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: 30.5625
Map: 0.2089
Map 50: 0.4081
Map 75: 0.1963
Map Small: 0.1412
Map Medium: 0.6277
Map Large: 0.8115
Mar 1: 0.0944
Mar 10: 0.25
Mar 100: 0.2879
Mar Small: 0.2137
Mar Medium: 0.7147
Mar Large: 0.8531
Map Person: 0.1381
Mar 100 Person: 0.2036
Map Car: 0.2797
Mar 100 Car: 0.3722

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
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
num_epochs: 2.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Map	Map 50	Map 75	Map Small	Map Medium	Map Large	Mar 1	Mar 10	Mar 100	Mar Small	Mar Medium	Mar Large	Map Person	Mar 100 Person	Map Car	Mar 100 Car
34.1337	1.0	100	32.3431	0.1958	0.3913	0.181	0.1319	0.6051	0.7775	0.0924	0.2465	0.2845	0.2104	0.7094	0.8587	0.1243	0.2001	0.2673	0.3689
28.4514	2.0	200	30.5625	0.2089	0.4081	0.1963	0.1412	0.6277	0.8115	0.0944	0.25	0.2879	0.2137	0.7147	0.8531	0.1381	0.2036	0.2797	0.3722

Framework versions

Transformers 4.47.0.dev0
Pytorch 2.3.1+cu121
Datasets 3.0.2
Tokenizers 0.20.1

amnraw/finetune-instance-segmentation-posture

finetune-instance-segmentation-posture

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

amnraw/
finetune-instance-segmentation-posture