You can deploy this model and start earning money today!

AdityasArsenal/
finetuned-for-YogaPosesv4

Name: finetuned-for-YogaPosesv4
Availability: InStock

generated_from_trainer

google/mobilenet_v2_1.0_224

finetune

other

endpoints_compatible

Views

No views yet

finetuned-for-YogaPosesv4

This model is a fine-tuned version of google/mobilenet_v2_1.0_224 on the yoga_pose_images dataset. It achieves the following results on the evaluation set:

Loss: 0.0743
Accuracy: 0.9907

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: 16
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 12
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0434	0.8772	100	0.1421	0.9595
0.033	1.7544	200	0.0880	0.9875
0.084	2.6316	300	0.0919	0.9844
0.0655	3.5088	400	0.0932	0.9875
0.0126	4.3860	500	0.0696	0.9875
0.0487	5.2632	600	0.0847	0.9720
0.0114	6.1404	700	0.1103	0.9813
0.0377	7.0175	800	0.0743	0.9907
0.062	7.8947	900	0.1642	0.9782
0.0025	8.7719	1000	0.0598	0.9875
0.0041	9.6491	1100	0.1280	0.9813
0.0305	10.5263	1200	0.0920	0.9813
0.0148	11.4035	1300	0.1209	0.9875

Framework versions

Transformers 4.46.3
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3

AdityasArsenal/finetuned-for-YogaPosesv4

finetuned-for-YogaPosesv4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

AdityasArsenal/
finetuned-for-YogaPosesv4