detr_finetuned_cppe5

This model is a fine-tuned version of microsoft/conditional-detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.5826
• Map: 0.0003
• Map 50: 0.0007
• Map 75: 0.0
• Map Small: 0.0014
• Map Medium: 0.0001
• Map Large: 0.0
• Mar 1: 0.0
• Mar 10: 0.0021
• Mar 100: 0.0075
• Mar Small: 0.0118
• Mar Medium: 0.0062
• Mar Large: 0.01
• Map Coverall: 0.0
• Mar 100 Coverall: 0.0
• Map Face Shield: 0.0
• Mar 100 Face Shield: 0.0
• Map Gloves: 0.0015
• Mar 100 Gloves: 0.0375
• Map Goggles: 0.0
• Mar 100 Goggles: 0.0
• Map Mask: 0.0
• Mar 100 Mask: 0.0

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: 0.001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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 Coverall	Mar 100 Coverall	Map Face Shield	Mar 100 Face Shield	Map Gloves	Mar 100 Gloves	Map Goggles	Mar 100 Goggles	Map Mask	Mar 100 Mask
No log	1.0	107	3.5856	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0003	0.0061	0.0006	0.0065	0.0157	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0307
No log	2.0	214	3.7297	0.0	0.0001	0.0	0.0	0.0	0.0	0.0	0.0002	0.0078	0.0097	0.011	0.0017	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0001	0.0391
No log	3.0	321	3.8304	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0044	0.0	0.0032	0.0149	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0222
No log	4.0	428	3.6958	0.0	0.0001	0.0	0.0	0.0	0.0	0.0002	0.0004	0.0071	0.0059	0.0105	0.0047	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0001	0.0356
2.8722	5.0	535	4.0271	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0014	0.0	0.0017	0.0034	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0071
2.8722	6.0	642	3.6288	0.0	0.0001	0.0	0.0001	0.0	0.0	0.0	0.001	0.0125	0.01	0.0159	0.014	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0002	0.0627
2.8722	7.0	749	3.6254	0.0	0.0001	0.0	0.0001	0.0	0.0001	0.0	0.0005	0.0063	0.0105	0.0035	0.0132	0.0	0.0	0.0	0.0	0.0001	0.0312	0.0	0.0	0.0	0.0
2.8722	8.0	856	3.8407	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0003	0.0016	0.0	0.0017	0.0043	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.008
2.8722	9.0	963	3.6509	0.0	0.0002	0.0	0.0001	0.0	0.0	0.0	0.0009	0.0066	0.0072	0.007	0.0059	0.0	0.0	0.0	0.0	0.0002	0.033	0.0	0.0	0.0	0.0
2.5968	10.0	1070	3.6992	0.0	0.0	0.0	0.0	0.0001	0.0	0.0	0.0003	0.0033	0.0033	0.0041	0.0014	0.0	0.0	0.0	0.0	0.0	0.0165	0.0	0.0	0.0	0.0
2.5968	11.0	1177	3.6423	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0012	0.006	0.0006	0.0097	0.0085	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0001	0.0298
2.5968	12.0	1284	3.5987	0.0005	0.0023	0.0	0.0019	0.0001	0.0	0.0002	0.0009	0.0077	0.0092	0.0066	0.0114	0.0	0.0	0.0	0.0	0.0024	0.0384	0.0	0.0	0.0	0.0
