Hugging Face's logo

MedicalVision
/
yolos_tiny_50ep

Object Detection
Transformers
Safetensors
yolos
Inference Endpoints
Model card Files Community
Edit model card

Original result 

IoU metric: bbox
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.007
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.008
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.008

After training result 

IoU metric: bbox
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.008
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.016
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.009
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.008
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.060
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.122
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.140
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.141

Config

  • dataset: NIH
  • original model: hustvl/yolos-tiny
  • lr: 1e-05
  • dropout_rate: 0.1
  • weight_decay: 0.05
  • max_epochs: 50
  • train samples: 885

Logging

Training process 

{'validation_loss': tensor(7.0099, device='cuda:0'), 'validation_loss_ce': tensor(2.4436, device='cuda:0'), 'validation_loss_bbox': tensor(0.5540, device='cuda:0'), 'validation_loss_giou': tensor(0.8981, device='cuda:0'), 'validation_cardinality_error': tensor(99., device='cuda:0')}
{'training_loss': tensor(3.9420, device='cuda:0'), 'train_loss_ce': tensor(1.3197, device='cuda:0'), 'train_loss_bbox': tensor(0.2500, device='cuda:0'), 'train_loss_giou': tensor(0.6860, device='cuda:0'), 'train_cardinality_error': tensor(7., device='cuda:0'), 'validation_loss': tensor(3.3165, device='cuda:0'), 'validation_loss_ce': tensor(1.2489, device='cuda:0'), 'validation_loss_bbox': tensor(0.1881, device='cuda:0'), 'validation_loss_giou': tensor(0.5635, device='cuda:0'), 'validation_cardinality_error': tensor(4.0101, device='cuda:0')}
{'training_loss': tensor(3.3235, device='cuda:0'), 'train_loss_ce': tensor(0.6793, device='cuda:0'), 'train_loss_bbox': tensor(0.2541, device='cuda:0'), 'train_loss_giou': tensor(0.6867, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4833, device='cuda:0'), 'validation_loss_ce': tensor(0.6021, device='cuda:0'), 'validation_loss_bbox': tensor(0.1646, device='cuda:0'), 'validation_loss_giou': tensor(0.5291, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3983, device='cuda:0'), 'train_loss_ce': tensor(0.5598, device='cuda:0'), 'train_loss_bbox': tensor(0.1766, device='cuda:0'), 'train_loss_giou': tensor(0.4778, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2504, device='cuda:0'), 'validation_loss_ce': tensor(0.4912, device='cuda:0'), 'validation_loss_bbox': tensor(0.1561, device='cuda:0'), 'validation_loss_giou': tensor(0.4895, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9965, device='cuda:0'), 'train_loss_ce': tensor(0.4444, device='cuda:0'), 'train_loss_bbox': tensor(0.1335, device='cuda:0'), 'train_loss_giou': tensor(0.4423, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2376, device='cuda:0'), 'validation_loss_ce': tensor(0.4733, device='cuda:0'), 'validation_loss_bbox': tensor(0.1545, device='cuda:0'), 'validation_loss_giou': tensor(0.4960, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.3605, device='cuda:0'), 'train_loss_ce': tensor(0.3837, device='cuda:0'), 'train_loss_bbox': tensor(0.1640, device='cuda:0'), 'train_loss_giou': tensor(0.5785, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2257, device='cuda:0'), 'validation_loss_ce': tensor(0.4630, device='cuda:0'), 'validation_loss_bbox': tensor(0.1510, device='cuda:0'), 'validation_loss_giou': tensor(0.5039, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8496, device='cuda:0'), 'train_loss_ce': tensor(0.4450, device='cuda:0'), 'train_loss_bbox': tensor(0.1345, device='cuda:0'), 'train_loss_giou': tensor(0.3660, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0929, device='cuda:0'), 'validation_loss_ce': tensor(0.4594, device='cuda:0'), 