Downloads · 30 days
3
4% of all-time downloads
koh43/vit-base-patch16-224-in21k-img-cls-food101
vit-base-patch16-224-in21k-img-cls-food101 is a image classification model from koh43. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
3
4% of all-time downloads
All-time downloads
72
Public
Parameters
85.9M
344 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors344 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.2111 | 1.0 | 474 | 4.1964 | 0.4976 |
| 3.4128 | 2.0 | 948 | 3.4369 | 0.6442 |
| 2.9888 | 3.0 | 1422 | 2.9964 | 0.6857 |
| 2.6569 | 4.0 | 1896 | 2.6797 | 0.7069 |
| 2.4144 | 5.0 | 2370 | 2.4458 | 0.7263 |
| 2.2286 | 6.0 | 2844 | 2.2687 | 0.7339 |
| 2.1169 | 7.0 | 3318 | 2.1351 | 0.7432 |
| 2.0138 | 8.0 | 3792 | 2.0445 | 0.7510 |
| 1.9197 | 9.0 | 4266 | 2.0001 | 0.7525 |
| 1.8709 | 10.0 | 4740 | 1.9840 | 0.7451 |