Update README file

README.md

@@ -13,28 +13,28 @@ IoU metric: bbox
  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 ] = 0.000
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.004
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.001
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.002
  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 ] = 0.004
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.002
 ```
 
 ## After training result
 ```
 IoU metric: bbox
- Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.040
- Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.071
- Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.047
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.028
+ Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.075
+ Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.021
  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 ] = 0.044
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.131
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.198
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.227
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.029
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.089
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.152
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.166
  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 ] = 0.018
- Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.247
+ 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 ] = 0.168
 ```
 
 ## Config
@@ -42,44 +42,44 @@ IoU metric: bbox
 - original model: hustvl/yolos-tiny
 - lr: 0.0001
 - dropout_rate: 0.1
-- weight_decay: 0.1
+- weight_decay: 1.0
 - max_epochs: 30
 - train samples: 885
 
 ## Logging
 ### Training process
 ```
-{'validation_loss': tensor(7.0933, device='cuda:0'), 'validation_loss_ce': tensor(2.6325, device='cuda:0'), 'validation_loss_bbox': tensor(0.5049, device='cuda:0'), 'validation_loss_giou': tensor(0.9681, device='cuda:0'), 'validation_cardinality_error': tensor(99., device='cuda:0')}
-{'training_loss': tensor(2.2101, device='cuda:0'), 'train_loss_ce': tensor(0.4669, device='cuda:0'), 'train_loss_bbox': tensor(0.1601, device='cuda:0'), 'train_loss_giou': tensor(0.4713, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4272, device='cuda:0'), 'validation_loss_ce': tensor(0.4454, device='cuda:0'), 'validation_loss_bbox': tensor(0.1814, device='cuda:0'), 'validation_loss_giou': tensor(0.5375, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.7165, device='cuda:0'), 'train_loss_ce': tensor(0.4522, device='cuda:0'), 'train_loss_bbox': tensor(0.1315, device='cuda:0'), 'train_loss_giou': tensor(0.3035, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2316, device='cuda:0'), 'validation_loss_ce': tensor(0.4329, device='cuda:0'), 'validation_loss_bbox': tensor(0.1506, device='cuda:0'), 'validation_loss_giou': tensor(0.5228, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.4262, device='cuda:0'), 'train_loss_ce': tensor(0.4559, device='cuda:0'), 'train_loss_bbox': tensor(0.1564, device='cuda:0'), 'train_loss_giou': tensor(0.5942, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1372, device='cuda:0'), 'validation_loss_ce': tensor(0.4360, device='cuda:0'), 'validation_loss_bbox': tensor(0.1478, device='cuda:0'), 'validation_loss_giou': tensor(0.4811, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.1364, device='cuda:0'), 'train_loss_ce': tensor(0.4127, device='cuda:0'), 'train_loss_bbox': tensor(0.1297, device='cuda:0'), 'train_loss_giou': tensor(0.5375, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1923, device='cuda:0'), 'validation_loss_ce': tensor(0.4127, device='cuda:0'), 'validation_loss_bbox': tensor(0.1510, device='cuda:0'), 'validation_loss_giou': tensor(0.5122, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.1083, device='cuda:0'), 