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 ] = 0.001
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.002
+ 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 ] = 0.000
  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 ] = 0.002
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
 ```
 
 ## After training result
 ```
 IoU metric: bbox
- 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=   all | maxDets=100 ] = 0.004
+ Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.011
+ Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.002
  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 ] = 0.029
- 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 Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.004
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.046
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.092
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.107
  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 ] = 0.168
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.108
 ```
 
 ## Config
@@ -42,44 +42,44 @@ IoU metric: bbox
 - original model: hustvl/yolos-tiny
 - lr: 0.0001
 - dropout_rate: 0.1
-- weight_decay: 1.0
+- weight_decay: 5.0
 - max_epochs: 30
 - train samples: 885
 
 ## Logging
 ### Training process
 ```
-{'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')}
+{'validation_loss': tensor(6.5564, device='cuda:0'), 'validation_loss_ce': tensor(2.0633, device='cuda:0'), 'validation_loss_bbox': tensor(0.5405, device='cuda:0'), 'validation_loss_giou': tensor(0.8954, device='cuda:0'), 'validation_cardinality_error': tensor(92.5312, device='cuda:0')}
+{'training_loss': tensor(3.7441, device='cuda:0'), 'train_loss_ce': tensor(0.4851, device='cuda:0'), 'train_loss_bbox': tensor(0.2741, device='cuda:0'), 'train_loss_giou': tensor(0.9444, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.8539, device='cuda:0'), 'validation_loss_ce': tensor(0.4760, device='cuda:0'), 'validation_loss_bbox': tensor(0.2163, device='cuda:0'), 'validation_loss_giou': tensor(0.6482, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.7504, device='cuda:0'), 'train_loss_ce': tensor(0.5047, device='cuda:0'), 'train_loss_bbox': tensor(0.1953, device='cuda:0'), 'train_loss_giou': tensor(0.6345, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6948, device='cuda:0'), 'validation_loss_ce': tensor(0.4437, device='cuda:0'), 'validation_loss_bbox': tensor(0.2097, device='cuda:0'), 'validation_loss_giou': tensor(0.6013, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.0392, device='cuda:0'), 'train_loss_ce': tensor(0.4076, device='cuda:0'), 'train_loss_bbox': tensor(0.1439, device='cuda:0'), 'train_loss_giou': tensor(0.4562, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4453, device='cuda:0'), 'validation_loss_ce': tensor(0.4250, device='cuda:0'), 'validation_loss_bbox': tensor(0.1845, device='cuda:0'), 'validation_loss_giou': tensor(0.5490, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.2227, device='cuda:0'), 'train_loss_ce': tensor(0.4271, device='cuda:0'), 'train_loss_bbox': tensor(0.1462, device='cuda:0'), 'train_loss_giou': tensor(0.5323, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4683, device='cuda:0'), 'validation_loss_ce': tensor(0.4277, device='cuda:0'), 'validation_loss_bbox': tensor(0.1854, device='cuda:0'), 'validation_loss_giou': tensor(0.5569, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.3469, device='cuda:0'), 'train_loss_ce': tensor(0.4323, device='cuda:0'), 'train_loss_bbox': tensor(0.1472, device='cuda:0'), 'train_loss_giou': tensor(0.5894, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4288, device='cuda:0'), 'validation_loss_ce': tensor(0.4206, device='cuda:0'), 'validation_loss_bbox': tensor(0.1770, device='cuda:0'), 'validation_loss_giou': tensor(0.5616, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.7726, device='cuda:0'), 'train_loss_ce': tensor(0.4058, device='cuda:0'), 'train_loss_bbox': tensor(0.2171, device='cuda:0'), 'train_loss_giou': tensor(0.6406, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4031, device='cuda:0'), 'validation_loss_ce': tensor(0.4243, device='cuda:0'), 'validation_loss_bbox': tensor(0.1760, device='cuda:0'), 'validation_loss_giou': tensor(0.5495, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.4850, device='cuda:0'), 'train_loss_ce': tensor(0.4841, device='cuda:0'), 'train_loss_bbox': tensor(0.1897, device='cuda:0'), 'train_loss_giou': tensor(0.5262, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3094, device='cuda:0'), 'validation_loss_ce': tensor(0.4155, device='cuda:0'), 'validation_loss_bbox': tensor(0.1648, device='cuda:0'), 'validation_loss_giou': tensor(0.5348, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.7707, device='cuda:0'), 'train_loss_ce': tensor(0.4562, device='cuda:0'), 'train_loss_bbox': tensor(0.0906, device='cuda:0'), 'train_loss_giou': tensor(0.4307, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3606, device='cuda:0'), 