Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
swin-base-patch4-window7-224-in22k-finetuned-eurosat – AI Model by erikejw | AlphaNeural AI
You can deploy this model and start earning money today!
erikejw
/
swin-base-patch4-window7-224-in22k-finetuned-eurosat
like
0
transformers
pytorch
tensorboard
swin
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
swin-base-patch4-window7-224-in22k-finetuned-eurosat
This model is a fine-tuned version of
microsoft/swin-base-patch4-window7-224-in22k
on the imagefolder dataset. It achieves the following results on the evaluation set:
Loss: 0.0390
Accuracy: 0.9896
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
0.1691
1.0
190
0.0693
0.9789
0.1275
2.0
380
0.0419
0.9889
0.1165
3.0
570
0.0390
0.9896
Framework versions
Transformers 4.21.3
Pytorch 1.12.1+cu113
Datasets 2.4.0
Tokenizers 0.12.1
