metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- food101
metrics:
- accuracy
model-index:
- name: swin-finetuned-food101
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: food101
type: food101
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9214257425742575
- task:
type: image-classification
name: Image Classification
dataset:
name: food101
type: food101
config: default
split: validation
metrics:
- name: Accuracy
type: accuracy
value: 0.9133861386138614
verified: true
- name: Precision Macro
type: precision
value: 0.9146993135465998
verified: true
- name: Precision Micro
type: precision
value: 0.9133861386138614
verified: true
- name: Precision Weighted
type: precision
value: 0.9146993135466
verified: true
- name: Recall Macro
type: recall
value: 0.9133861386138615
verified: true
- name: Recall Micro
type: recall
value: 0.9133861386138614
verified: true
- name: Recall Weighted
type: recall
value: 0.9133861386138614
verified: true
- name: F1 Macro
type: f1
value: 0.9136408807067767
verified: true
- name: F1 Micro
type: f1
value: 0.9133861386138614
verified: true
- name: F1 Weighted
type: f1
value: 0.9136408807067764
verified: true
- name: loss
type: loss
value: 0.30173271894454956
verified: true
swin-finetuned-food101
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the food101 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2779
- Accuracy: 0.9214
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5646 | 1.0 | 1183 | 0.3937 | 0.8861 |
0.3327 | 2.0 | 2366 | 0.3024 | 0.9124 |
0.1042 | 3.0 | 3549 | 0.2779 | 0.9214 |
Framework versions
- Transformers 4.20.0
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1