mruby/reef_classifier_5

1---2license: apache-2.03tags:4- generated_from_keras_callback5model-index:6- name: mruby/reef_classifier_57  results: []8---9 10<!-- This model card has been generated automatically according to the information Keras had access to. You should11probably proofread and complete it, then remove this comment. -->12 13# mruby/reef_classifier_514 15This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on an unknown dataset.16It achieves the following results on the evaluation set:17- Train Loss: 0.215518- Validation Loss: 0.212119- Train Accuracy: 0.925920- Epoch: 421 22## Model description23 24More information needed25 26## Intended uses & limitations27 28More information needed29 30## Training and evaluation data31 32More information needed33 34## Training procedure35 36### Training hyperparameters37 38The following hyperparameters were used during training:39- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 18885, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}40- training_precision: float3241 42### Training results43 44| Train Loss | Validation Loss | Train Accuracy | Epoch |45|:----------:|:---------------:|:--------------:|:-----:|46| 0.6147     | 0.5483          | 0.7640         | 0     |47| 0.4143     | 0.3372          | 0.9122         | 1     |48| 0.2795     | 0.2246          | 0.9323         | 2     |49| 0.2336     | 0.2087          | 0.9280         | 3     |50| 0.2155     | 0.2121          | 0.9259         | 4     |51 52 53### Framework versions54 55- Transformers 4.27.456- TensorFlow 2.8.057- Datasets 2.12.058- Tokenizers 0.13.359