detr-arrows

This model is a fine-tuned version of facebook/detr-resnet-50 on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.0051
Map: 0.0157
Map 50: 0.0235
Map 75: 0.017
Map Small: 0.0157
Map Medium: -1.0
Map Large: -1.0
Mar 1: 0.0854
Mar 10: 0.0917
Mar 100: 0.2917
Mar Small: 0.2917
Mar Medium: -1.0
Mar Large: -1.0
Map Left: 0.0
Mar 100 Left: 0.0
Map Right: -1.0
Mar 100 Right: -1.0
Map Up: 0.0385
Mar 100 Up: 0.2667
Map Down: 0.0146
Mar 100 Down: 0.8
Map ?: 0.0099
Mar 100 ?: 0.1

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: 3e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
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: cosine
num_epochs: 30

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 Right	Mar 100 Right	Map Up	Mar 100 Up	Map Down	Mar 100 Down	Map ?	Mar 100 ?
No log	1.0	8	2.9834	0.0001	0.0014	0.0	0.0002	-1.0	-1.0	0.0	0.0	0.025	0.025	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0006	0.1	0.0	0.0
No log	2.0	16	2.3564	0.0005	0.0023	0.0	0.0007	-1.0	-1.0	0.0	0.0	0.05	0.05	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0019	0.2	0.0	0.0
No log	3.0	24	2.1618	0.001	0.0025	0.0	0.0012	-1.0	-1.0	0.0	0.0	0.1	0.1	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.004	0.4	0.0	0.0
No log	4.0	32	2.0074	0.0005	0.0027	0.0	0.0007	-1.0	-1.0	0.0	0.0	0.05	0.05	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0022	0.2	0.0	0.0
No log	5.0	40	1.7452	0.0008	0.003	0.0	0.0009	-1.0	-1.0	0.0	0.0	0.0812	0.0812	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0028	0.3	0.0003	0.025
No log	6.0	48	1.6746	0.0009	0.0024	0.0	0.0011	-1.0	-1.0	0.0	0.0	0.1	0.1	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0038	0.4	0.0	0.0
No log	7.0	56	1.5161	0.0014	0.0023	0.0023	0.0016	-1.0	-1.0	0.0	0.0	0.15	0.15	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0054	0.6	0.0	0.0
No log	8.0	64	1.5721	0.0009	0.0017	0.0	0.001	-1.0	-1.0	0.0	0.0	0.125	0.125	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0034	0.5	0.0	0.0
No log	9.0	72	1.4536	0.0014	0.0021	0.0021	0.0021	-1.0	-1.0	0.0	0.0	0.175	0.175	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0056	0.7	0.0	0.0
No log	10.0	80	1.2638	0.0013	0.0023	0.0014	0.0019	-1.0	-1.0	0.0	0.0	0.175	0.175	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0052	0.7	0.0	0.0
No log	11.0	88	1.2646	0.0015	0.0025	0.0014	0.0025	-1.0	-1.0	0.0	0.0	0.175	0.175	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0062	0.7	0.0	0.0
No log	12.0	96	1.2239	0.0023	0.003	0.003	0.0038	-1.0	-1.0	0.0	0.0	0.2	0.2	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0092	0.8	0.0	0.0
No log	13.0	104	1.1191	0.0023	0.0057	0.0025	0.0035	-1.0	-1.0	0.0	0.0125	0.1875	0.1875	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0068	0.7	0.0026	0.05
No log	14.0	112	1.1491	0.0029	0.0054	0.002	0.0038	-1.0	-1.0	0.0312	0.0312	0.1813	0.1813	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0047	0.6	0.0068	0.125
No log	15.0	120	1.1062	0.02	0.0349	0.0297	0.0287	-1.0	-1.0	0.05	0.075	0.25	0.25	-1.0	-1.0	-1.0	-1.0	0.0673	0.2	0.0053	0.7	0.0074	0.1
No log	16.0	128	1.0963	0.0705	0.0925	0.086	0.0705	-1.0	-1.0	0.0854	0.0854	0.2354	0.2354	-1.0	-1.0	-1.0	-1.0	0.2693	0.2667	0.0058	0.6	0.007	0.075
No log	17.0	136	1.0369	0.0349	0.051	0.0434	0.0349	-1.0	-1.0	0.075	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.1234	0.2667	0.0049	0.8	0.0114	0.1
No log	18.0	144	1.0721	0.0324	0.05	0.0435	0.0324	-1.0	-1.0	0.0771	0.0771	0.2521	0.2521	-1.0	-1.0	-1.0	-1.0	0.1178	0.2333	0.004	0.7	0.0077	0.075
No log	19.0	152	1.0081	0.0623	0.0922	0.0858	0.0625	-1.0	-1.0	0.0646	0.0833	0.2833	0.2833	-1.0	-1.0	-1.0	-1.0	0.2356	0.2333	0.0051	0.8	0.0085	0.1
No log	20.0	160	1.0390	0.0367	0.0504	0.044	0.0367	-1.0	-1.0	0.0729	0.0854	0.2604	0.2604	-1.0	-1.0	-1.0	-1.0	0.1347	0.2667	0.0053	0.7	0.0071	0.075
No log	21.0	168	1.0262	0.0255	0.0371	0.0299	0.0255	-1.0	-1.0	0.0729	0.0854	0.2604	0.2604	-1.0	-1.0	-1.0	-1.0	0.0898	0.2667	0.0052	0.7	0.0068	0.075
No log	22.0	176	0.9972	0.0134	0.0223	0.0159	0.0134	-1.0	-1.0	0.0646	0.0833	0.2833	0.2833	-1.0	-1.0	-1.0	-1.0	0.0393	0.2333	0.0058	0.8	0.0086	0.1
No log	23.0	184	1.0195	0.0135	0.0204	0.014	0.0135	-1.0	-1.0	0.0729	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.0061	0.8	0.0092	0.1
No log	24.0	192	1.0240	0.0145	0.023	0.0139	0.0145	-1.0	-1.0	0.0792	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.0101	0.8	0.0095	0.1
No log	25.0	200	1.0151	0.0157	0.024	0.0176	0.0157	-1.0	-1.0	0.0854	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.0147	0.8	0.0096	0.1
No log	26.0	208	1.0143	0.0153	0.0233	0.0168	0.0153	-1.0	-1.0	0.0854	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.013	0.8	0.0099	0.1
No log	27.0	216	1.0092	0.0157	0.0235	0.017	0.0157	-1.0	-1.0	0.0854	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.0146	0.8	0.0099	0.1
No log	28.0	224	1.0051	0.0157	0.0235	0.017	0.0157	-1.0	-1.0	0.0854	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.0146	0.8	0.0099	0.1
No log	29.0	232	1.0046	0.0157	0.0235	0.017	0.0157	-1.0	-1.0	0.0854	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.0146	0.8	0.0099	0.1
No log	30.0	240	1.0051	0.0157	0.0235	0.017	0.0157	-1.0	-1.0	0.0854	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.0146	0.8	0.0099	0.1

