unlearn_cifar100_swin-base_salun_6_87

jialicheng/unlearn_cifar100_swin-base_salun_6_87

unlearn_cifar100_swin-base_salun_6_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

3% 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: 0.4085
Accuracy: 0.8986
Dt Accuracy: 0.8986
Df Accuracy: 0.181
Unlearn Overall Accuracy: 0.8933
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	0.4644	0.7567	0.3997	0.3997	None
1.2191	2.0	782	0.4517	0.7757	0.3762	0.3762	None
1.0422	3.0	1173	0.4464	0.762	0.3936	0.3936	None
0.957	4.0	1564	0.4284	0.7643	0.3911	0.3911	None
0.957	5.0	1955	0.4414	0.74	0.4212	0.4212	None
0.8645	6.0	2346	0.4284	0.7053	0.4628	0.4628	None
0.7948	7.0	2737	0.4500	0.6687	0.5030	0.5030	None
0.7387	8.0	3128	0.4367	0.605	0.5698	0.5698	None
0.6704	9.0	3519	0.4417	0.564	0.6089	0.6089	None
0.6704	10.0	3910	0.4513	0.4847	0.6789	0.6789	None
0.6087	11.0	4301	0.4567	0.462	0.6966	0.6966	None
0.5658	12.0	4692	0.4552	0.3947	0.7488	0.7488	None
0.5189	13.0	5083	0.4431	0.3567	0.7760	0.7760	None
0.5189	14.0	5474	0.4482	0.283	0.8261	0.8261	None
0.4829	15.0	5865	0.4426	0.2557	0.8441	0.8441	None
0.4438	16.0	6256	0.4309	0.24	0.8551	0.8551	None
0.4128	17.0	6647	0.4218	0.2277	0.8638	0.8638	None
0.3889	18.0	7038	0.4209	0.1967	0.8820	0.8820	None
0.3889	19.0	7429	0.4116	0.189	0.8880	0.8880	None
0.3609	20.0	7820	0.4085	0.181	0.8933	0.8933	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