efficientnet_b1-food101
This model is a fine-tuned version of google/efficientnet-b1 on food101 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0490
- Accuracy: 0.9947
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:
- learning_rate: 0.0002
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 47 | 4.3674 | 0.1548 |
| No log | 2.0 | 94 | 3.1870 | 0.8915 |
| No log | 3.0 | 141 | 0.8758 | 0.9751 |
| No log | 4.0 | 188 | 0.1010 | 0.9858 |
| No log | 5.0 | 235 | 0.0503 | 0.9893 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 326
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for gabrielganan/efficientnet_b1-food101
Base model
google/efficientnet-b1