'train_loss_ce': tensor(0.3250, device='cuda:0'), 'train_loss_bbox': tensor(0.1613, device='cuda:0'), 'train_loss_giou': tensor(0.4884, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0341, device='cuda:0'), 'validation_loss_ce': tensor(0.4116, device='cuda:0'), 'validation_loss_bbox': tensor(0.1375, device='cuda:0'), 'validation_loss_giou': tensor(0.4674, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.1673, device='cuda:0'), 'train_loss_ce': tensor(0.4102, device='cuda:0'), 'train_loss_bbox': tensor(0.1334, device='cuda:0'), 'train_loss_giou': tensor(0.5452, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0928, device='cuda:0'), 'validation_loss_ce': tensor(0.3856, device='cuda:0'), 'validation_loss_bbox': tensor(0.1463, device='cuda:0'), 'validation_loss_giou': tensor(0.4878, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.7178, device='cuda:0'), 'train_loss_ce': tensor(0.4061, device='cuda:0'), 'train_loss_bbox': tensor(0.0982, device='cuda:0'), 'train_loss_giou': tensor(0.4103, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1328, device='cuda:0'), 'validation_loss_ce': tensor(0.3973, device='cuda:0'), 'validation_loss_bbox': tensor(0.1413, device='cuda:0'), 'validation_loss_giou': tensor(0.5145, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.2961, device='cuda:0'), 'train_loss_ce': tensor(0.3717, device='cuda:0'), 'train_loss_bbox': tensor(0.1444, device='cuda:0'), 'train_loss_giou': tensor(0.6012, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9445, device='cuda:0'), 'validation_loss_ce': tensor(0.3745, device='cuda:0'), 'validation_loss_bbox': tensor(0.1293, device='cuda:0'), 'validation_loss_giou': tensor(0.4619, device='cuda:0'), 'validation_cardinality_error': tensor(0.8990, device='cuda:0')}
-{'training_loss': tensor(2.0082, device='cuda:0'), 'train_loss_ce': tensor(0.4834, device='cuda:0'), 'train_loss_bbox': tensor(0.1454, device='cuda:0'), 'train_loss_giou': tensor(0.3990, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8980, device='cuda:0'), 'validation_loss_ce': tensor(0.3738, device='cuda:0'), 'validation_loss_bbox': tensor(0.1218, device='cuda:0'), 'validation_loss_giou': tensor(0.4576, device='cuda:0'), 'validation_cardinality_error': tensor(0.8182, device='cuda:0')}
-{'training_loss': tensor(2.5432, device='cuda:0'), 'train_loss_ce': tensor(0.4593, device='cuda:0'), 'train_loss_bbox': tensor(0.1676, device='cuda:0'), 'train_loss_giou': tensor(0.6229, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9865, device='cuda:0'), 'validation_loss_ce': tensor(0.3900, device='cuda:0'), 'validation_loss_bbox': tensor(0.1392, device='cuda:0'), 'validation_loss_giou': tensor(0.4503, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.9886, device='cuda:0'), 'train_loss_ce': tensor(0.3825, device='cuda:0'), 'train_loss_bbox': tensor(0.1169, device='cuda:0'), 'train_loss_giou': tensor(0.5109, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9185, device='cuda:0'), 'validation_loss_ce': tensor(0.3755, device='cuda:0'), 'validation_loss_bbox': tensor(0.1302, device='cuda:0'), 'validation_loss_giou': tensor(0.4460, device='cuda:0'), 'validation_cardinality_error': tensor(0.9697, device='cuda:0')}
-{'training_loss': tensor(1.4652, device='cuda:0'), 'train_loss_ce': tensor(0.3647, device='cuda:0'), 'train_loss_bbox': tensor(0.0751, device='cuda:0'), 'train_loss_giou': tensor(0.3625, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.9299, device='cuda:0'), 'validation_loss_ce': tensor(0.3658, device='cuda:0'), 'validation_loss_bbox': tensor(0.1326, device='cuda:0'), 'validation_loss_giou': tensor(0.4505, device='cuda:0'), 'validation_cardinality_error': tensor(0.3434, device='cuda:0')}
