segformer-webots-grasp

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

segformer-webots-grasp

This model is a fine-tuned version of nvidia/mit-b0 on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 2.6628
• eval_mean_iou: 0.8546
• eval_mean_accuracy: 0.8633
• eval_overall_accuracy: 0.8633
• eval_per_category_iou: [0.8545649439735425, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
• eval_per_category_accuracy: [0.8632884477610067, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
• eval_runtime: 53.0339
• eval_samples_per_second: 0.396
• eval_steps_per_second: 0.207
• epoch: 2.6
• step: 104

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: 6e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0