Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
segformer-b5-finetuned-ce-head-batch4 – AI Model by ypark-bioinfo | AlphaNeural AI
You can deploy this model and start earning money today!
ypark-bioinfo
/
segformer-b5-finetuned-ce-head-batch4
like
0
transformers
tensorboard
safetensors
segformer
generated_from_trainer
nvidia/mit-b5
finetune
other
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
segformer-b5-finetuned-ce-head-batch4
This model is a fine-tuned version of
nvidia/mit-b5
on the None dataset. It achieves the following results on the evaluation set:
eval_loss: 0.0871
eval_mean_iou: 0.7378
eval_mean_accuracy: 0.8916
eval_overall_accuracy: 0.9634
eval_accuracy_bg: 0.9710
eval_accuracy_head: 0.8121
eval_iou_bg: 0.9620
eval_iou_head: 0.5136
eval_runtime: 3.4796
eval_samples_per_second: 5.173
eval_steps_per_second: 2.586
epoch: 5.9706
step: 203
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: 7e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 30
Framework versions
Transformers 4.46.2
Pytorch 2.5.1
Datasets 3.1.0
Tokenizers 0.20.3