-{'training_loss': tensor(1.8145, device='cuda:0'), 'train_loss_ce': tensor(0.4718, device='cuda:0'), 'train_loss_bbox': tensor(0.0969, device='cuda:0'), 'train_loss_giou': tensor(0.4291, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.9555, device='cuda:0'), 'validation_loss_ce': tensor(0.3583, device='cuda:0'), 'validation_loss_bbox': tensor(0.1334, device='cuda:0'), 'validation_loss_giou': tensor(0.4650, device='cuda:0'), 'validation_cardinality_error': tensor(0.5152, device='cuda:0')}
-{'training_loss': tensor(2.0291, device='cuda:0'), 'train_loss_ce': tensor(0.3718, device='cuda:0'), 'train_loss_bbox': tensor(0.1291, device='cuda:0'), 'train_loss_giou': tensor(0.5060, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3917, device='cuda:0'), 'validation_loss_ce': tensor(0.3621, device='cuda:0'), 'validation_loss_bbox': tensor(0.1767, device='cuda:0'), 'validation_loss_giou': tensor(0.5731, device='cuda:0'), 'validation_cardinality_error': tensor(0.7879, device='cuda:0')}
-{'training_loss': tensor(2.1299, device='cuda:0'), 'train_loss_ce': tensor(0.4300, device='cuda:0'), 'train_loss_bbox': tensor(0.1054, device='cuda:0'), 'train_loss_giou': tensor(0.5863, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1091, device='cuda:0'), 'validation_loss_ce': tensor(0.3579, device='cuda:0'), 'validation_loss_bbox': tensor(0.1479, device='cuda:0'), 'validation_loss_giou': tensor(0.5058, device='cuda:0'), 'validation_cardinality_error': tensor(0.6061, device='cuda:0')}
-{'training_loss': tensor(2.0963, device='cuda:0'), 'train_loss_ce': tensor(0.2759, device='cuda:0'), 'train_loss_bbox': tensor(0.1520, device='cuda:0'), 'train_loss_giou': tensor(0.5301, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.0418, device='cuda:0'), 'validation_loss_ce': tensor(0.3464, device='cuda:0'), 'validation_loss_bbox': tensor(0.1385, device='cuda:0'), 'validation_loss_giou': tensor(0.5015, device='cuda:0'), 'validation_cardinality_error': tensor(0.6263, device='cuda:0')}
-{'training_loss': tensor(2.1784, device='cuda:0'), 'train_loss_ce': tensor(0.3634, device='cuda:0'), 'train_loss_bbox': tensor(0.1741, device='cuda:0'), 'train_loss_giou': tensor(0.4723, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9543, device='cuda:0'), 'validation_loss_ce': tensor(0.3518, device='cuda:0'), 'validation_loss_bbox': tensor(0.1322, device='cuda:0'), 'validation_loss_giou': tensor(0.4707, device='cuda:0'), 'validation_cardinality_error': tensor(0.9495, device='cuda:0')}
-{'training_loss': tensor(2.0823, device='cuda:0'), 'train_loss_ce': tensor(0.3437, device='cuda:0'), 'train_loss_bbox': tensor(0.1144, device='cuda:0'), 'train_loss_giou': tensor(0.5833, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8429, device='cuda:0'), 'validation_loss_ce': tensor(0.3513, device='cuda:0'), 'validation_loss_bbox': tensor(0.1216, device='cuda:0'), 'validation_loss_giou': tensor(0.4417, device='cuda:0'), 'validation_cardinality_error': tensor(0.8687, device='cuda:0')}
-{'training_loss': tensor(1.4899, device='cuda:0'), 'train_loss_ce': tensor(0.3300, device='cuda:0'), 'train_loss_bbox': tensor(0.0826, device='cuda:0'), 'train_loss_giou': tensor(0.3734, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8750, device='cuda:0'), 'validation_loss_ce': tensor(0.3539, device='cuda:0'), 'validation_loss_bbox': tensor(0.1210, device='cuda:0'), 'validation_loss_giou': tensor(0.4580, device='cuda:0'), 'validation_cardinality_error': tensor(0.7273, device='cuda:0')}
-{'training_loss': tensor(2.2234, device='cuda:0'), 'train_loss_ce': tensor(0.3947, device='cuda:0'), 'train_loss_bbox': tensor(0.1587, device='cuda:0'), 'train_loss_giou': tensor(0.5175, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.9507, device='cuda:0'), 'validation_loss_ce': tensor(0.3356, device='cuda:0'), 'validation_loss_bbox': tensor(0.1303, device='cuda:0'), 'validation_loss_giou': tensor(0.4817, device='cuda:0'), 'validation_cardinality_error': tensor(0.5657, device='cuda:0')}
