swinv2-tiny-patch4-window8-256-dmae-humeda-DAV58

RobertoSonic/swinv2-tiny-patch4-window8-256-dmae-humeda-DAV58

swinv2-tiny-patch4-window8-256-dmae-humeda-DAV58 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

4% of all-time downloads

All-time downloads

271

Public

Parameters

27.6M

4.9 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: Feb 10, 2025
Updated: Feb 10, 2025
SHA: fc4cfa0b

Base models

microsoft/swinv2-tiny-patch4-window8-256

Model card

From the Hugging Face model README

swinv2-tiny-patch4-window8-256-dmae-humeda-DAV58

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: 0.8236
Accuracy: 0.7308

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 45
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.8421	4	1.5015	0.4423
No log	1.8421	8	1.4596	0.4231
1.7006	2.8421	12	1.3454	0.5192
1.7006	3.8421	16	1.2081	0.5577
1.7006	4.8421	20	1.0746	0.5577
1.3198	5.8421	24	0.9099	0.5962
1.3198	6.8421	28	0.8862	0.6346
1.3198	7.8421	32	0.8236	0.7308
0.86	8.8421	36	0.8757	0.6154
0.86	9.8421	40	0.8234	0.7115
0.86	10.8421	44	0.8238	0.7115
0.6765	11.8421	48	0.9140	0.6538
0.6765	12.8421	52	0.8608	0.6731
0.6765	13.8421	56	0.8913	0.6538
0.5549	14.8421	60	0.8184	0.7115
0.5549	15.8421	64	0.8233	0.7308
0.5549	16.8421	68	0.8051	0.7308
0.4803	17.8421	72	0.8256	0.7115
0.4803	18.8421	76	0.8907	0.6731
0.4803	19.8421	80	0.9122	0.7115
0.3757	20.8421	84	0.8812	0.7115
0.3757	21.8421	88	0.9496	0.7308
0.3757	22.8421	92	0.9228	0.7115
0.3166	23.8421	96	0.9533	0.6538
0.3166	24.8421	100	0.9486	0.6731
0.3166	25.8421	104	0.9961	0.6731
0.2869	26.8421	108	0.9953	0.6538
0.2869	27.8421	112	0.9716	0.7308
0.2869	28.8421	116	0.9851	0.7115
0.2901	29.8421	120	1.0567	0.6731
0.2901	30.8421	124	1.0905	0.7308
0.2901	31.8421	128	1.0009	0.6731
0.2548	32.8421	132	1.0158	0.6538
0.2548	33.8421	136	1.0908	0.7308
0.2548	34.8421	140	1.0802	0.6538
0.2359	35.8421	144	1.0642	0.6346
0.2359	36.8421	148	1.1139	0.6538
0.2359	37.8421	152	1.0740	0.6731
0.2295	38.8421	156	1.0772	0.7115
0.2295	39.8421	160	1.0724	0.6731
0.2295	40.8421	164	1.0859	0.6731
0.2234	41.8421	168	1.0928	0.6923
0.2234	42.8421	172	1.0850	0.6923
0.2234	43.8421	176	1.0761	0.6923
0.2086	44.8421	180	1.0766	0.6731

Framework versions

Transformers 4.48.2
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0

Task: Image Classification
Library: transformers
Type: swinv2
License: apache-2.0
Created: Feb 10, 2025
Updated: Feb 10, 2025