+ | No log | 12.0 | 120 | 1.7943 | 0.3688 |
79
+ | No log | 13.0 | 130 | 1.7616 | 0.35 |
80
+ | No log | 14.0 | 140 | 1.7186 | 0.3937 |
81
+ | No log | 15.0 | 150 | 1.6926 | 0.4062 |
82
+ | No log | 16.0 | 160 | 1.6778 | 0.4062 |
83
+ | No log | 17.0 | 170 | 1.6579 | 0.4062 |
84
+ | No log | 18.0 | 180 | 1.6462 | 0.4 |
85
+ | No log | 19.0 | 190 | 1.6143 | 0.4188 |
86
+ | No log | 20.0 | 200 | 1.5932 | 0.4313 |
87
+ | No log | 21.0 | 210 | 1.5833 | 0.4625 |
88
+ | No log | 22.0 | 220 | 1.5726 | 0.4437 |
89
+ | No log | 23.0 | 230 | 1.5545 | 0.4188 |
90
+ | No log | 24.0 | 240 | 1.5220 | 0.4688 |
91
+ | No log | 25.0 | 250 | 1.5237 | 0.4188 |
92
+ | No log | 26.0 | 260 | 1.5175 | 0.4375 |
93
+ | No log | 27.0 | 270 | 1.5008 | 0.4 |
94
+ | No log | 28.0 | 280 | 1.5100 | 0.4875 |
95
+ | No log | 29.0 | 290 | 1.4730 | 0.4938 |
96
+ | No log | 30.0 | 300 | 1.4842 | 0.5125 |
97
+ | No log | 31.0 | 310 | 1.4967 | 0.45 |
98
+ | No log | 32.0 | 320 | 1.4584 | 0.4562 |
99
+ | No log | 33.0 | 330 | 1.4458 | 0.4813 |
100
+ | No log | 34.0 | 340 | 1.4850 | 0.475 |
101
+ | No log | 35.0 | 350 | 1.4558 | 0.4688 |
102
+ | No log | 36.0 | 360 | 1.4438 | 0.5 |
103
+ | No log | 37.0 | 370 | 1.4290 | 0.475 |
104
+ | No log | 38.0 | 380 | 1.4347 | 0.4938 |
105
+ | No log | 39.0 | 390 | 1.4283 | 0.4437 |
106
+ | No log | 40.0 | 400 | 1.4149 | 0.4813 |
107
+ | No log | 41.0 | 410 | 1.3983 | 0.4813 |
108
+ | No log | 42.0 | 420 | 1.4079 | 0.45 |
109
+ | No log | 43.0 | 430 | 1.3984 | 0.45 |
110
+ | No log | 44.0 | 440 | 1.3866 | 0.5 |
111
+ | No log | 45.0 | 450 | 1.3809 | 0.4875 |
112
+ | No log | 46.0 | 460 | 1.3858 | 0.4813 |
113
+ | No log | 47.0 | 470 | 1.3981 | 0.4875 |
114
+ | No log | 48.0 | 480 | 1.3822 | 0.4813 |
115
+ | No log | 49.0 | 490 | 1.3728 | 0.4437 |
116
+ | 1.4038 | 50.0 | 500 | 1.3828 | 0.45 |
117
+ | 1.4038 | 51.0 | 510 | 1.3842 | 0.4813 |
118
+ | 1.4038 | 52.0 | 520 | 1.3460 | 0.4688 |
119
+ | 1.4038 | 53.0 | 530 | 1.3513 | 0.4938 |
120
+ | 1.4038 | 54.0 | 540 | 1.3645 | 0.4875 |
121
+ | 1.4038 | 55.0 | 550 | 1.3273 | 0.5062 |
122
+ | 1.4038 | 56.0 | 560 | 1.3470 | 0.525 |
123
+ | 1.4038 | 57.0 | 570 | 1.4006 | 0.45 |
124
+ | 1.4038 | 58.0 | 580 | 1.3259 | 0.5312 |
125
+ | 1.4038 | 59.0 | 590 | 1.3030 | 0.5062 |