'validation_loss_ce': tensor(0.4136, device='cuda:0'), 'validation_loss_bbox': tensor(0.1676, device='cuda:0'), 'validation_loss_giou': tensor(0.5546, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.8267, device='cuda:0'), 'train_loss_ce': tensor(0.4556, device='cuda:0'), 'train_loss_bbox': tensor(0.1383, device='cuda:0'), 'train_loss_giou': tensor(0.3398, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3544, device='cuda:0'), 'validation_loss_ce': tensor(0.4203, device='cuda:0'), 'validation_loss_bbox': tensor(0.1730, device='cuda:0'), 'validation_loss_giou': tensor(0.5346, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.6995, device='cuda:0'), 'train_loss_ce': tensor(0.4739, device='cuda:0'), 'train_loss_bbox': tensor(0.2123, device='cuda:0'), 'train_loss_giou': tensor(0.5820, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3790, device='cuda:0'), 'validation_loss_ce': tensor(0.4226, device='cuda:0'), 'validation_loss_bbox': tensor(0.1763, device='cuda:0'), 'validation_loss_giou': tensor(0.5375, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.9513, device='cuda:0'), 'train_loss_ce': tensor(0.4720, device='cuda:0'), 'train_loss_bbox': tensor(0.0936, device='cuda:0'), 'train_loss_giou': tensor(0.5057, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4871, device='cuda:0'), 'validation_loss_ce': tensor(0.3954, device='cuda:0'), 'validation_loss_bbox': tensor(0.1899, device='cuda:0'), 'validation_loss_giou': tensor(0.5711, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.8887, device='cuda:0'), 'train_loss_ce': tensor(0.4222, device='cuda:0'), 'train_loss_bbox': tensor(0.1872, device='cuda:0'), 'train_loss_giou': tensor(0.7651, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3490, device='cuda:0'), 'validation_loss_ce': tensor(0.4116, device='cuda:0'), 'validation_loss_bbox': tensor(0.1671, device='cuda:0'), 'validation_loss_giou': tensor(0.5511, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(3.0653, device='cuda:0'), 'train_loss_ce': tensor(0.3967, device='cuda:0'), 'train_loss_bbox': tensor(0.2608, device='cuda:0'), 'train_loss_giou': tensor(0.6824, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3907, device='cuda:0'), 'validation_loss_ce': tensor(0.3930, device='cuda:0'), 'validation_loss_bbox': tensor(0.1780, device='cuda:0'), 'validation_loss_giou': tensor(0.5538, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.6032, device='cuda:0'), 'train_loss_ce': tensor(0.4456, device='cuda:0'), 'train_loss_bbox': tensor(0.1778, device='cuda:0'), 'train_loss_giou': tensor(0.6342, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5283, device='cuda:0'), 'validation_loss_ce': tensor(0.3733, device='cuda:0'), 'validation_loss_bbox': tensor(0.1893, device='cuda:0'), 'validation_loss_giou': tensor(0.6041, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.2535, device='cuda:0'), 'train_loss_ce': tensor(0.4025, device='cuda:0'), 'train_loss_bbox': tensor(0.1915, device='cuda:0'), 'train_loss_giou': tensor(0.4469, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5700, device='cuda:0'), 'validation_loss_ce': tensor(0.3973, device='cuda:0'), 'validation_loss_bbox': tensor(0.2018, device='cuda:0'), 'validation_loss_giou': tensor(0.5819, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.3217, device='cuda:0'), 'train_loss_ce': tensor(0.3088, device='cuda:0'), 'train_loss_bbox': tensor(0.1950, device='cuda:0'), 'train_loss_giou': tensor(0.5188, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4046, device='cuda:0'), 'validation_loss_ce': tensor(0.3842, device='cuda:0'), 'validation_loss_bbox': tensor(0.1765, device='cuda:0'), 'validation_loss_giou': tensor(0.5688, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.0773, device='cuda:0'), 'train_loss_ce': tensor(0.3404, device='cuda:0'), 'train_loss_bbox': tensor(0.1290, device='cuda:0'), 'train_loss_giou': tensor(0.5459, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3971, device='cuda:0'), 'validation_loss_ce': tensor(0.3989, device='cuda:0'), 'validation_loss_bbox': tensor(0.1737, device='cuda:0'), 'validation_loss_giou': tensor(0.5648, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.3780, device='cuda:0'), 'train_loss_ce': tensor(0.4421, device='cuda:0'), 'train_loss_bbox': tensor(0.2007, device='cuda:0'), 'train_loss_giou': tensor(0.4663, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5065, device='cuda:0'), 'validation_loss_ce': tensor(0.3807, device='cuda:0'), 'validation_loss_bbox': tensor(0.1850, device='cuda:0'), 'validation_loss_giou': tensor(0.6004, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.9553, device='cuda:0'), 'train_loss_ce': tensor(0.2818, device='cuda:0'), 'train_loss_bbox': tensor(0.1281, device='cuda:0'), 'train_loss_giou': tensor(0.5166, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6497, device='cuda:0'), 'validation_loss_ce': tensor(0.4114, device='cuda:0'), 'validation_loss_bbox': tensor(0.2036, device='cuda:0'), 