-{'training_loss': tensor(1.5594, device='cuda:0'), 'train_loss_ce': tensor(0.3898, device='cuda:0'), 'train_loss_bbox': tensor(0.1000, device='cuda:0'), 'train_loss_giou': tensor(0.3347, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9082, device='cuda:0'), 'validation_loss_ce': tensor(0.3350, device='cuda:0'), 'validation_loss_bbox': tensor(0.1296, device='cuda:0'), 'validation_loss_giou': tensor(0.4626, device='cuda:0'), 'validation_cardinality_error': tensor(0.5859, device='cuda:0')}
-{'training_loss': tensor(1.3733, device='cuda:0'), 'train_loss_ce': tensor(0.2466, device='cuda:0'), 'train_loss_bbox': tensor(0.0828, device='cuda:0'), 'train_loss_giou': tensor(0.3563, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8808, device='cuda:0'), 'validation_loss_ce': tensor(0.3422, device='cuda:0'), 'validation_loss_bbox': tensor(0.1253, device='cuda:0'), 'validation_loss_giou': tensor(0.4559, device='cuda:0'), 'validation_cardinality_error': tensor(0.7273, device='cuda:0')}
-{'training_loss': tensor(1.9375, device='cuda:0'), 'train_loss_ce': tensor(0.3146, device='cuda:0'), 'train_loss_bbox': tensor(0.1273, device='cuda:0'), 'train_loss_giou': tensor(0.4931, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8543, device='cuda:0'), 'validation_loss_ce': tensor(0.3441, device='cuda:0'), 'validation_loss_bbox': tensor(0.1196, device='cuda:0'), 'validation_loss_giou': tensor(0.4561, device='cuda:0'), 'validation_cardinality_error': tensor(0.7879, device='cuda:0')}
-{'training_loss': tensor(1.7360, device='cuda:0'), 'train_loss_ce': tensor(0.2615, device='cuda:0'), 'train_loss_bbox': tensor(0.1172, device='cuda:0'), 'train_loss_giou': tensor(0.4441, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8177, device='cuda:0'), 'validation_loss_ce': tensor(0.3491, device='cuda:0'), 'validation_loss_bbox': tensor(0.1182, device='cuda:0'), 'validation_loss_giou': tensor(0.4387, device='cuda:0'), 'validation_cardinality_error': tensor(0.6465, device='cuda:0')}
-{'training_loss': tensor(1.4278, device='cuda:0'), 'train_loss_ce': tensor(0.4191, device='cuda:0'), 'train_loss_bbox': tensor(0.0621, device='cuda:0'), 'train_loss_giou': tensor(0.3491, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.7745, device='cuda:0'), 'validation_loss_ce': tensor(0.3331, device='cuda:0'), 'validation_loss_bbox': tensor(0.1184, device='cuda:0'), 'validation_loss_giou': tensor(0.4248, device='cuda:0'), 'validation_cardinality_error': tensor(0.5152, device='cuda:0')}
-{'training_loss': tensor(1.5275, device='cuda:0'), 'train_loss_ce': tensor(0.2538, device='cuda:0'), 'train_loss_bbox': tensor(0.1081, device='cuda:0'), 'train_loss_giou': tensor(0.3666, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.7723, device='cuda:0'), 'validation_loss_ce': tensor(0.3335, device='cuda:0'), 'validation_loss_bbox': tensor(0.1156, device='cuda:0'), 'validation_loss_giou': tensor(0.4303, device='cuda:0'), 'validation_cardinality_error': tensor(0.5657, device='cuda:0')}
-{'training_loss': tensor(1.2553, device='cuda:0'), 'train_loss_ce': tensor(0.2647, device='cuda:0'), 'train_loss_bbox': tensor(0.0725, device='cuda:0'), 'train_loss_giou': tensor(0.3140, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.7969, device='cuda:0'), 'validation_loss_ce': tensor(0.3384, device='cuda:0'), 'validation_loss_bbox': tensor(0.1183, device='cuda:0'), 'validation_loss_giou': tensor(0.4334, device='cuda:0'), 'validation_cardinality_error': tensor(0.6667, device='cuda:0')}