Framework versions

Transformers 4.48.0.dev0
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0

加载中…

detr-arrows

This model is a fine-tuned version of facebook/detr-resnet-50 on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.0051

Map: 0.0157

Map 50: 0.0235

Map 75: 0.017

Map Small: 0.0157

Map Medium: -1.0

Map Large: -1.0

Mar 1: 0.0854

Mar 10: 0.0917

Mar 100: 0.2917

Mar Small: 0.2917

Mar Medium: -1.0

Mar Large: -1.0

Map Left: 0.0

Mar 100 Left: 0.0

Map Right: -1.0

Mar 100 Right: -1.0

Map Up: 0.0385

Mar 100 Up: 0.2667

Map Down: 0.0146

Mar 100 Down: 0.8

Map ?: 0.0099

Mar 100 ?: 0.1

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 3e-05

train_batch_size: 8

eval_batch_size: 8

seed: 42

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: cosine

num_epochs: 30

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 Right	Mar 100 Right	Map Up	Mar 100 Up	Map Down	Mar 100 Down	Map ?	Mar 100 ?
No log	1.0	8	2.9834	0.0001	0.0014	0.0	0.0002	-1.0	-1.0	0.0	0.0	0.025	0.025	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0006	0.1	0.0	0.0
No log	2.0	16	2.3564	0.0005	0.0023	0.0	0.0007	-1.0	-1.0	0.0	0.0	0.05	0.05	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0019	0.2	0.0	0.0
No log	3.0	24	2.1618	0.001	0.0025	0.0	0.0012	-1.0	-1.0	0.0	0.0	0.1	0.1	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.004	0.4	0.0	0.0
No log	4.0	32	2.0074	0.0005	0.0027	0.0	0.0007	-1.0	-1.0	0.0	0.0	0.05	0.05	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0022	0.2	0.0	0.0
No log	5.0	40	1.7452	0.0008	0.003	0.0	0.0009	-1.0	-1.0	0.0	0.0	0.0812	0.0812	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0028	0.3	0.0003	0.025
No log	6.0	48	1.6746	0.0009	0.0024	0.0	0.0011	-1.0	-1.0	0.0	0.0	0.1	0.1	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0038	0.4	0.0	0.0
No log	7.0	56	1.5161	0.0014	0.0023	0.0023	0.0016	-1.0	-1.0	0.0	0.0	0.15	0.15	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0054	0.6	0.0	0.0
No log	8.0	64	1.5721	0.0009	0.0017	0.0	0.001	-1.0	-1.0	0.0	0.0	0.125	0.125	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0034	0.5	0.0	0.0
No log	9.0	72	1.4536	0.0014	0.0021	0.0021	0.0021	-1.0	-1.0	0.0	0.0	0.175	0.175	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0056	0.7	0.0	0.0
No log	10.0	80	1.2638	0.0013	0.0023	0.0014	0.0019	-1.0	-1.0	0.0	0.0	0.175	0.175	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0052	0.7	0.0	0.0
No log	11.0	88	1.2646	0.0015	0.0025	0.0014	0.0025	-1.0	-1.0	0.0	0.0	0.175	0.175	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0062	0.7	0.0	0.0
No log	12.0	96	1.2239	0.0023	0.003	0.003	0.0038	-1.0	-1.0	0.0	0.0	0.2	0.2	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0092	0.8	0.0	0.0