'validation_loss_giou': tensor(0.6101, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(3.0033, device='cuda:0'), 'train_loss_ce': tensor(0.4743, device='cuda:0'), 'train_loss_bbox': tensor(0.2637, device='cuda:0'), 'train_loss_giou': tensor(0.6052, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7365, device='cuda:0'), 'validation_loss_ce': tensor(0.3921, device='cuda:0'), 'validation_loss_bbox': tensor(0.2165, device='cuda:0'), 'validation_loss_giou': tensor(0.6309, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.4115, device='cuda:0'), 'train_loss_ce': tensor(0.4218, device='cuda:0'), 'train_loss_bbox': tensor(0.1878, device='cuda:0'), 'train_loss_giou': tensor(0.5255, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7406, device='cuda:0'), 'validation_loss_ce': tensor(0.3620, device='cuda:0'), 'validation_loss_bbox': tensor(0.2215, device='cuda:0'), 'validation_loss_giou': tensor(0.6356, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.6330, device='cuda:0'), 'train_loss_ce': tensor(0.3572, device='cuda:0'), 'train_loss_bbox': tensor(0.2481, device='cuda:0'), 'train_loss_giou': tensor(0.5176, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5378, device='cuda:0'), 'validation_loss_ce': tensor(0.3836, device='cuda:0'), 'validation_loss_bbox': tensor(0.1972, device='cuda:0'), 'validation_loss_giou': tensor(0.5842, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.4576, device='cuda:0'), 'train_loss_ce': tensor(0.3233, device='cuda:0'), 'train_loss_bbox': tensor(0.1875, device='cuda:0'), 'train_loss_giou': tensor(0.5983, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4691, device='cuda:0'), 'validation_loss_ce': tensor(0.3929, device='cuda:0'), 'validation_loss_bbox': tensor(0.1909, device='cuda:0'), 'validation_loss_giou': tensor(0.5609, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.4825, device='cuda:0'), 'train_loss_ce': tensor(0.4494, device='cuda:0'), 'train_loss_bbox': tensor(0.1926, device='cuda:0'), 'train_loss_giou': tensor(0.5351, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6155, device='cuda:0'), 'validation_loss_ce': tensor(0.4034, device='cuda:0'), 'validation_loss_bbox': tensor(0.2007, device='cuda:0'), 'validation_loss_giou': tensor(0.6043, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.6028, device='cuda:0'), 'train_loss_ce': tensor(0.4207, device='cuda:0'), 'train_loss_bbox': tensor(0.1980, device='cuda:0'), 'train_loss_giou': tensor(0.5962, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.6668, device='cuda:0'), 'validation_loss_ce': tensor(0.3779, device='cuda:0'), 'validation_loss_bbox': tensor(0.2057, device='cuda:0'), 'validation_loss_giou': tensor(0.6303, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.9037, device='cuda:0'), 'train_loss_ce': tensor(0.2973, device='cuda:0'), 'train_loss_bbox': tensor(0.1633, device='cuda:0'), 'train_loss_giou': tensor(0.3951, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5248, device='cuda:0'), 'validation_loss_ce': tensor(0.3994, device='cuda:0'), 'validation_loss_bbox': tensor(0.1943, device='cuda:0'), 'validation_loss_giou': tensor(0.5770, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.6755, device='cuda:0'), 'train_loss_ce': tensor(0.3837, device='cuda:0'), 'train_loss_bbox': tensor(0.2018, device='cuda:0'), 'train_loss_giou': tensor(0.6414, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7245, device='cuda:0'), 'validation_loss_ce': tensor(0.4018, device='cuda:0'), 'validation_loss_bbox': tensor(0.2082, device='cuda:0'), 'validation_loss_giou': tensor(0.6410, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.8687, device='cuda:0'), 'train_loss_ce': tensor(0.4472, device='cuda:0'), 'train_loss_bbox': tensor(0.2041, device='cuda:0'), 'train_loss_giou': tensor(0.7005, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4158, device='cuda:0'), 'validation_loss_ce': tensor(0.4104, device='cuda:0'), 'validation_loss_bbox': tensor(0.1761, device='cuda:0'), 'validation_loss_giou': tensor(0.5626, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.8324, device='cuda:0'), 'train_loss_ce': tensor(0.4533, device='cuda:0'), 'train_loss_bbox': tensor(0.1971, device='cuda:0'), 'train_loss_giou': tensor(0.6968, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3753, device='cuda:0'), 'validation_loss_ce': tensor(0.4029, device='cuda:0'), 'validation_loss_bbox': tensor(0.1723, device='cuda:0'), 'validation_loss_giou': tensor(0.5555, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.8085, device='cuda:0'), 'train_loss_ce': tensor(0.3939, device='cuda:0'), 'train_loss_bbox': tensor(0.2750, device='cuda:0'), 'train_loss_giou': tensor(0.5198, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3772, device='cuda:0'), 'validation_loss_ce': tensor(0.4097, device='cuda:0'), 'validation_loss_bbox': tensor(0.1783, device='cuda:0'), 'validation_loss_giou': tensor(0.5380, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
 ```
 
 ## Examples