---

library_name: transformers
tags: []
---

## 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 ] = 0.000
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 ] = 0.002
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 ] = 0.000
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
```

## After training result
```
IoU metric: bbox
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.015
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.035
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.010
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.009
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.018
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.080
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.183
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.201
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.016
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.225
```

## Config
- dataset: NIH
- original model: facebook/detr-resnet-50
- lr: 0.0001
- max_epochs: 50

## Logging
### Training process
```
{'validation_loss': tensor(6.3440, device='cuda:0'), 'validation_loss_ce': tensor(2.0978, device='cuda:0'), 'validation_loss_bbox': tensor(0.4936, device='cuda:0'), 'validation_loss_giou': tensor(0.8890, device='cuda:0'), 'validation_cardinality_error': tensor(85.6562, device='cuda:0')}
{'training_loss': tensor(3.1706, device='cuda:0'), 'train_loss_ce': tensor(0.5251, device='cuda:0'), 'train_loss_bbox': tensor(0.2706, device='cuda:0'), 'train_loss_giou': tensor(0.6462, device='cuda:0'), 'train_cardinality_error': tensor(1.1250, device='cuda:0'), 'validation_loss': tensor(2.9125, device='cuda:0'), 'validation_loss_ce': tensor(0.5056, device='cuda:0'), 'validation_loss_bbox': tensor(0.2312, device='cuda:0'), 'validation_loss_giou': tensor(0.6255, device='cuda:0'), 'validation_cardinality_error': tensor(1.1205, device='cuda:0')}
{'training_loss': tensor(2.4987, device='cuda:0'), 'train_loss_ce': tensor(0.5532, device='cuda:0'), 'train_loss_bbox': tensor(0.1583, device='cuda:0'), 'train_loss_giou': tensor(0.5770, device='cuda:0'), 'train_cardinality_error': tensor(1.3125, device='cuda:0'), 'validation_loss': tensor(2.3335, device='cuda:0'), 'validation_loss_ce': tensor(0.4910, device='cuda:0'), 'validation_loss_bbox': tensor(0.1606, device='cuda:0'), 'validation_loss_giou': tensor(0.5197, device='cuda:0'), 'validation_cardinality_error': tensor(1.1205, device='cuda:0')}
{'training_loss': tensor(2.5471, device='cuda:0'), 'train_loss_ce': tensor(0.4087, device='cuda:0'), 'train_loss_bbox': tensor(0.1558, device='cuda:0'), 'train_loss_giou': tensor(0.6798, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3420, device='cuda:0'), 'validation_loss_ce': tensor(0.4825, device='cuda:0'), 'validation_loss_bbox': tensor(0.1571, device='cuda:0'), 'validation_loss_giou': tensor(0.5370, device='cuda:0'), 'validation_cardinality_error': tensor(1.1205, device='cuda:0')}
{'training_loss': tensor(2.4962, device='cuda:0'), 'train_loss_ce': tensor(0.5160, device='cuda:0'), 'train_loss_bbox': tensor(0.1702, device='cuda:0'), 'train_loss_giou': tensor(0.5646, device='cuda:0'), 'train_cardinality_error': tensor(1.1250, device='cuda:0'), 'validation_loss': tensor(2.4121, device='cuda:0'), 'validation_loss_ce': tensor(0.4837, device='cuda:0'), 'validation_loss_bbox': tensor(0.1671, device='cuda:0'), 'validation_loss_giou': tensor(0.5463, device='cuda:0'), 'validation_cardinality_error': tensor(1.1205, device='cuda:0')}
{'training_loss': tensor(2.0146, device='cuda:0'), 'train_loss_ce': tensor(0.4475, device='cuda:0'), 'train_loss_bbox': tensor(0.1417, device='cuda:0'), 'train_loss_giou': tensor(0.4294, device='cuda:0'), 'train_cardinality_error': tensor(1.0625, device='cuda:0'), 'validation_loss': tensor(2.4437, device='cuda:0'), 'validation_loss_ce': tensor(0.4664, device='cuda:0'), 'validation_loss_bbox': tensor(0.1689, device='cuda:0'), 'validation_loss_giou': tensor(0.5664, device='cuda:0'), 'validation_cardinality_error': tensor(1.1205, device='cuda:0')}
{'training_loss': tensor(2.5258, device='cuda:0'), 'train_loss_ce': tensor(0.4352, device='cuda:0'), 'train_loss_bbox': tensor(0.1822, device='cuda:0'), 'train_loss_giou': tensor(0.5898, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2827, device='cuda:0'), 'validation_loss_ce': tensor(0.4655, device='cuda:0'), 'validation_loss_bbox': tensor(0.1534, device='cuda:0'), 'validation_loss_giou': tensor(0.5252, device='cuda:0'), 'validation_cardinality_error': tensor(1.1205, device='cuda:0')}