No log	13.0	104	1.1191	0.0023	0.0057	0.0025	0.0035	-1.0	-1.0	0.0	0.0125	0.1875	0.1875	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0068	0.7	0.0026	0.05
No log	14.0	112	1.1491	0.0029	0.0054	0.002	0.0038	-1.0	-1.0	0.0312	0.0312	0.1813	0.1813	-1.0	-1.0	-1.0	-1.0	0.0	0.0	0.0047	0.6	0.0068	0.125
No log	15.0	120	1.1062	0.02	0.0349	0.0297	0.0287	-1.0	-1.0	0.05	0.075	0.25	0.25	-1.0	-1.0	-1.0	-1.0	0.0673	0.2	0.0053	0.7	0.0074	0.1
No log	16.0	128	1.0963	0.0705	0.0925	0.086	0.0705	-1.0	-1.0	0.0854	0.0854	0.2354	0.2354	-1.0	-1.0	-1.0	-1.0	0.2693	0.2667	0.0058	0.6	0.007	0.075
No log	17.0	136	1.0369	0.0349	0.051	0.0434	0.0349	-1.0	-1.0	0.075	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.1234	0.2667	0.0049	0.8	0.0114	0.1
No log	18.0	144	1.0721	0.0324	0.05	0.0435	0.0324	-1.0	-1.0	0.0771	0.0771	0.2521	0.2521	-1.0	-1.0	-1.0	-1.0	0.1178	0.2333	0.004	0.7	0.0077	0.075
No log	19.0	152	1.0081	0.0623	0.0922	0.0858	0.0625	-1.0	-1.0	0.0646	0.0833	0.2833	0.2833	-1.0	-1.0	-1.0	-1.0	0.2356	0.2333	0.0051	0.8	0.0085	0.1
No log	20.0	160	1.0390	0.0367	0.0504	0.044	0.0367	-1.0	-1.0	0.0729	0.0854	0.2604	0.2604	-1.0	-1.0	-1.0	-1.0	0.1347	0.2667	0.0053	0.7	0.0071	0.075
No log	21.0	168	1.0262	0.0255	0.0371	0.0299	0.0255	-1.0	-1.0	0.0729	0.0854	0.2604	0.2604	-1.0	-1.0	-1.0	-1.0	0.0898	0.2667	0.0052	0.7	0.0068	0.075
No log	22.0	176	0.9972	0.0134	0.0223	0.0159	0.0134	-1.0	-1.0	0.0646	0.0833	0.2833	0.2833	-1.0	-1.0	-1.0	-1.0	0.0393	0.2333	0.0058	0.8	0.0086	0.1
No log	23.0	184	1.0195	0.0135	0.0204	0.014	0.0135	-1.0	-1.0	0.0729	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.0061	0.8	0.0092	0.1
No log	24.0	192	1.0240	0.0145	0.023	0.0139	0.0145	-1.0	-1.0	0.0792	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.0101	0.8	0.0095	0.1
No log	25.0	200	1.0151	0.0157	0.024	0.0176	0.0157	-1.0	-1.0	0.0854	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.0147	0.8	0.0096	0.1
No log	26.0	208	1.0143	0.0153	0.0233	0.0168	0.0153	-1.0	-1.0	0.0854	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.013	0.8	0.0099	0.1
No log	27.0	216	1.0092	0.0157	0.0235	0.017	0.0157	-1.0	-1.0	0.0854	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.0146	0.8	0.0099	0.1
No log	28.0	224	1.0051	0.0157	0.0235	0.017	0.0157	-1.0	-1.0	0.0854	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.0146	0.8	0.0099	0.1
No log	29.0	232	1.0046	0.0157	0.0235	0.017	0.0157	-1.0	-1.0	0.0854	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.0146	0.8	0.0099	0.1
No log	30.0	240	1.0051	0.0157	0.0235	0.017	0.0157	-1.0	-1.0	0.0854	0.0917	0.2917	0.2917	-1.0	-1.0	-1.0	-1.0	0.0385	0.2667	0.0146	0.8	0.0099	0.1

Framework versions

Transformers 4.48.0.dev0

Pytorch 2.5.1+cu124

Datasets 3.2.0

Tokenizers 0.21.0

GAVLM/detr-arrows

detr-arrows

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

detr-arrows

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions