Hugging Face's logo

hbenitez
/
AV_classifier_resnet50

Image Classification
Transformers
TensorFlow
resnet
generated_from_keras_callback
Inference Endpoints
Model card Files Community
AV_classifier_resnet50 / README.md
hbenitez's picture
hbenitez
End of training
b0aae72
preview code
|
raw
history blame
7.37 kB
metadata
license: apache-2.0
tags:
  - generated_from_keras_callback
model-index:
  - name: hbenitez/AV_classifier_resnet50
    results: []

hbenitez/AV_classifier_resnet50

This model is a fine-tuned version of microsoft/resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.8261
  • Validation Loss: 2.4425
  • Train Accuracy: 0.6
  • Epoch: 99

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 8000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: float32

Training results

Train Loss Validation Loss Train Accuracy Epoch
8.2326 8.1060 0.0 0
8.3420 7.6394 0.05 1
7.9643 7.5706 0.05 2
7.9337 7.6265 0.05 3
7.8018 7.7736 0.05 4
7.8009 7.7905 0.05 5
7.6369 7.6354 0.05 6
7.4782 7.5608 0.05 7
7.3655 7.6271 0.05 8
7.2886 7.6028 0.0 9
7.1145 7.5211 0.0 10
7.1232 7.2993 0.0 11
6.8393 7.2079 0.0 12
6.8202 7.2143 0.0 13
6.7180 7.1236 0.05 14
6.7318 7.1061 0.0 15
6.4563 6.9758 0.05 16
6.3765 6.9413 0.05 17
6.1791 6.8315 0.05 18
6.1946 6.7703 0.05 19
5.8448 6.7431 0.1 20
5.8514 6.6876 0.1 21
5.8200 6.6353 0.05 22
5.8323 6.5814 0.05 23
5.5553 6.4306 0.05 24
5.4999 6.4455 0.05 25
5.4370 6.3026 0.05 26
5.2288 6.0093 0.1 27
5.2173 6.0593 0.05 28
5.2280 6.0598 0.05 29
5.0484 5.9769 0.05 30
4.8703 5.8336 0.05 31
4.9881 5.7711 0.1 32
4.5905 5.6685 0.1 33
4.7240 5.6156 0.15 34
4.5095 5.4680 0.15 35
4.2225 5.3962 0.15 36
4.3615 5.3290 0.2 37
4.1862 5.3602 0.15 38
3.9455 5.2635 0.15 39
3.9737 5.2337 0.15 40
4.0922 5.1268 0.15 41
3.6042 4.9972 0.2 42
3.7219 4.8787 0.15 43
3.5563 4.9075 0.2 44
3.5897 4.9157 0.25 45
3.5769 4.7936 0.25 46
3.6225 4.8689 0.2 47
3.4568 4.8767 0.2 48
3.1431 4.7520 0.25 49
3.0607 4.5815 0.3 50
2.8904 4.5007 0.2 51
2.8308 4.5054 0.25 52
2.8136 4.2745 0.25 53
2.6192 4.3300 0.2 54
2.5308 4.3180 0.2 55
2.5192 4.2706 0.2 56
2.5761 4.1395 0.25 57
2.3516 3.9031 0.3 58
2.3231 3.8172 0.35 59
2.2735 3.7651 0.35 60
2.1215 3.8034 0.35 61
2.3229 3.8096 0.35 62
2.2230 3.7000 0.35 63
1.9059 3.6666 0.25 64
2.0289 3.6743 0.25 65
1.9178 3.5819 0.3 66
2.0295 3.5087 0.35 67
1.6499 3.4962 0.4 68
1.6261 3.4146 0.3 69
1.7059 3.4097 0.35 70
1.4837 3.2702 0.35 71
1.3766 3.2214 0.4 72
1.5898 3.2674 0.4 73
1.5002 3.1907 0.4 74
1.2641 3.1176 0.4 75
1.3456 3.1562 0.4 76
1.2655 2.9548 0.5 77
1.5449 2.8738 0.5 78
1.2519 2.8336 0.45 79
1.0682 2.8478 0.35 80
1.1891 2.8408 0.5 81
1.2920 2.6254 0.5 82
1.1239 2.7507 0.5 83
1.0857 2.7772 0.4 84
0.9821 2.8372 0.45 85
1.0457 2.8636 0.45 86
1.1419 2.8426 0.45 87
1.0782 2.7856 0.5 88
0.9906 2.6826 0.55 89
1.0766 2.6707 0.5 90
1.1115 2.6457 0.5 91
1.2201 2.6838 0.55 92
0.8706 2.5262 0.55 93
0.7441 2.5422 0.55 94
0.9710 2.4211 0.6 95
0.9731 2.4090 0.6 96
0.8942 2.3773 0.6 97
1.0461 2.4159 0.55 98
0.8261 2.4425 0.6 99

Framework versions

  • Transformers 4.30.2
  • TensorFlow 2.13.0-rc2
  • Datasets 2.13.1
  • Tokenizers 0.13.3