Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mit-b0-finetuned-eurosat – AI Model by Chandanab | AlphaNeural AI
You can deploy this model and start earning money today!
Chandanab
/
mit-b0-finetuned-eurosat
like
0
transformers
pytorch
segformer
image-classification
generated_from_trainer
image_folder
other
model-index
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
mit-b0-finetuned-eurosat
This model is a fine-tuned version of
nvidia/mit-b0
on the image_folder dataset. It achieves the following results on the evaluation set:
Loss: 0.1782
Accuracy: 0.9495
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
1.0
7
0.3828
0.8081
0.4864
2.0
14
0.2224
0.9192
0.2035
3.0
21
0.1782
0.9495
Framework versions
Transformers 4.17.0
Pytorch 1.11.0+cpu
Datasets 2.2.0
Tokenizers 0.12.1
