Downloads · 30 days
6
1% of all-time downloads
vit-mlo-512-breat_composition
mm-ai/vit-mlo-512-breat_composition
vit-mlo-512-breat_composition is a image classification model from mm-ai. Use it when you need a label for an image. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
645
Public
Repo size
3.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin344 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- Model type
- vit
- Access
- Public
- Created
- Feb 28, 2023
- Updated
- Feb 28, 2023
- SHA
- c15ae009
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
vit-mlo-512-breat_composition
This model is a fine-tuned version of on the preprocessed1024_config dataset. It achieves the following results on the evaluation set:
- Loss: 1.3123
- Accuracy: {'accuracy': 0.5791457286432161}
- F1: {'f1': 0.5749067914290308}
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.2679 | 1.0 | 796 | 1.0281 | {'accuracy': 0.5062814070351759} | {'f1': 0.38950358034816535} |
| 0.9805 | 2.0 | 1592 | 0.9240 | {'accuracy': 0.5672110552763819} | {'f1': 0.5273112700912543} |
| 0.9167 | 3.0 | 2388 | 0.9608 | {'accuracy': 0.5477386934673367} | {'f1': 0.45736748568671376} |
| 0.8292 | 4.0 | 3184 | 0.8973 | {'accuracy': 0.5891959798994975} | {'f1': 0.5783349603036094} |
| 0.7695 | 5.0 | 3980 | 1.0477 | {'accuracy': 0.5571608040201005} | {'f1': 0.5379432393338944} |
| 0.6912 | 6.0 | 4776 | 0.9479 | {'accuracy': 0.585427135678392} | {'f1': 0.5766494177636581} |
| 0.61 | 7.0 | 5572 | 1.1280 | {'accuracy': 0.5703517587939698} | {'f1': 0.5560158679652624} |
| 0.5591 | 8.0 | 6368 | 1.1866 | {'accuracy': 0.5741206030150754} | {'f1': 0.5541999644498281} |
| 0.5021 | 9.0 | 7164 | 1.1537 | {'accuracy': 0.582286432160804} | {'f1': 0.566315815243799} |
| 0.4262 | 10.0 | 7960 | 1.3123 | {'accuracy': 0.5791457286432161} | {'f1': 0.5749067914290308} |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0
- Datasets 2.1.0
- Tokenizers 0.12.1
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- Created
- Feb 28, 2023
- Updated
- Feb 28, 2023