Downloads · 30 days
28
3% of all-time downloads
resnet-18-finetuned-wikiart
Iust1n2/resnet-18-finetuned-wikiart
resnet-18-finetuned-wikiart is a image classification model from Iust1n2. 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. --
All-time downloads
1K
Public
Parameters
11.3M
45 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors45 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- resnet
- Access
- Public
- Created
- Nov 22, 2023
- Updated
- Nov 24, 2023
- SHA
- 3a761439
Base models
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. -->
resnet-18-finetuned-wikiart
This model is a fine-tuned version of microsoft/resnet-18 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6256
- Accuracy: 0.6247
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0382 | 1.0 | 2037 | 1.8771 | 0.5938 |
| 1.8027 | 2.0 | 4074 | 1.6860 | 0.6160 |
| 1.7033 | 3.0 | 6111 | 1.6256 | 0.6247 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Image Classification
- Library
- transformers
- Type
- resnet
- License
- apache-2.0
- Created
- Nov 22, 2023
- Updated
- Nov 24, 2023