-{'training_loss': tensor(2.2105, device='cuda:0'), 'train_loss_ce': tensor(0.4101, device='cuda:0'), 'train_loss_bbox': tensor(0.1634, device='cuda:0'), 'train_loss_giou': tensor(0.4917, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.7978, device='cuda:0'), 'validation_loss_ce': tensor(0.3421, device='cuda:0'), 'validation_loss_bbox': tensor(0.1197, device='cuda:0'), 'validation_loss_giou': tensor(0.4286, device='cuda:0'), 'validation_cardinality_error': tensor(0.7677, device='cuda:0')}
-{'training_loss': tensor(1.3302, device='cuda:0'), 'train_loss_ce': tensor(0.3538, device='cuda:0'), 'train_loss_bbox': tensor(0.0723, device='cuda:0'), 'train_loss_giou': tensor(0.3074, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.8850, device='cuda:0'), 'validation_loss_ce': tensor(0.3273, device='cuda:0'), 'validation_loss_bbox': tensor(0.1313, device='cuda:0'), 'validation_loss_giou': tensor(0.4507, device='cuda:0'), 'validation_cardinality_error': tensor(0.5960, device='cuda:0')}
-{'training_loss': tensor(1.5171, device='cuda:0'), 'train_loss_ce': tensor(0.3285, device='cuda:0'), 'train_loss_bbox': tensor(0.0630, device='cuda:0'), 'train_loss_giou': tensor(0.4368, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.7658, device='cuda:0'), 'validation_loss_ce': tensor(0.3375, device='cuda:0'), 'validation_loss_bbox': tensor(0.1182, device='cuda:0'), 'validation_loss_giou': tensor(0.4186, device='cuda:0'), 'validation_cardinality_error': tensor(0.7273, device='cuda:0')}
+{'validation_loss': tensor(7.2510, device='cuda:0'), 'validation_loss_ce': tensor(2.7062, device='cuda:0'), 'validation_loss_bbox': tensor(0.5285, device='cuda:0'), 'validation_loss_giou': tensor(0.9513, device='cuda:0'), 'validation_cardinality_error': tensor(99., device='cuda:0')}
+{'training_loss': tensor(2.0733, device='cuda:0'), 'train_loss_ce': tensor(0.4772, device='cuda:0'), 'train_loss_bbox': tensor(0.1542, device='cuda:0'), 'train_loss_giou': tensor(0.4126, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3407, device='cuda:0'), 'validation_loss_ce': tensor(0.4447, device='cuda:0'), 'validation_loss_bbox': tensor(0.1600, device='cuda:0'), 'validation_loss_giou': tensor(0.5479, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.3671, device='cuda:0'), 'train_loss_ce': tensor(0.3991, device='cuda:0'), 'train_loss_bbox': tensor(0.1568, device='cuda:0'), 'train_loss_giou': tensor(0.5919, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3726, device='cuda:0'), 'validation_loss_ce': tensor(0.4201, device='cuda:0'), 'validation_loss_bbox': tensor(0.1725, device='cuda:0'), 'validation_loss_giou': tensor(0.5451, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.8530, device='cuda:0'), 'train_loss_ce': tensor(0.4628, device='cuda:0'), 'train_loss_bbox': tensor(0.2022, device='cuda:0'), 'train_loss_giou': tensor(0.6896, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1740, device='cuda:0'), 'validation_loss_ce': tensor(0.4275, device='cuda:0'), 'validation_loss_bbox': tensor(0.1443, device='cuda:0'), 'validation_loss_giou': tensor(0.5126, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.4427, device='cuda:0'), 'train_loss_ce': tensor(0.4072, device='cuda:0'), 'train_loss_bbox': tensor(0.1748, device='cuda:0'), 'train_loss_giou': tensor(0.5806, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1416, device='cuda:0'), 'validation_loss_ce': tensor(0.4228, device='cuda:0'), 'validation_loss_bbox': tensor(0.1418, device='cuda:0'), 'validation_loss_giou': tensor(0.5049, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.2765, device='cuda:0'), 'train_loss_ce': tensor(0.4684, device='cuda:0'), 'train_loss_bbox': tensor(0.1437, device='cuda:0'), 'train_loss_giou': tensor(0.5449, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1062, device='cuda:0'), 'validation_loss_ce': tensor(0.4127, device='cuda:0'), 'validation_loss_bbox': tensor(0.1439, device='cuda:0'), 