qubvel-hf/finetune-instance-segmentation-ade20k-mini-mask2former-v1
015
<!-- 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-ade20k-mini-mask2former-v1
This model is a fine-tuned version of facebook/mask2former-swin-tiny-coco-instance on the qubvel-hf/ade20k-mini dataset. It achieves the following results on the evaluation set:
- Loss: 27.5494
- Map: 0.2315
- Map 50: 0.4495
- Map 75: 0.2185
- Map Small: 0.1535
- Map Medium: 0.6606
- Map Large: 0.8161
- Mar 1: 0.0981
- Mar 10: 0.2576
- Mar 100: 0.3
- Mar Small: 0.2272
- Mar Medium: 0.7189
- Mar Large: 0.8618
- Map Person: 0.1626
- Mar 100 Person: 0.2224
- Map Car: 0.3003
- Mar 100 Car: 0.3776
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: constant
- num_epochs: 40.0
- mixedprecisiontraining: Native AMP
Training results
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.18.0
- Tokenizers 0.19.1
