finetune-instance-segmentation-mini-mask2former_augmentation_default

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
• 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 Angular leafspot	Mar 100 Angular leafspot	Map Anthracnose fruit rot	Mar 100 Anthracnose fruit rot	Map Blossom blight	Mar 100 Blossom blight	Map Gray mold	Mar 100 Gray mold	Map Leaf spot	Mar 100 Leaf spot	Map Powdery mildew fruit	Mar 100 Powdery mildew fruit	Map Powdery mildew leaf	Mar 100 Powdery mildew leaf
48.1383	1.0	91	32.7441	0.072	0.0944	0.0789	0.0008	0.028	0.1218	0.1444	0.2815	0.3583	0.2	0.1977	0.4277	0.0097	0.4962	0.001	0.0529	0.0025	0.0727	0.0527	0.2222	0.1818	0.8401	0.0002	0.05	0.2557	0.7737
28.1321	2.0	182	26.8257	0.2203	0.2891	0.2395	0.1267	0.1186	0.2617	0.2987	0.5351	0.5913	0.4	0.3726	0.6649	0.0203	0.5981	0.0049	0.1706	0.1769	0.65	0.1961	0.6324	0.6355	0.9082	0.0087	0.3444	0.4998	0.8353
23.6192	3.0	273	23.0934	0.3141	0.408	0.3423	0.2133	0.195	0.3834	0.3621	0.6516	0.6971	0.4	0.4291	0.7797	0.0457	0.7288	0.0175	0.4059	0.4873	0.7205	0.2984	0.7102	0.7575	0.9249	0.0257	0.5444	0.5666	0.8451
20.6054	4.0	364	21.1837	0.398	0.5303	0.434	0.2115	0.237	0.4998	0.3852	0.7062	0.7568	0.5	0.5624	0.8306	0.264	0.7365	0.0368	0.5882	0.5386	0.75	0.434	0.7287	0.7965	0.9331	0.107	0.7056	0.6088	0.8557
19.4288	5.0	455	19.9111	0.4366	0.5924	0.4686	0.1758	0.256	0.5269	0.4005	0.7295	0.7887	0.4	0.5917	0.8558	0.3157	0.7788	0.0679	0.6471	0.5715	0.7636	0.4758	0.7389	0.8107	0.9315	0.1825	0.8	0.632	0.8608
17.8867	6.0	546	18.9302	0.5064	0.6834	0.5457	0.35	0.3232	0.5693	0.395	0.7462	0.8006	0.45	0.6427	0.8583	0.3472	0.7731	0.1802	0.7	0.6516	0.7909	0.5193	0.7398	0.8209	0.9362	0.3584	0.8	0.6671	0.8639
16.9985	7.0	637	18.2692	0.5458	0.7266	0.6036	0.2667	0.353	0.6138	0.4145	0.7701	0.8142	0.4	0.6488	0.876	0.4325	0.775	0.2601	0.7118	0.7072	0.8159	0.5295	0.7472	0.8566	0.9424	0.3656	0.8333	0.6692	0.8737
16.1493	8.0	728	17.3118	0.5707	0.7557	0.6298	0.4036	0.3684	0.6464	0.4175	0.7831	0.8275	0.45	0.6815	0.8822	0.4954	0.7923	0.3283	0.7588	0.7096	0.8159	0.5474	0.7528	0.8717	0.9436	0.3381	0.8444	0.7045	0.8847
15.3879	9.0	819	16.7216	0.5907	0.7634	0.6611	0.35	0.3824	0.6636	0.4145	0.7808	0.8258	0.45	0.6663	0.8821	0.5305	0.8019	0.3748	0.7529	0.7337	0.8136	0.5658	0.7574	0.8738	0.9377	0.3421	0.8333	0.7144	0.8835
14.4614	10.0	910	16.2566	0.6229	0.8172	0.6824	0.35	0.401	0.7146	0.4279	0.7886	0.831	0.5	0.7108	0.8802	0.54	0.8135	0.405	0.7118	0.7372	0.8159	0.5767	0.7648	0.8783	0.9416	0.5019	0.8833	0.7209	0.8863

Framework versions

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