'validation_loss_giou': tensor(0.4869, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.9443, device='cuda:0'), 'train_loss_ce': tensor(0.3799, device='cuda:0'), 'train_loss_bbox': tensor(0.1032, device='cuda:0'), 'train_loss_giou': tensor(0.5243, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9993, device='cuda:0'), 'validation_loss_ce': tensor(0.4028, device='cuda:0'), 'validation_loss_bbox': tensor(0.1352, device='cuda:0'), 'validation_loss_giou': tensor(0.4602, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.7868, device='cuda:0'), 'train_loss_ce': tensor(0.3504, device='cuda:0'), 'train_loss_bbox': tensor(0.1213, device='cuda:0'), 'train_loss_giou': tensor(0.4149, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0064, device='cuda:0'), 'validation_loss_ce': tensor(0.3905, device='cuda:0'), 'validation_loss_bbox': tensor(0.1337, device='cuda:0'), 'validation_loss_giou': tensor(0.4736, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.8019, device='cuda:0'), 'train_loss_ce': tensor(0.3278, device='cuda:0'), 'train_loss_bbox': tensor(0.0954, device='cuda:0'), 'train_loss_giou': tensor(0.4986, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0142, device='cuda:0'), 'validation_loss_ce': tensor(0.3723, device='cuda:0'), 'validation_loss_bbox': tensor(0.1391, device='cuda:0'), 'validation_loss_giou': tensor(0.4733, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.7681, device='cuda:0'), 'train_loss_ce': tensor(0.2725, device='cuda:0'), 'train_loss_bbox': tensor(0.1038, device='cuda:0'), 'train_loss_giou': tensor(0.4883, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0256, device='cuda:0'), 'validation_loss_ce': tensor(0.3890, device='cuda:0'), 'validation_loss_bbox': tensor(0.1334, device='cuda:0'), 'validation_loss_giou': tensor(0.4848, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.7969, device='cuda:0'), 'train_loss_ce': tensor(0.3935, device='cuda:0'), 'train_loss_bbox': tensor(0.1829, device='cuda:0'), 'train_loss_giou': tensor(0.7444, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0852, device='cuda:0'), 'validation_loss_ce': tensor(0.3799, device='cuda:0'), 'validation_loss_bbox': tensor(0.1377, device='cuda:0'), 'validation_loss_giou': tensor(0.5084, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.2780, device='cuda:0'), 'train_loss_ce': tensor(0.3727, device='cuda:0'), 'train_loss_bbox': tensor(0.1636, device='cuda:0'), 'train_loss_giou': tensor(0.5436, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8908, device='cuda:0'), 'validation_loss_ce': tensor(0.3772, device='cuda:0'), 'validation_loss_bbox': tensor(0.1258, device='cuda:0'), 'validation_loss_giou': tensor(0.4424, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.1853, device='cuda:0'), 'train_loss_ce': tensor(0.4098, device='cuda:0'), 'train_loss_bbox': tensor(0.1223, device='cuda:0'), 'train_loss_giou': tensor(0.5820, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8623, device='cuda:0'), 'validation_loss_ce': tensor(0.3716, device='cuda:0'), 'validation_loss_bbox': tensor(0.1160, device='cuda:0'), 'validation_loss_giou': tensor(0.4554, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.1250, device='cuda:0'), 'train_loss_ce': tensor(0.3339, device='cuda:0'), 'train_loss_bbox': tensor(0.1228, device='cuda:0'), 'train_loss_giou': tensor(0.5886, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8199, device='cuda:0'), 'validation_loss_ce': tensor(0.3661, device='cuda:0'), 'validation_loss_bbox': tensor(0.1161, device='cuda:0'), 'validation_loss_giou': tensor(0.4366, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.8382, device='cuda:0'), 'train_loss_ce': tensor(0.3676, device='cuda:0'), 'train_loss_bbox': tensor(0.1031, device='cuda:0'), 'train_loss_giou': tensor(0.4776, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9126, device='cuda:0'), 