'validation_loss_bbox': tensor(0.1348, device='cuda:0'), 'validation_loss_giou': tensor(0.4796, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8037, device='cuda:0'), 'train_loss_ce': tensor(0.4246, device='cuda:0'), 'train_loss_bbox': tensor(0.1193, device='cuda:0'), 'train_loss_giou': tensor(0.3912, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1036, device='cuda:0'), 'validation_loss_ce': tensor(0.4565, device='cuda:0'), 'validation_loss_bbox': tensor(0.1409, device='cuda:0'), 'validation_loss_giou': tensor(0.4713, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4431, device='cuda:0'), 'train_loss_ce': tensor(0.4050, device='cuda:0'), 'train_loss_bbox': tensor(0.1342, device='cuda:0'), 'train_loss_giou': tensor(0.6835, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0913, device='cuda:0'), 'validation_loss_ce': tensor(0.4534, device='cuda:0'), 'validation_loss_bbox': tensor(0.1405, device='cuda:0'), 'validation_loss_giou': tensor(0.4676, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5937, device='cuda:0'), 'train_loss_ce': tensor(0.4950, device='cuda:0'), 'train_loss_bbox': tensor(0.0820, device='cuda:0'), 'train_loss_giou': tensor(0.3444, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1049, device='cuda:0'), 'validation_loss_ce': tensor(0.4502, device='cuda:0'), 'validation_loss_bbox': tensor(0.1431, device='cuda:0'), 'validation_loss_giou': tensor(0.4696, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.4078, device='cuda:0'), 'train_loss_ce': tensor(0.3842, device='cuda:0'), 'train_loss_bbox': tensor(0.1092, device='cuda:0'), 'train_loss_giou': tensor(0.2389, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0739, device='cuda:0'), 'validation_loss_ce': tensor(0.4510, device='cuda:0'), 'validation_loss_bbox': tensor(0.1392, device='cuda:0'), 'validation_loss_giou': tensor(0.4634, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7135, device='cuda:0'), 'train_loss_ce': tensor(0.3938, device='cuda:0'), 'train_loss_bbox': tensor(0.1142, device='cuda:0'), 'train_loss_giou': tensor(0.3742, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0500, device='cuda:0'), 'validation_loss_ce': tensor(0.4449, device='cuda:0'), 'validation_loss_bbox': tensor(0.1333, device='cuda:0'), 'validation_loss_giou': tensor(0.4693, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8719, device='cuda:0'), 'train_loss_ce': tensor(0.4170, device='cuda:0'), 'train_loss_bbox': tensor(0.0880, device='cuda:0'), 'train_loss_giou': tensor(0.5075, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9737, device='cuda:0'), 'validation_loss_ce': tensor(0.4429, device='cuda:0'), 'validation_loss_bbox': tensor(0.1294, device='cuda:0'), 'validation_loss_giou': tensor(0.4419, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9734, device='cuda:0'), 'train_loss_ce': tensor(0.4615, device='cuda:0'), 'train_loss_bbox': tensor(0.1003, device='cuda:0'), 'train_loss_giou': tensor(0.5052, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9729, device='cuda:0'), 'validation_loss_ce': tensor(0.4415, device='cuda:0'), 'validation_loss_bbox': tensor(0.1275, device='cuda:0'), 'validation_loss_giou': tensor(0.4470, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9288, device='cuda:0'), 'train_loss_ce': tensor(0.4898, device='cuda:0'), 'train_loss_bbox': tensor(0.0967, device='cuda:0'), 'train_loss_giou': tensor(0.4778, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0077, device='cuda:0'), 'validation_loss_ce': tensor(0.4397, device='cuda:0'), 'validation_loss_bbox': tensor(0.1310, device='cuda:0'), 'validation_loss_giou': tensor(0.4565, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5813, device='cuda:0'), 'train_loss_ce': tensor(0.3213, device='cuda:0'), 'train_loss_bbox': tensor(0.0890, device='cuda:0'), 'train_loss_giou': tensor(0.4076, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0185, device='cuda:0'), 'validation_loss_ce': tensor(0.4393, device='cuda:0'), 'validation_loss_bbox': tensor(0.1303, device='cuda:0'), 