You can deploy this model and start earning money today!

mfly-auton/
suas-2025-rtdetr-finetuned-b16-lr1e-5

Name: suas-2025-rtdetr-finetuned-b16-lr1e-5
Availability: InStock

generated_from_trainer

Views

No views yet

suas-2025-rtdetr-finetuned-b16-lr1e-5

This model is a fine-tuned version of PekingU/rtdetr_r50vd on the mfly-auton/suas-2025-synthetic-data dataset. It achieves the following results on the evaluation set:

Loss: 3.6523
Map: 0.8465
Map 50: 0.9229
Map 75: 0.9193
Map Small: 0.7682
Map Medium: 0.8561
Map Large: 0.9144
Mar 1: 0.7945
Mar 10: 0.9245
Mar 100: 0.9271
Mar Small: 0.8316
Mar Medium: 0.9357
Mar Large: 0.9779
Map Baseball-bat: 0.8128
Mar 100 Baseball-bat: 0.892
Map Basketball: 0.8105
Mar 100 Basketball: 0.8993
Map Car: -1.0
Mar 100 Car: -1.0
Map Football: 0.7611
Mar 100 Football: 0.8113
Map Human: 0.9382
Mar 100 Human: 0.9641
Map Luggage: 0.8579
Mar 100 Luggage: 0.9191
Map Mattress: 0.9384
Mar 100 Mattress: 0.977
Map Motorcycle: 0.9309
Mar 100 Motorcycle: 0.9773
Map Skis: 0.7044
Mar 100 Skis: 0.995
Map Snowboard: 0.9834
Mar 100 Snowboard: 0.9932
Map Soccer-ball: 0.8245
Mar 100 Soccer-ball: 0.8733
Map Stop-sign: 0.9671
Mar 100 Stop-sign: 0.9925
Map Tennis-racket: 0.7064
Mar 100 Tennis-racket: 0.8539
Map Umbrella: 0.8285
Mar 100 Umbrella: 0.9803
Map Volleyball: 0.787
Mar 100 Volleyball: 0.8517

