This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 1.2815
Accuracy: 0.5563

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: 0.0001
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	20	1.8308	0.375
No log	2.0	40	1.5510	0.4875
No log	3.0	60	1.4138	0.5062
No log	4.0	80	1.3845	0.4875
No log	5.0	100	1.3245	0.525
No log	6.0	120	1.2645	0.6
No log	7.0	140	1.2887	0.5188
No log	8.0	160	1.2395	0.5875
No log	9.0	180	1.2267	0.55
No log	10.0	200	1.1883	0.6

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3

kittendev/visual_emotional_analysis

visual_emotional_analysis

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

kittendev/
visual_emotional_analysis