swinv2-tiny-patch4-window8-256-dmae-humeda-DA

RobertoSonic/swinv2-tiny-patch4-window8-256-dmae-humeda-DA

swinv2-tiny-patch4-window8-256-dmae-humeda-DA is a image classification model from RobertoSonic. 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

9% of all-time downloads

All-time downloads

Public

Parameters

27.6M

3.6 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors110 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: swinv2
Access: Public
Created: Jul 3, 2024
Updated: Jul 3, 2024
SHA: 7f314491

Base models

microsoft/swinv2-tiny-patch4-window8-256

Model card

From the Hugging Face model README

swinv2-tiny-patch4-window8-256-dmae-humeda-DA

This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.9032
Accuracy: 0.7692

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: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.8421	4	1.6342	0.1346
No log	1.8947	9	1.5368	0.2692
1.5734	2.9474	14	1.3871	0.4808
1.5734	4.0	19	1.2443	0.5192
1.3253	4.8421	23	1.1185	0.5577
1.3253	5.8947	28	1.0374	0.5962
1.044	6.9474	33	0.9798	0.6346
1.044	8.0	38	0.9702	0.6731
0.8487	8.8421	42	0.9567	0.6538
0.8487	9.8947	47	0.9292	0.6538
0.7359	10.9474	52	0.9042	0.6923
0.7359	12.0	57	0.9032	0.7692
0.6592	12.8421	61	0.9060	0.6538
0.6592	13.8947	66	0.9208	0.6538
0.6257	14.9474	71	0.9272	0.6923
0.6257	16.0	76	1.0044	0.6731
0.5927	16.8421	80	0.9176	0.7308
0.5927	17.8947	85	0.9261	0.75
0.5255	18.9474	90	0.9058	0.6538
0.5255	20.0	95	0.9338	0.75
0.5255	20.8421	99	0.9103	0.6923
0.5098	21.8947	104	0.9329	0.75
0.5098	22.9474	109	0.9886	0.75
0.4347	24.0	114	0.9331	0.7308
0.4347	24.8421	118	1.0086	0.6923
0.4269	25.8947	123	1.0184	0.7308
0.4269	26.9474	128	0.9698	0.7115
0.42	28.0	133	0.9873	0.6923
0.42	28.8421	137	0.9996	0.6923
0.4239	29.8947	142	0.9858	0.6923
0.4239	30.9474	147	0.9964	0.7308
0.3713	32.0	152	1.0338	0.7115
0.3713	32.8421	156	1.0474	0.6923
0.4133	33.6842	160	1.0444	0.6923

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Task: Image Classification
Library: transformers
Type: swinv2
License: apache-2.0
Created: Jul 3, 2024
Updated: Jul 3, 2024