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: 16
eval_batch_size: 32
seed: 1337
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
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 Baseball-bat	Mar 100 Baseball-bat	Map Basketball	Mar 100 Basketball	Map Car	Mar 100 Car	Map Football	Mar 100 Football	Map Human	Mar 100 Human	Map Luggage	Mar 100 Luggage	Map Mattress	Mar 100 Mattress	Map Motorcycle	Mar 100 Motorcycle	Map Skis	Mar 100 Skis	Map Snowboard	Mar 100 Snowboard	Map Soccer-ball	Mar 100 Soccer-ball	Map Stop-sign	Mar 100 Stop-sign	Map Tennis-racket	Mar 100 Tennis-racket	Map Umbrella	Mar 100 Umbrella	Map Volleyball	Mar 100 Volleyball
26.4817	1.0	438	7.1796	0.5246	0.6136	0.5998	0.4998	0.4541	0.685	0.6337	0.8316	0.8375	0.7077	0.8446	0.9453	0.3868	0.8129	0.1579	0.8832	-1.0	-1.0	0.5107	0.6099	0.8625	0.9246	0.6942	0.792	0.568	0.8388	0.7128	0.9384	0.085	0.9099	0.9532	0.9784	0.5658	0.7478	0.3822	0.9553	0.2726	0.7264	0.6033	0.9515	0.5895	0.6554
8.2849	2.0	876	5.1650	0.6623	0.7385	0.7311	0.6108	0.674	0.8009	0.6914	0.87	0.8726	0.7227	0.9081	0.9696	0.7515	0.8723	0.2886	0.8671	-1.0	-1.0	0.6431	0.7019	0.9057	0.9462	0.8014	0.8587	0.8949	0.9605	0.8986	0.9603	0.1247	0.9936	0.9665	0.9862	0.7817	0.8419	0.8546	0.9869	0.0862	0.7197	0.7593	0.9635	0.5151	0.5581
6.559	3.0	1314	4.4005	0.7504	0.8276	0.8215	0.7114	0.7272	0.8594	0.7435	0.8949	0.8966	0.7711	0.9093	0.975	0.7706	0.8428	0.6714	0.8801	-1.0	-1.0	0.6961	0.7498	0.9191	0.9553	0.8097	0.8663	0.9315	0.981	0.9122	0.9665	0.356	0.9926	0.9799	0.9927	0.8045	0.8594	0.9288	0.9846	0.2706	0.7788	0.7865	0.9736	0.6683	0.7284
6.1007	4.0	1752	4.3050	0.7733	0.8501	0.8445	0.672	0.8036	0.8698	0.75	0.8933	0.8959	0.7471	0.93	0.977	0.7927	0.8788	0.5734	0.7517	-1.0	-1.0	0.7111	0.7712	0.9262	0.959	0.8357	0.8953	0.9221	0.966	0.9326	0.9731	0.4091	0.9936	0.9788	0.9937	0.7975	0.8563	0.9535	0.9877	0.5879	0.8409	0.798	0.9753	0.6073	0.6998
5.7812	5.0	2190	3.9205	0.8281	0.91	0.9046	0.741	0.8373	0.9087	0.7819	0.9162	0.9196	0.8073	0.9294	0.9776	0.8105	0.8866	0.7005	0.8344	-1.0	-1.0	0.7656	0.8203	0.9326	0.9609	0.8291	0.9	0.9399	0.9791	0.9223	0.9695	0.6417	0.9906	0.977	0.9935	0.8194	0.8738	0.9422	0.9858	0.7258	0.8819	0.8433	0.9767	0.744	0.8208
5.4833	6.0	2628	3.7494	0.8402	0.9191	0.915	0.7567	0.861	0.9247	0.7947	0.9219	0.9246	0.8235	0.9378	0.9902	0.8153	0.8907	0.8096	0.9043	-1.0	-1.0	0.7586	0.8083	0.9378	0.9627	0.8322	0.9015	0.9545	0.989	0.9241	0.9725	0.7303	0.9926	0.9832	0.9947	0.8225	0.8707	0.9542	0.988	0.6731	0.871	0.8273	0.9776	0.7398	0.8213
5.3134	7.0	3066	3.7250	0.8437	0.9213	0.9165	0.7597	0.854	0.919	0.7917	0.9213	0.9241	0.8256	0.9419	0.9775	0.8142	0.8876	0.8066	0.9014	-1.0	-1.0	0.7341	0.7887	0.9359	0.9624	0.8417	0.9133	0.9412	0.9782	0.9292	0.9777	0.713	0.9931	0.9828	0.9934	0.828	0.8761	0.963	0.9922	0.7265	0.8554	0.8307	0.9791	0.7646	0.8392
5.2982	8.0	3504	3.7825	0.8419	0.9181	0.9133	0.7599	0.8549	0.9154	0.7909	0.9198	0.922	0.8277	0.9355	0.9768	0.8151	0.8931	0.8242	0.9066	-1.0	-1.0	0.7225	0.772	0.9375	0.9627	0.8383	0.9052	0.9338	0.9744	0.9288	0.9755	0.7353	0.996	0.9818	0.9925	0.8221	0.873	0.9675	0.9891	0.6801	0.8466	0.8273	0.9818	0.7726	0.8397
5.1855	9.0	3942	3.7947	0.8365	0.913	0.9085	0.7528	0.8439	0.9104	0.7884	0.9184	0.9219	0.8189	0.9344	0.979	0.8041	0.8864	0.8009	0.8955	-1.0	-1.0	0.7239	0.7755	0.9351	0.9622	0.8444	0.9119	0.9314	0.9771	0.9241	0.9735	0.7034	0.995	0.984	0.995	0.8168	0.8704	0.9639	0.9922	0.6888	0.8513	0.8203	0.9808	0.7704	0.8402
5.1499	10.0	4380	3.6523	0.8465	0.9229	0.9193	0.7682	0.8561	0.9144	0.7945	0.9245	0.9271	0.8316	0.9357	0.9779	0.8128	0.892	0.8105	0.8993	-1.0	-1.0	0.7611	0.8113	0.9382	0.9641	0.8579	0.9191	0.9384	0.977	0.9309	0.9773	0.7044	0.995	0.9834	0.9932	0.8245	0.8733	0.9671	0.9925	0.7064	0.8539	0.8285	0.9803	0.787	0.8517

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.21.0

mfly-auton/suas-2025-rtdetr-finetuned-b16-lr1e-5

suas-2025-rtdetr-finetuned-b16-lr1e-5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

mfly-auton/
suas-2025-rtdetr-finetuned-b16-lr1e-5