2.5968	13.0	1391	3.6200	0.0	0.0001	0.0	0.0005	0.0	0.0	0.0	0.0028	0.0076	0.0099	0.0077	0.0068	0.0	0.0	0.0	0.0	0.0002	0.0379	0.0	0.0	0.0	0.0
2.5968	14.0	1498	3.7723	0.0	0.0001	0.0	0.0	0.0001	0.0	0.0003	0.0006	0.0044	0.0007	0.0044	0.0077	0.0	0.0	0.0	0.0	0.0001	0.0219	0.0	0.0	0.0	0.0
2.5557	15.0	1605	3.6236	0.0	0.0001	0.0	0.0	0.0	0.0	0.0003	0.0011	0.0081	0.0021	0.0099	0.0162	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0001	0.0404
2.5557	16.0	1712	3.6496	0.0001	0.0002	0.0	0.0008	0.0003	0.0	0.0004	0.0017	0.0065	0.0059	0.0066	0.0077	0.0	0.0	0.0	0.0	0.0003	0.0326	0.0	0.0	0.0	0.0
2.5557	17.0	1819	3.6098	0.0	0.0001	0.0	0.0	0.0001	0.0	0.0	0.0009	0.0046	0.0007	0.0039	0.0105	0.0	0.0	0.0	0.0	0.0001	0.0232	0.0	0.0	0.0	0.0
2.5557	18.0	1926	3.6017	0.0001	0.0003	0.0	0.0	0.0005	0.0	0.0004	0.0015	0.0061	0.0026	0.0069	0.0068	0.0	0.0	0.0	0.0	0.0003	0.0304	0.0	0.0	0.0	0.0
2.5084	19.0	2033	3.5866	0.0003	0.0006	0.0004	0.0045	0.0002	0.0	0.0013	0.0029	0.0078	0.0066	0.0079	0.0095	0.0	0.0	0.0	0.0	0.0014	0.0388	0.0	0.0	0.0	0.0
2.5084	20.0	2140	3.6129	0.0002	0.0022	0.0	0.0008	0.0001	0.0	0.0001	0.0015	0.0073	0.0066	0.0069	0.0105	0.0	0.0	0.0	0.0	0.0012	0.0366	0.0	0.0	0.0	0.0
2.5084	21.0	2247	3.5974	0.0004	0.001	0.0	0.002	0.0002	0.0	0.0004	0.0033	0.0083	0.0099	0.0086	0.0077	0.0	0.0	0.0	0.0	0.002	0.0415	0.0	0.0	0.0	0.0
2.5084	22.0	2354	3.5810	0.0	0.0002	0.0	0.0001	0.0001	0.0	0.0	0.0012	0.0075	0.0072	0.0069	0.0109	0.0	0.0	0.0	0.0	0.0002	0.0375	0.0	0.0	0.0	0.0
2.5084	23.0	2461	3.6132	0.0005	0.0013	0.0	0.0016	0.0002	0.0	0.0	0.0028	0.0077	0.0079	0.0079	0.0082	0.0	0.0	0.0	0.0	0.0023	0.0384	0.0	0.0	0.0	0.0
2.4812	24.0	2568	3.5863	0.0002	0.0022	0.0	0.0009	0.0001	0.0	0.0001	0.0018	0.0069	0.0079	0.007	0.0068	0.0	0.0	0.0	0.0	0.0012	0.0344	0.0	0.0	0.0	0.0
2.4812	25.0	2675	3.6469	0.0002	0.0022	0.0	0.0008	0.0001	0.0	0.0001	0.0018	0.007	0.0059	0.0076	0.0068	0.0	0.0	0.0	0.0	0.0012	0.0348	0.0	0.0	0.0	0.0
2.4812	26.0	2782	3.5896	0.0001	0.0006	0.0	0.0004	0.0001	0.0	0.0	0.0017	0.007	0.0099	0.0063	0.0082	0.0	0.0	0.0	0.0	0.0004	0.0348	0.0	0.0	0.0	0.0
2.4812	27.0	2889	3.5994	0.0001	0.0005	0.0	0.0007	0.0001	0.0	0.0004	0.0024	0.0074	0.0112	0.0066	0.0086	0.0	0.0	0.0	0.0	0.0006	0.0371	0.0	0.0	0.0	0.0
2.4812	28.0	2996	3.5806	0.0002	0.0006	0.0	0.0014	0.0001	0.0	0.0	0.0019	0.0072	0.0112	0.0058	0.0105	0.0	0.0	0.0	0.0	0.0012	0.0362	0.0	0.0	0.0	0.0
2.4512	29.0	3103	3.5821	0.0002	0.0006	0.0	0.0014	0.0001	0.0	0.0004	0.0023	0.0075	0.0118	0.0062	0.01	0.0	0.0	0.0	0.0	0.0011	0.0375	0.0	0.0	0.0	0.0
2.4512	30.0	3210	3.5826	0.0003	0.0007	0.0	0.0014	0.0001	0.0	0.0	0.0021	0.0075	0.0118	0.0062	0.01	0.0	0.0	0.0	0.0	0.0015	0.0375	0.0	0.0	0.0	0.0

Framework versions

• Transformers 4.55.4
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.21.4