Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
vit-convnext-tiny-224-eurosat – AI Model by polejowska | AlphaNeural AI
You can deploy this model and start earning money today!
polejowska
/
vit-convnext-tiny-224-eurosat
like
0
transformers
pytorch
convnext
image-classification
generated_from_trainer
imagefolder
apache-2.0
model-index
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
vit-convnext-tiny-224-eurosat
This model is a fine-tuned version of
facebook/convnext-tiny-224
on the imagefolder dataset. It achieves the following results on the evaluation set:
Loss: 0.0576
Accuracy: 0.9859
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: 5
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
0.2881
0.99
147
0.2325
0.9588
0.0869
1.99
294
0.0912
0.9753
0.0687
2.99
441
0.0663
0.9805
0.0272
3.99
588
0.0576
0.9859
0.0247
4.99
735
0.0532
0.9854
Framework versions
Transformers 4.25.1
Pytorch 1.13.0+cu116
Datasets 2.7.1
Tokenizers 0.13.2