'validation_loss_giou': tensor(0.4639, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5830, device='cuda:0'), 'train_loss_ce': tensor(0.3790, device='cuda:0'), 'train_loss_bbox': tensor(0.1060, device='cuda:0'), 'train_loss_giou': tensor(0.3371, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0351, device='cuda:0'), 'validation_loss_ce': tensor(0.4372, device='cuda:0'), 'validation_loss_bbox': tensor(0.1342, device='cuda:0'), 'validation_loss_giou': tensor(0.4634, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.2645, device='cuda:0'), 'train_loss_ce': tensor(0.4014, device='cuda:0'), 'train_loss_bbox': tensor(0.0714, device='cuda:0'), 'train_loss_giou': tensor(0.2532, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9948, device='cuda:0'), 'validation_loss_ce': tensor(0.4346, device='cuda:0'), 'validation_loss_bbox': tensor(0.1306, device='cuda:0'), 'validation_loss_giou': tensor(0.4536, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.3426, device='cuda:0'), 'train_loss_ce': tensor(0.3139, device='cuda:0'), 'train_loss_bbox': tensor(0.0778, device='cuda:0'), 'train_loss_giou': tensor(0.3199, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9602, device='cuda:0'), 'validation_loss_ce': tensor(0.4345, device='cuda:0'), 'validation_loss_bbox': tensor(0.1249, device='cuda:0'), 'validation_loss_giou': tensor(0.4505, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5074, device='cuda:0'), 'train_loss_ce': tensor(0.4651, device='cuda:0'), 'train_loss_bbox': tensor(0.0795, device='cuda:0'), 'train_loss_giou': tensor(0.3223, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9882, device='cuda:0'), 'validation_loss_ce': tensor(0.4357, device='cuda:0'), 'validation_loss_bbox': tensor(0.1282, device='cuda:0'), 'validation_loss_giou': tensor(0.4558, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6619, device='cuda:0'), 'train_loss_ce': tensor(0.4541, device='cuda:0'), 'train_loss_bbox': tensor(0.1077, device='cuda:0'), 'train_loss_giou': tensor(0.3347, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9714, device='cuda:0'), 'validation_loss_ce': tensor(0.4288, device='cuda:0'), 'validation_loss_bbox': tensor(0.1264, device='cuda:0'), 'validation_loss_giou': tensor(0.4554, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.2751, device='cuda:0'), 'train_loss_ce': tensor(0.4780, device='cuda:0'), 'train_loss_bbox': tensor(0.0599, device='cuda:0'), 'train_loss_giou': tensor(0.2488, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9359, device='cuda:0'), 'validation_loss_ce': tensor(0.4287, device='cuda:0'), 'validation_loss_bbox': tensor(0.1222, device='cuda:0'), 'validation_loss_giou': tensor(0.4481, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.3953, device='cuda:0'), 'train_loss_ce': tensor(0.4210, device='cuda:0'), 'train_loss_bbox': tensor(0.0698, device='cuda:0'), 'train_loss_giou': tensor(0.3127, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9527, device='cuda:0'), 'validation_loss_ce': tensor(0.4282, device='cuda:0'), 'validation_loss_bbox': tensor(0.1249, device='cuda:0'), 'validation_loss_giou': tensor(0.4501, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.2062, device='cuda:0'), 'train_loss_ce': tensor(0.4534, device='cuda:0'), 'train_loss_bbox': tensor(0.0659, device='cuda:0'), 'train_loss_giou': tensor(0.2117, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9332, device='cuda:0'), 'validation_loss_ce': tensor(0.4249, device='cuda:0'), 'validation_loss_bbox': tensor(0.1223, device='cuda:0'), 'validation_loss_giou': tensor(0.4484, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5195, device='cuda:0'), 'train_loss_ce': tensor(0.3928, device='cuda:0'), 'train_loss_bbox': tensor(0.1094, device='cuda:0'), 'train_loss_giou': tensor(0.2898, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9284, device='cuda:0'), 'validation_loss_ce': tensor(0.4224, device='cuda:0'), 'validation_loss_bbox': tensor(0.1230, device='cuda:0'), 'validation_loss_giou': tensor(0.4454, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.1695, device='cuda:0'), 