'validation_loss_ce': tensor(0.3584, device='cuda:0'), 'validation_loss_bbox': tensor(0.1291, device='cuda:0'), 'validation_loss_giou': tensor(0.4544, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.2184, device='cuda:0'), 'train_loss_ce': tensor(0.3580, device='cuda:0'), 'train_loss_bbox': tensor(0.1687, device='cuda:0'), 'train_loss_giou': tensor(0.5085, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9112, device='cuda:0'), 'validation_loss_ce': tensor(0.3618, device='cuda:0'), 'validation_loss_bbox': tensor(0.1275, device='cuda:0'), 'validation_loss_giou': tensor(0.4559, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.4304, device='cuda:0'), 'train_loss_ce': tensor(0.2193, device='cuda:0'), 'train_loss_bbox': tensor(0.0824, device='cuda:0'), 'train_loss_giou': tensor(0.3997, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9278, device='cuda:0'), 'validation_loss_ce': tensor(0.3509, device='cuda:0'), 'validation_loss_bbox': tensor(0.1320, device='cuda:0'), 'validation_loss_giou': tensor(0.4585, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.8228, device='cuda:0'), 'train_loss_ce': tensor(0.4408, device='cuda:0'), 'train_loss_bbox': tensor(0.1186, device='cuda:0'), 'train_loss_giou': tensor(0.3946, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8695, device='cuda:0'), 'validation_loss_ce': tensor(0.3668, device='cuda:0'), 'validation_loss_bbox': tensor(0.1232, device='cuda:0'), 'validation_loss_giou': tensor(0.4434, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.4936, device='cuda:0'), 'train_loss_ce': tensor(0.2966, device='cuda:0'), 'train_loss_bbox': tensor(0.0936, device='cuda:0'), 'train_loss_giou': tensor(0.3645, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8164, device='cuda:0'), 'validation_loss_ce': tensor(0.3554, device='cuda:0'), 'validation_loss_bbox': tensor(0.1208, device='cuda:0'), 'validation_loss_giou': tensor(0.4286, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.5842, device='cuda:0'), 'train_loss_ce': tensor(0.3072, device='cuda:0'), 'train_loss_bbox': tensor(0.0867, device='cuda:0'), 'train_loss_giou': tensor(0.4217, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9658, device='cuda:0'), 'validation_loss_ce': tensor(0.3572, device='cuda:0'), 'validation_loss_bbox': tensor(0.1300, device='cuda:0'), 'validation_loss_giou': tensor(0.4792, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.4302, device='cuda:0'), 'train_loss_ce': tensor(0.3983, device='cuda:0'), 'train_loss_bbox': tensor(0.0977, device='cuda:0'), 'train_loss_giou': tensor(0.2716, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9079, device='cuda:0'), 'validation_loss_ce': tensor(0.3678, device='cuda:0'), 'validation_loss_bbox': tensor(0.1266, device='cuda:0'), 'validation_loss_giou': tensor(0.4535, device='cuda:0'), 'validation_cardinality_error': tensor(0.9596, device='cuda:0')}
+{'training_loss': tensor(1.8392, device='cuda:0'), 'train_loss_ce': tensor(0.3940, device='cuda:0'), 'train_loss_bbox': tensor(0.1368, device='cuda:0'), 'train_loss_giou': tensor(0.3806, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1207, device='cuda:0'), 'validation_loss_ce': tensor(0.3700, device='cuda:0'), 'validation_loss_bbox': tensor(0.1498, device='cuda:0'), 'validation_loss_giou': tensor(0.5008, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.0952, device='cuda:0'), 'train_loss_ce': tensor(0.3566, device='cuda:0'), 'train_loss_bbox': tensor(0.1601, device='cuda:0'), 'train_loss_giou': tensor(0.4692, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0796, device='cuda:0'), 'validation_loss_ce': tensor(0.4127, device='cuda:0'), 'validation_loss_bbox': tensor(0.1413, device='cuda:0'), 'validation_loss_giou': tensor(0.4801, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.7375, device='cuda:0'), 