unlearn_cifar100_swin-base_salun_4_87

jialicheng/unlearn_cifar100_swin-base_salun_4_87

unlearn_cifar100_swin-base_salun_4_87 is a image classification model from jialicheng. Use it when you need a label for an image. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

4% of all-time downloads

All-time downloads

Public

Parameters

86.9M

1.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt695 MB · 65%

Parameter types

How the weights are stored.

F3286.8M · 100%

Base models

microsoft/swin-base-patch4-window7-224

Model card

From the Hugging Face model README

87

This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the cifar100 dataset. It achieves the following results on the evaluation set:

Loss: 0.3886
Accuracy: 0.9078
Dt Accuracy: 0.9078
Df Accuracy: 0.1775
Unlearn Overall Accuracy: 0.8993
Unlearn Time: None

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: 0.0002
train_batch_size: 128
eval_batch_size: 256
seed: 87
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
No log	1.0	391	0.4379	0.7805	0.3698	0.3698	None
1.1499	2.0	782	0.4373	0.762	0.3935	0.3935	None
0.9943	3.0	1173	0.4099	0.7775	0.3745	0.3745	None
0.9059	4.0	1564	0.4158	0.7575	0.4000	0.4000	None
0.9059	5.0	1955	0.4009	0.7445	0.4165	0.4165	None
0.8207	6.0	2346	0.4035	0.702	0.4670	0.4670	None
0.7303	7.0	2737	0.4019	0.6665	0.5065	0.5065	None
0.6821	8.0	3128	0.4369	0.597	0.5771	0.5771	None
0.6317	9.0	3519	0.4289	0.542	0.6299	0.6299	None
0.6317	10.0	3910	0.4187	0.5055	0.6629	0.6629	None
0.5746	11.0	4301	0.4064	0.4875	0.6790	0.6790	None
0.5297	12.0	4692	0.4135	0.4025	0.7454	0.7454	None
0.4889	13.0	5083	0.4244	0.327	0.8001	0.8001	None
0.4889	14.0	5474	0.4162	0.3075	0.8132	0.8132	None
0.4439	15.0	5865	0.4161	0.2795	0.8328	0.8328	None
0.4123	16.0	6256	0.3959	0.238	0.8601	0.8601	None
0.3922	17.0	6647	0.3945	0.2305	0.8660	0.8660	None
0.3637	18.0	7038	0.3955	0.2	0.8847	0.8847	None
0.3637	19.0	7429	0.3861	0.202	0.8845	0.8845	None
0.3396	20.0	7820	0.3886	0.1775	0.8993	0.8993	None

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.18.0
Tokenizers 0.15.2

Task: Image Classification
Type: swin
License: apache-2.0
Created: Oct 22, 2025
Updated: Oct 22, 2025