Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mobilevit-small-finetuned-eurosat – AI Model by loucad | AlphaNeural AI
You can deploy this model and start earning money today!
loucad
/
mobilevit-small-finetuned-eurosat
like
0
transformers
pytorch
mobilevit
image-classification
generated_from_trainer
imagefolder
apple/mobilevit-small
finetune
other
model-index
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
mobilevit-small-finetuned-eurosat
This model is a fine-tuned version of
apple/mobilevit-small
on the imagefolder dataset. It achieves the following results on the evaluation set:
Loss: 0.3838
Accuracy: 0.9189
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: 3
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
1.065
1.0
190
0.8779
0.8385
0.636
2.0
380
0.4618
0.9011
0.5761
3.0
570
0.3838
0.9189
Framework versions
Transformers 4.31.0
Pytorch 2.0.1+cu117
Datasets 2.14.1
Tokenizers 0.13.3
