yeray142/finetune-instance-segmentation-mini-mask2former_augmentation_default

<!-- 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. -->

finetune-instance-segmentation-mini-mask2formeraugmentationdefault

This model is a fine-tuned version of facebook/mask2former-swin-tiny-coco-instance on the jsalavedra/strawberry_disease dataset. It achieves the following results on the evaluation set:

• —Loss: 16.2566
• —Map: 0.6229
• —Map 50: 0.8172
• —Map 75: 0.6824
• —Map Small: 0.35
• —Map Medium: 0.401
• —Map Large: 0.7146
• —Mar 1: 0.4279
• —Mar 10: 0.7886
• —Mar 100: 0.831
• —Mar Small: 0.5
• —Mar Medium: 0.7108
• —Mar Large: 0.8802
• —Map Angular leafspot: 0.54
• —Mar 100 Angular leafspot: 0.8135
• —Map Anthracnose fruit rot: 0.405
• —Mar 100 Anthracnose fruit rot: 0.7118
• —Map Blossom blight: 0.7372
• —Mar 100 Blossom blight: 0.8159
• —Map Gray mold: 0.5767
• —Mar 100 Gray mold: 0.7648
• —Map Leaf spot: 0.8783
• —Mar 100 Leaf spot: 0.9416
• —Map Powdery mildew fruit: 0.5019
• —Mar 100 Powdery mildew fruit: 0.8833
• —Map Powdery mildew leaf: 0.7209
• —Mar 100 Powdery mildew leaf: 0.8863

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: 1e-05
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 16
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: constant
• —num_epochs: 10.0
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.50.0.dev0
• —Pytorch 2.6.0+cu124
• —Datasets 3.3.2
• —Tokenizers 0.21.0