126
+ | 1.4038 | 60.0 | 600 | 1.3526 | 0.5125 |
127
+ | 1.4038 | 61.0 | 610 | 1.3665 | 0.4625 |
128
+ | 1.4038 | 62.0 | 620 | 1.3689 | 0.4813 |
129
+ | 1.4038 | 63.0 | 630 | 1.3139 | 0.4813 |
130
+ | 1.4038 | 64.0 | 640 | 1.3618 | 0.4875 |
131
+ | 1.4038 | 65.0 | 650 | 1.3596 | 0.4938 |
132
+ | 1.4038 | 66.0 | 660 | 1.3360 | 0.4813 |
133
+ | 1.4038 | 67.0 | 670 | 1.3201 | 0.5062 |
134
+ | 1.4038 | 68.0 | 680 | 1.3615 | 0.5 |
135
+ | 1.4038 | 69.0 | 690 | 1.3335 | 0.5062 |
136
+ | 1.4038 | 70.0 | 700 | 1.2843 | 0.5687 |
137
+ | 1.4038 | 71.0 | 710 | 1.3697 | 0.4813 |
138
+ | 1.4038 | 72.0 | 720 | 1.2891 | 0.5188 |
139
+ | 1.4038 | 73.0 | 730 | 1.3355 | 0.5 |
140
+ | 1.4038 | 74.0 | 740 | 1.3400 | 0.4813 |
141
+ | 1.4038 | 75.0 | 750 | 1.3140 | 0.4938 |
142
+ | 1.4038 | 76.0 | 760 | 1.3492 | 0.4688 |
143
+ | 1.4038 | 77.0 | 770 | 1.2946 | 0.5188 |
144
+ | 1.4038 | 78.0 | 780 | 1.3635 | 0.45 |
145
+ | 1.4038 | 79.0 | 790 | 1.3224 | 0.5 |
146
+ | 1.4038 | 80.0 | 800 | 1.3092 | 0.525 |
147
+ | 1.4038 | 81.0 | 810 | 1.3298 | 0.475 |
148
+ | 1.4038 | 82.0 | 820 | 1.3626 | 0.4562 |
149
+ | 1.4038 | 83.0 | 830 | 1.3028 | 0.5375 |
150
+ | 1.4038 | 84.0 | 840 | 1.3025 | 0.5375 |
151
+ | 1.4038 | 85.0 | 850 | 1.3433 | 0.5188 |
152
+ | 1.4038 | 86.0 | 860 | 1.2508 | 0.5437 |
153
+ | 1.4038 | 87.0 | 870 | 1.3074 | 0.5062 |
154
+ | 1.4038 | 88.0 | 880 | 1.3227 | 0.4875 |
155
+ | 1.4038 | 89.0 | 890 | 1.3069 | 0.5188 |
156
+ | 1.4038 | 90.0 | 900 | 1.3278 | 0.4875 |
157
+ | 1.4038 | 91.0 | 910 | 1.3475 | 0.4875 |
158
+ | 1.4038 | 92.0 | 920 | 1.3310 | 0.4875 |
159
+ | 1.4038 | 93.0 | 930 | 1.3015 | 0.5062 |
160
+ | 1.4038 | 94.0 | 940 | 1.3635 | 0.4875 |
161
+ | 1.4038 | 95.0 | 950 | 1.3610 | 0.475 |
162
+ | 1.4038 | 96.0 | 960 | 1.2927 | 0.525 |
163
+ | 1.4038 | 97.0 | 970 | 1.3346 | 0.475 |
164
+ | 1.4038 | 98.0 | 980 | 1.3628 | 0.4625 |
165
+ | 1.4038 | 99.0 | 990 | 1.3301 | 0.4813 |
166
+ | 0.8016 | 100.0 | 1000 | 1.3301 | 0.475 |
167
 
168
 
169
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1708132cfdef78afde75edf3f47c87137bee29839004b8e1f55898be610b324d
3
  size 343287149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ebe4bcc4d899cc85cd7cc8652f3282728f1279cd7ce8d1b451573ee103ff1f6
3
  size 343287149