'train_loss_ce': tensor(0.3714, device='cuda:0'), 'train_loss_bbox': tensor(0.0564, device='cuda:0'), 'train_loss_giou': tensor(0.2579, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9271, device='cuda:0'), 'validation_loss_ce': tensor(0.4234, device='cuda:0'), 'validation_loss_bbox': tensor(0.1215, device='cuda:0'), 'validation_loss_giou': tensor(0.4481, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.4215, device='cuda:0'), 'train_loss_ce': tensor(0.4881, device='cuda:0'), 'train_loss_bbox': tensor(0.0761, device='cuda:0'), 'train_loss_giou': tensor(0.2763, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9468, device='cuda:0'), 'validation_loss_ce': tensor(0.4214, device='cuda:0'), 'validation_loss_bbox': tensor(0.1246, device='cuda:0'), 'validation_loss_giou': tensor(0.4512, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.3969, device='cuda:0'), 'train_loss_ce': tensor(0.4695, device='cuda:0'), 'train_loss_bbox': tensor(0.0575, device='cuda:0'), 'train_loss_giou': tensor(0.3200, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9221, device='cuda:0'), 'validation_loss_ce': tensor(0.4188, device='cuda:0'), 'validation_loss_bbox': tensor(0.1234, device='cuda:0'), 'validation_loss_giou': tensor(0.4433, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.3017, device='cuda:0'), 'train_loss_ce': tensor(0.3737, device='cuda:0'), 'train_loss_bbox': tensor(0.0451, device='cuda:0'), 'train_loss_giou': tensor(0.3513, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9424, device='cuda:0'), 'validation_loss_ce': tensor(0.4178, device='cuda:0'), 'validation_loss_bbox': tensor(0.1247, device='cuda:0'), 'validation_loss_giou': tensor(0.4505, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.8226, device='cuda:0'), 'train_loss_ce': tensor(0.2608, device='cuda:0'), 'train_loss_bbox': tensor(0.0339, device='cuda:0'), 'train_loss_giou': tensor(0.1962, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9638, device='cuda:0'), 'validation_loss_ce': tensor(0.4177, device='cuda:0'), 'validation_loss_bbox': tensor(0.1261, device='cuda:0'), 'validation_loss_giou': tensor(0.4579, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.9972, device='cuda:0'), 'train_loss_ce': tensor(0.4199, device='cuda:0'), 'train_loss_bbox': tensor(0.0402, device='cuda:0'), 'train_loss_giou': tensor(0.1882, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9488, device='cuda:0'), 'validation_loss_ce': tensor(0.4148, device='cuda:0'), 'validation_loss_bbox': tensor(0.1252, device='cuda:0'), 'validation_loss_giou': tensor(0.4539, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.2127, device='cuda:0'), 'train_loss_ce': tensor(0.3963, device='cuda:0'), 'train_loss_bbox': tensor(0.0675, device='cuda:0'), 'train_loss_giou': tensor(0.2394, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9382, device='cuda:0'), 'validation_loss_ce': tensor(0.4113, device='cuda:0'), 'validation_loss_bbox': tensor(0.1234, device='cuda:0'), 'validation_loss_giou': tensor(0.4550, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.4711, device='cuda:0'), 'train_loss_ce': tensor(0.4774, device='cuda:0'), 'train_loss_bbox': tensor(0.0708, device='cuda:0'), 'train_loss_giou': tensor(0.3198, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9266, device='cuda:0'), 'validation_loss_ce': tensor(0.4101, device='cuda:0'), 'validation_loss_bbox': tensor(0.1233, device='cuda:0'), 'validation_loss_giou': tensor(0.4500, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.9959, device='cuda:0'), 'train_loss_ce': tensor(0.3633, device='cuda:0'), 'train_loss_bbox': tensor(0.0561, device='cuda:0'), 'train_loss_giou': tensor(0.1760, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9331, device='cuda:0'), 'validation_loss_ce': tensor(0.4114, device='cuda:0'), 'validation_loss_bbox': tensor(0.1232, device='cuda:0'), 'validation_loss_giou': tensor(0.4529, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.2761, device='cuda:0'), 