Downloads · 30 days
5
1% of all-time downloads
phuong-tk-nguyen/swin-base-patch4-window7-224-in22k-newly-trained
swin-base-patch4-window7-224-in22k-newly-trained is a image classification model from phuong-tk-nguyen. 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
5
1% of all-time downloads
All-time downloads
629
Public
Parameters
86.8M
348 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors348 MB · 100%
How the weights are stored.
F3286.8M · 100%
From the Hugging Face model README
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224-in22k on the imagefolder 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 |
|---|---|---|---|---|
| 2.2459 | 0.14 | 10 | 1.7346 | 0.575 |
| 1.4338 | 0.28 | 20 | 0.7222 | 0.841 |
| 0.8059 | 0.43 | 30 | 0.3252 | 0.915 |
| 0.5772 | 0.57 | 40 | 0.2071 | 0.942 |
| 0.5599 | 0.71 | 50 | 0.1553 | 0.958 |
| 0.4473 | 0.85 | 60 | 0.1373 | 0.958 |
| 0.4292 | 0.99 | 70 | 0.1335 | 0.959 |