Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
convnext-tiny-224-eurosat – AI Model by jinneer | AlphaNeural AI
You can deploy this model and start earning money today!
jinneer
/
convnext-tiny-224-eurosat
like
0
transformers
tensorboard
safetensors
convnext
image-classification
generated_from_trainer
imagefolder
facebook/convnext-tiny-224
finetune
apache-2.0
model-index
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
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: 1.6036
Accuracy: 1.0
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
No log
0.97
7
1.6036
1.0
1.8522
1.93
14
1.1066
1.0
1.12
2.9
21
0.9435
1.0
Framework versions
Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2