'train_loss_ce': tensor(0.3369, device='cuda:0'), 'train_loss_bbox': tensor(0.0609, device='cuda:0'), 'train_loss_giou': tensor(0.3174, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8959, device='cuda:0'), 'validation_loss_ce': tensor(0.4092, device='cuda:0'), 'validation_loss_bbox': tensor(0.1196, device='cuda:0'), 'validation_loss_giou': tensor(0.4443, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.1052, device='cuda:0'), 'train_loss_ce': tensor(0.4021, device='cuda:0'), 'train_loss_bbox': tensor(0.0450, device='cuda:0'), 'train_loss_giou': tensor(0.2390, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9103, device='cuda:0'), 'validation_loss_ce': tensor(0.4082, device='cuda:0'), 'validation_loss_bbox': tensor(0.1223, device='cuda:0'), 'validation_loss_giou': tensor(0.4453, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.0489, device='cuda:0'), 'train_loss_ce': tensor(0.4296, device='cuda:0'), 'train_loss_bbox': tensor(0.0439, device='cuda:0'), 'train_loss_giou': tensor(0.2000, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9410, device='cuda:0'), 'validation_loss_ce': tensor(0.4067, device='cuda:0'), 'validation_loss_bbox': tensor(0.1275, device='cuda:0'), 'validation_loss_giou': tensor(0.4484, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.0332, device='cuda:0'), 'train_loss_ce': tensor(0.3963, device='cuda:0'), 'train_loss_bbox': tensor(0.0597, device='cuda:0'), 'train_loss_giou': tensor(0.1693, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9021, device='cuda:0'), 'validation_loss_ce': tensor(0.4044, device='cuda:0'), 'validation_loss_bbox': tensor(0.1204, device='cuda:0'), 'validation_loss_giou': tensor(0.4479, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.3650, device='cuda:0'), 'train_loss_ce': tensor(0.4742, device='cuda:0'), 'train_loss_bbox': tensor(0.0558, device='cuda:0'), 'train_loss_giou': tensor(0.3059, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9119, device='cuda:0'), 'validation_loss_ce': tensor(0.4054, device='cuda:0'), 'validation_loss_bbox': tensor(0.1221, device='cuda:0'), 'validation_loss_giou': tensor(0.4479, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.2805, device='cuda:0'), 'train_loss_ce': tensor(0.4037, device='cuda:0'), 'train_loss_bbox': tensor(0.0486, device='cuda:0'), 'train_loss_giou': tensor(0.3169, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8817, device='cuda:0'), 'validation_loss_ce': tensor(0.4047, device='cuda:0'), 'validation_loss_bbox': tensor(0.1203, device='cuda:0'), 'validation_loss_giou': tensor(0.4377, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.1888, device='cuda:0'), 'train_loss_ce': tensor(0.4283, device='cuda:0'), 'train_loss_bbox': tensor(0.0574, device='cuda:0'), 'train_loss_giou': tensor(0.2369, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8818, device='cuda:0'), 'validation_loss_ce': tensor(0.4025, device='cuda:0'), 'validation_loss_bbox': tensor(0.1179, device='cuda:0'), 'validation_loss_giou': tensor(0.4451, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.7404, device='cuda:0'), 'train_loss_ce': tensor(0.3634, device='cuda:0'), 'train_loss_bbox': tensor(0.0316, device='cuda:0'), 'train_loss_giou': tensor(0.1096, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8977, device='cuda:0'), 'validation_loss_ce': tensor(0.4013, device='cuda:0'), 'validation_loss_bbox': tensor(0.1235, device='cuda:0'), 'validation_loss_giou': tensor(0.4395, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.0661, device='cuda:0'), 'train_loss_ce': tensor(0.4053, device='cuda:0'), 'train_loss_bbox': tensor(0.0441, device='cuda:0'), 'train_loss_giou': tensor(0.2203, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8821, device='cuda:0'), 'validation_loss_ce': tensor(0.3989, device='cuda:0'), 'validation_loss_bbox': tensor(0.1186, device='cuda:0'), 'validation_loss_giou': tensor(0.4450, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.7028, device='cuda:0'), 'train_loss_ce': tensor(0.3904, device='cuda:0'), 