finetune-instance-segmentation-ade20k-mini-mask2former_backbone_frozen_1

This model is a fine-tuned version of facebook/mask2former-swin-tiny-coco-instance on the yeray142/kitti-mots-instance dataset. It achieves the following results on the evaluation set:

• Loss: 22.5821
• Map: 0.181
• Map 50: 0.35
• Map 75: 0.164
• Map Small: 0.0954
• Map Medium: 0.3758
• Map Large: 0.9135
• Mar 1: 0.0856
• Mar 10: 0.2359
• Mar 100: 0.2819
• Mar Small: 0.2158
• Mar Medium: 0.4688
• Mar Large: 0.9371
• Map Car: 0.3473
• Mar 100 Car: 0.4911
• Map Person: 0.0147
• Mar 100 Person: 0.0727

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 OptimizerNames.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: 10.0
• 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 Car	Mar 100 Car	Map Person	Mar 100 Person
36.0195	1.0	315	27.1721	0.1432	0.279	0.1349	0.0688	0.3117	0.8516	0.0714	0.1887	0.2291	0.1605	0.4115	0.9133	0.2849	0.4372	0.0014	0.0209
28.6156	2.0	630	25.2879	0.1597	0.2996	0.1521	0.0779	0.337	0.8789	0.078	0.2055	0.2497	0.1825	0.4386	0.9173	0.3147	0.4628	0.0046	0.0367
26.5961	3.0	945	24.4641	0.1679	0.3171	0.1572	0.0817	0.3481	0.8921	0.0809	0.2137	0.259	0.193	0.4441	0.9229	0.326	0.473	0.0098	0.045
25.435	4.0	1260	24.1017	0.1701	0.3217	0.1577	0.0815	0.3562	0.9002	0.0816	0.2169	0.2601	0.1929	0.4479	0.9272	0.329	0.469	0.0112	0.0512
24.7221	5.0	1575	23.5551	0.1738	0.3286	0.162	0.0855	0.3615	0.8986	0.0833	0.2226	0.2717	0.2053	0.462	0.9276	0.3357	0.4836	0.0119	0.0597
24.1639	6.0	1890	23.3457	0.1761	0.3319	0.1641	0.0891	0.3606	0.9016	0.0838	0.2249	0.267	0.2003	0.4539	0.9265	0.3412	0.4749	0.0111	0.059
23.581	7.0	2205	23.0218	0.1801	0.3415	0.1687	0.0924	0.3682	0.9111	0.0854	0.2295	0.2735	0.2061	0.4619	0.9356	0.3475	0.4829	0.0126	0.064
23.1336	8.0	2520	22.8133	0.1817	0.3458	0.1673	0.0959	0.3723	0.9122	0.0852	0.234	0.2782	0.2108	0.4682	0.9352	0.3507	0.4868	0.0127	0.0697
22.6498	9.0	2835	22.8115	0.1823	0.3478	0.1683	0.0948	0.3758	0.9137	0.0856	0.2347	0.2818	0.2148	0.4691	0.9358	0.3508	0.4884	0.0139	0.0751
22.3868	9.9698	3140	22.5821	0.181	0.35	0.164	0.0954	0.3758	0.9135	0.0856	0.2359	0.2819	0.2158	0.4688	0.9371	0.3473	0.4911	0.0147	0.0727

Framework versions

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