'train_loss_ce': tensor(0.3531, device='cuda:0'), 'train_loss_bbox': tensor(0.1156, device='cuda:0'), 'train_loss_giou': tensor(0.4033, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9825, device='cuda:0'), 'validation_loss_ce': tensor(0.3733, device='cuda:0'), 'validation_loss_bbox': tensor(0.1305, device='cuda:0'), 'validation_loss_giou': tensor(0.4784, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.6773, device='cuda:0'), 'train_loss_ce': tensor(0.3795, device='cuda:0'), 'train_loss_bbox': tensor(0.2213, device='cuda:0'), 'train_loss_giou': tensor(0.5956, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0580, device='cuda:0'), 'validation_loss_ce': tensor(0.3698, device='cuda:0'), 'validation_loss_bbox': tensor(0.1406, device='cuda:0'), 'validation_loss_giou': tensor(0.4927, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.0451, device='cuda:0'), 'train_loss_ce': tensor(0.3619, device='cuda:0'), 'train_loss_bbox': tensor(0.1562, device='cuda:0'), 'train_loss_giou': tensor(0.4512, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0350, device='cuda:0'), 'validation_loss_ce': tensor(0.3855, device='cuda:0'), 'validation_loss_bbox': tensor(0.1382, device='cuda:0'), 'validation_loss_giou': tensor(0.4791, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.1357, device='cuda:0'), 'train_loss_ce': tensor(0.3901, device='cuda:0'), 'train_loss_bbox': tensor(0.1723, device='cuda:0'), 'train_loss_giou': tensor(0.4422, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9736, device='cuda:0'), 'validation_loss_ce': tensor(0.3603, device='cuda:0'), 'validation_loss_bbox': tensor(0.1357, device='cuda:0'), 'validation_loss_giou': tensor(0.4673, device='cuda:0'), 'validation_cardinality_error': tensor(0.8687, device='cuda:0')}
+{'training_loss': tensor(1.5814, device='cuda:0'), 'train_loss_ce': tensor(0.3938, device='cuda:0'), 'train_loss_bbox': tensor(0.0935, device='cuda:0'), 'train_loss_giou': tensor(0.3600, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0607, device='cuda:0'), 'validation_loss_ce': tensor(0.3561, device='cuda:0'), 'validation_loss_bbox': tensor(0.1488, device='cuda:0'), 'validation_loss_giou': tensor(0.4804, device='cuda:0'), 'validation_cardinality_error': tensor(0.9394, device='cuda:0')}
+{'training_loss': tensor(1.7642, device='cuda:0'), 'train_loss_ce': tensor(0.3312, device='cuda:0'), 'train_loss_bbox': tensor(0.0892, device='cuda:0'), 'train_loss_giou': tensor(0.4934, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9519, device='cuda:0'), 'validation_loss_ce': tensor(0.3478, device='cuda:0'), 'validation_loss_bbox': tensor(0.1330, device='cuda:0'), 'validation_loss_giou': tensor(0.4697, device='cuda:0'), 'validation_cardinality_error': tensor(0.9697, device='cuda:0')}
+{'training_loss': tensor(1.3615, device='cuda:0'), 'train_loss_ce': tensor(0.3474, device='cuda:0'), 'train_loss_bbox': tensor(0.0976, device='cuda:0'), 'train_loss_giou': tensor(0.2630, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8283, device='cuda:0'), 'validation_loss_ce': tensor(0.3620, device='cuda:0'), 'validation_loss_bbox': tensor(0.1182, device='cuda:0'), 'validation_loss_giou': tensor(0.4376, device='cuda:0'), 'validation_cardinality_error': tensor(0.9596, device='cuda:0')}
+{'training_loss': tensor(1.4507, device='cuda:0'), 'train_loss_ce': tensor(0.2499, device='cuda:0'), 'train_loss_bbox': tensor(0.0839, device='cuda:0'), 'train_loss_giou': tensor(0.3905, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0212, device='cuda:0'), 'validation_loss_ce': tensor(0.3600, device='cuda:0'), 'validation_loss_bbox': tensor(0.1371, device='cuda:0'), 'validation_loss_giou': tensor(0.4878, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
 ```
 
 ## Examples