'train_loss_bbox': tensor(0.0235, device='cuda:0'), 'train_loss_giou': tensor(0.0974, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.9134, device='cuda:0'), 'validation_loss_ce': tensor(0.3996, device='cuda:0'), 'validation_loss_bbox': tensor(0.1234, device='cuda:0'), 'validation_loss_giou': tensor(0.4485, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.7978, device='cuda:0'), 'train_loss_ce': tensor(0.3985, device='cuda:0'), 'train_loss_bbox': tensor(0.0377, device='cuda:0'), 'train_loss_giou': tensor(0.1054, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9087, device='cuda:0'), 'validation_loss_ce': tensor(0.3957, device='cuda:0'), 'validation_loss_bbox': tensor(0.1230, device='cuda:0'), 'validation_loss_giou': tensor(0.4489, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.9359, device='cuda:0'), 'train_loss_ce': tensor(0.4104, device='cuda:0'), 'train_loss_bbox': tensor(0.0329, device='cuda:0'), 'train_loss_giou': tensor(0.1804, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8785, device='cuda:0'), 'validation_loss_ce': tensor(0.3954, device='cuda:0'), 'validation_loss_bbox': tensor(0.1187, device='cuda:0'), 'validation_loss_giou': tensor(0.4448, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.4489, device='cuda:0'), 'train_loss_ce': tensor(0.3335, device='cuda:0'), 'train_loss_bbox': tensor(0.0751, device='cuda:0'), 'train_loss_giou': tensor(0.3699, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8740, device='cuda:0'), 'validation_loss_ce': tensor(0.3949, device='cuda:0'), 'validation_loss_bbox': tensor(0.1199, device='cuda:0'), 'validation_loss_giou': tensor(0.4397, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.8472, device='cuda:0'), 'train_loss_ce': tensor(0.3181, device='cuda:0'), 'train_loss_bbox': tensor(0.0378, device='cuda:0'), 'train_loss_giou': tensor(0.1699, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8785, device='cuda:0'), 'validation_loss_ce': tensor(0.3940, device='cuda:0'), 'validation_loss_bbox': tensor(0.1190, device='cuda:0'), 'validation_loss_giou': tensor(0.4448, device='cuda:0'), 'validation_cardinality_error': tensor(0.9697, device='cuda:0')}
{'training_loss': tensor(1.0123, device='cuda:0'), 'train_loss_ce': tensor(0.4111, device='cuda:0'), 'train_loss_bbox': tensor(0.0362, device='cuda:0'), 'train_loss_giou': tensor(0.2100, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9187, device='cuda:0'), 'validation_loss_ce': tensor(0.3924, device='cuda:0'), 'validation_loss_bbox': tensor(0.1253, device='cuda:0'), 'validation_loss_giou': tensor(0.4500, device='cuda:0'), 'validation_cardinality_error': tensor(0.9899, device='cuda:0')}
{'training_loss': tensor(0.5481, device='cuda:0'), 'train_loss_ce': tensor(0.2719, device='cuda:0'), 'train_loss_bbox': tensor(0.0257, device='cuda:0'), 'train_loss_giou': tensor(0.0739, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9145, device='cuda:0'), 'validation_loss_ce': tensor(0.3937, device='cuda:0'), 'validation_loss_bbox': tensor(0.1219, device='cuda:0'), 'validation_loss_giou': tensor(0.4556, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.0651, device='cuda:0'), 'train_loss_ce': tensor(0.3829, device='cuda:0'), 'train_loss_bbox': tensor(0.0515, device='cuda:0'), 'train_loss_giou': tensor(0.2123, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8978, device='cuda:0'), 'validation_loss_ce': tensor(0.3919, device='cuda:0'), 'validation_loss_bbox': tensor(0.1215, device='cuda:0'), 'validation_loss_giou': tensor(0.4491, device='cuda:0'), 'validation_cardinality_error': tensor(0.9899, device='cuda:0')}

Examples

{'size': tensor([512, 512]), 'image_id': tensor([1]), 'class_labels': tensor([4]), 'boxes': tensor([[0.2622, 0.5729, 0.0847, 0.0773]]), 'area': tensor([1717.9431]), 'iscrowd': tensor([0]), 'orig_size': tensor([1024, 1024])}

Example

Downloads last month
50
Safetensors
Model size
6.47M params
Tensor type
F32
·
Inference Examples
Object Detection
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.