{'training_loss': tensor(2.5122, device='cuda:0'), 'train_loss_ce': tensor(0.4750, device='cuda:0'), 'train_loss_bbox': tensor(0.1781, device='cuda:0'), 'train_loss_giou': tensor(0.5734, device='cuda:0'), 'train_cardinality_error': tensor(1.2500, device='cuda:0'), 'validation_loss': tensor(2.3420, device='cuda:0'), 'validation_loss_ce': tensor(0.4609, device='cuda:0'), 'validation_loss_bbox': tensor(0.1545, device='cuda:0'), 'validation_loss_giou': tensor(0.5543, device='cuda:0'), 'validation_cardinality_error': tensor(1.1205, device='cuda:0')}
{'training_loss': tensor(2.5104, device='cuda:0'), 'train_loss_ce': tensor(0.4122, device='cuda:0'), 'train_loss_bbox': tensor(0.1681, device='cuda:0'), 'train_loss_giou': tensor(0.6288, device='cuda:0'), 'train_cardinality_error': tensor(1.0625, device='cuda:0'), 'validation_loss': tensor(2.2988, device='cuda:0'), 'validation_loss_ce': tensor(0.4562, device='cuda:0'), 'validation_loss_bbox': tensor(0.1513, device='cuda:0'), 'validation_loss_giou': tensor(0.5432, device='cuda:0'), 'validation_cardinality_error': tensor(1.1205, device='cuda:0')}
{'training_loss': tensor(2.5571, device='cuda:0'), 'train_loss_ce': tensor(0.5181, device='cuda:0'), 'train_loss_bbox': tensor(0.1580, device='cuda:0'), 'train_loss_giou': tensor(0.6245, device='cuda:0'), 'train_cardinality_error': tensor(1.3125, device='cuda:0'), 'validation_loss': tensor(2.3666, device='cuda:0'), 'validation_loss_ce': tensor(0.4579, device='cuda:0'), 'validation_loss_bbox': tensor(0.1604, device='cuda:0'), 'validation_loss_giou': tensor(0.5533, device='cuda:0'), 'validation_cardinality_error': tensor(1.1205, device='cuda:0')}
{'training_loss': tensor(2.1376, device='cuda:0'), 'train_loss_ce': tensor(0.5280, device='cuda:0'), 'train_loss_bbox': tensor(0.1437, device='cuda:0'), 'train_loss_giou': tensor(0.4456, device='cuda:0'), 'train_cardinality_error': tensor(1.2500, device='cuda:0'), 'validation_loss': tensor(2.2616, device='cuda:0'), 'validation_loss_ce': tensor(0.4543, device='cuda:0'), 'validation_loss_bbox': tensor(0.1543, device='cuda:0'), 'validation_loss_giou': tensor(0.5179, device='cuda:0'), 'validation_cardinality_error': tensor(1.1205, device='cuda:0')}
{'training_loss': tensor(2.2242, device='cuda:0'), 'train_loss_ce': tensor(0.4644, device='cuda:0'), 'train_loss_bbox': tensor(0.1293, device='cuda:0'), 'train_loss_giou': tensor(0.5567, device='cuda:0'), 'train_cardinality_error': tensor(1.1250, device='cuda:0'), 'validation_loss': tensor(2.2209, device='cuda:0'), 'validation_loss_ce': tensor(0.4515, device='cuda:0'), 'validation_loss_bbox': tensor(0.1492, device='cuda:0'), 'validation_loss_giou': tensor(0.5117, device='cuda:0'), 'validation_cardinality_error': tensor(1.1205, device='cuda:0')}
{'training_loss': tensor(2.1088, device='cuda:0'), 'train_loss_ce': tensor(0.3916, device='cuda:0'), 'train_loss_bbox': tensor(0.1388, device='cuda:0'), 'train_loss_giou': tensor(0.5116, device='cuda:0'), 'train_cardinality_error': tensor(1.1250, device='cuda:0'), 'validation_loss': tensor(2.1887, device='cuda:0'), 'validation_loss_ce': tensor(0.4398, device='cuda:0'), 'validation_loss_bbox': tensor(0.1450, device='cuda:0'), 'validation_loss_giou': tensor(0.5119, device='cuda:0'), 'validation_cardinality_error': tensor(1.1205, device='cuda:0')}
{'training_loss': tensor(2.1986, device='cuda:0'), 'train_loss_ce': tensor(0.4151, device='cuda:0'), 'train_loss_bbox': tensor(0.1447, device='cuda:0'), 'train_loss_giou': tensor(0.5301, device='cuda:0'), 'train_cardinality_error': tensor(1.2500, device='cuda:0'), 'validation_loss': tensor(2.1999, device='cuda:0'), 'validation_loss_ce': tensor(0.4299, device='cuda:0'), 'validation_loss_bbox': tensor(0.1486, device='cuda:0'), 'validation_loss_giou': tensor(0.5135, device='cuda:0'), 'validation_cardinality_error': tensor(1.1205, device='cuda:0')}
{'training_loss': tensor(2.0995, device='cuda:0'), 'train_loss_ce': tensor(0.4170, device='cuda:0'), 'train_loss_bbox': tensor(0.1438, device='cuda:0'), 'train_loss_giou': tensor(0.4818, device='cuda:0'), 'train_cardinality_error': tensor(1.1875, device='cuda:0'), 'validation_loss': tensor(2.1373, device='cuda:0'), 'validation_loss_ce': tensor(0.4293, device='cuda:0'), 'validation_loss_bbox': tensor(0.1426, device='cuda:0'), 'validation_loss_giou': tensor(0.4974, device='cuda:0'), 'validation_cardinality_error': tensor(1.1205, device='cuda:0')}
{'training_loss': tensor(2.2508, device='cuda:0'),

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f271bd931a70aca8da320ed04dc943dc5adf0003dfd9e212f3a2b9dad8969f
+oid sha256:08b92ae58b33e31e82563d64521ec9746418f96d01609477205c548a9b48c3a1
 size 166510924