Hugging Face's logo

MedicalVision
/
detr_nih_10ep

Object Detection
Transformers
Safetensors
detr
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 ] = 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 ] = 0.001
 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 ] = 0.004
 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 ] = 0.004

After training result 

IoU metric: bbox
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.003
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.011
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.001
 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 ] = 0.003
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.037
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.074
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.084
 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 ] = 0.006
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.085

Config

  • dataset: NIH
  • original model: facebook/detr-resnet-50
  • lr: 5e-05
  • max_epochs: 10

Logging

Training process 

{'validation_loss': tensor(6.4663, device='cuda:0'), 'validation_loss_ce': tensor(2.5639, device='cuda:0'), 'validation_loss_bbox': tensor(0.4662, device='cuda:0'), 'validation_loss_giou': tensor(0.7858, device='cuda:0'), 'validation_cardinality_error': tensor(98.8125, device='cuda:0')}
{'training_loss': tensor(4.3831, device='cuda:0'), 'train_loss_ce': tensor(1.5780, device='cuda:0'), 'train_loss_bbox': tensor(0.2546, device='cuda:0'), 'train_loss_giou': tensor(0.7661, device='cuda:0'), 'train_cardinality_error': tensor(3.7500, device='cuda:0'), 'validation_loss': tensor(4.1328, device='cuda:0'), 'validation_loss_ce': tensor(1.5373, device='cuda:0'), 'validation_loss_bbox': tensor(0.2405, device='cuda:0'), 'validation_loss_giou': tensor(0.6965, device='cuda:0'), 'validation_cardinality_error': tensor(1.4364, device='cuda:0')}
{'training_loss': tensor(2.8787, device='cuda:0'), 'train_loss_ce': tensor(0.7759, device='cuda:0'), 'train_loss_bbox': tensor(0.1841, device='cuda:0'), 'train_loss_giou': tensor(0.5911, device='cuda:0'), 'train_cardinality_error': tensor(1.0625, device='cuda:0'), 'validation_loss': tensor(2.8971, device='cuda:0'), 'validation_loss_ce': tensor(0.7507, device='cuda:0'), 'validation_loss_bbox': tensor(0.1935, device='cuda:0'), 'validation_loss_giou': tensor(0.5893, device='cuda:0'), 'validation_cardinality_error': tensor(1.1159, device='cuda:0')}
{'training_loss': tensor(2.8165, device='cuda:0'), 'train_loss_ce': tensor(0.5296, device='cuda:0'), 'train_loss_bbox': tensor(0.2043, device='cuda:0'), 'train_loss_giou': tensor(0.6328, device='cuda:0'), 'train_cardinality_error': tensor(1.0625, device='cuda:0'), 'validation_loss': tensor(2.6196, device='cuda:0'), 'validation_loss_ce': tensor(0.5727, device='cuda:0'), 'validation_loss_bbox': tensor(0.1831, device='cuda:0'), 'validation_loss_giou': tensor(0.5656, device='cuda:0'), 'validation_cardinality_error': tensor(1.1159, device='cuda:0')}
{'training_loss': tensor(2.6336, device='cuda:0'), 'train_loss_ce': tensor(0.5603, device='cuda:0'), 'train_loss_bbox': tensor(0.1886, device='cuda:0'), 'train_loss_giou': tensor(0.5651, device='cuda:0'), 'train_cardinality_error': tensor(1.1875, device='cuda:0'), 'validation_loss': tensor(2.4110, device='cuda:0'), 'validation_loss_ce': tensor(0.5158, device='cuda:0'), 'validation_loss_bbox': tensor(0.1616, device='cuda:0'), 'validation_loss_giou': tensor(0.5437, device='cuda:0'), 'validation_cardinality_error': tensor(1.1159, device='cuda:0')}
{'training_loss': tensor(2.3404, device='cuda:0'), 'train_loss_ce': tensor(0.4770, device='cuda:0'), 'train_loss_bbox': tensor(0.1684, device='cuda:0'), 'train_loss_giou': tensor(0.5106, device='cuda:0'), 'train_cardinality_error': tensor(1.2500, device='cuda:0'), 'validation_loss': tensor(2.3158, device='cuda:0'), 'validation_loss_ce': tensor(0.5015, device='cuda:0'), 'validation_loss_bbox': tensor(0.1579, device='cuda:0'), 'validation_loss_giou': tensor(0.5123, device='cuda:0'), 'validation_cardinality_error': tensor(1.1159, device='cuda:0')}
{'training_loss': tensor(2.4181, device='cuda:0'), 'train_loss_ce': tensor(0.4818, device='cuda:0'), 'train_loss_bbox': tensor(0.1594, device='cuda:0'), 'train_loss_giou': tensor(0.5697, device='cuda:0'), 'train_cardinality_error': tensor(1.0625, device='cuda:0'), 'validation_loss': tensor(2.2529, device='cuda:0'), 'validation_loss_ce': tensor(0.4929, device='cuda:0'), 'validation_loss_bbox': tensor(0.1507, device='cuda:0'), 'validation_loss_giou': tensor(0.5034, device='cuda:0'), 'validation_cardinality_error': tensor(1.1159, device='cuda:0')}
{'training_loss': tensor(2.3413, device='cuda:0'), 'train_loss_ce': tensor(0.6037, device='cuda:0'), 'train_loss_bbox': tensor(0.1422, device='cuda:0'), 'train_loss_giou': tensor(0.5133, device='cuda:0'), 'train_cardinality_error': tensor(1.3750, device='cuda:0'), 'validation_loss': tensor(2.2137, device='cuda:0'), 'validation_loss_ce': tensor(0.4902, device='cuda:0'), 'validation_loss_bbox': tensor(0.1481, device='cuda:0'), 'validation_loss_giou': tensor(0.4914, device='cuda:0'), 'validation_cardinality_error': tensor(1.1159, device='cuda:0')}
{'training_loss': tensor(2.3693, device='cuda:0'), 'train_loss_ce': tensor(0.4641, device='cuda:0'), 'train_loss_bbox': tensor(0.1578, device='cuda:0'), 'train_loss_giou': tensor(0.5582, device='cuda:0'), 'train_cardinality_error': tensor(1.1250, device='cuda:0'), 'validation_loss': tensor(2.1577, device='cuda:0'), 'validation_loss_ce': tensor(0.4842, device='cuda:0'), 'validation_loss_bbox': tensor(0.1380, device='cuda:0'), 'validation_loss_giou': tensor(0.4917, device='cuda:0'), 'validation_cardinality_error': tensor(1.1159, device='cuda:0')}
{'training_loss': tensor(2.0663, device='cuda:0'), 'train_loss_ce': tensor(0.4912, device='cuda:0'), 'train_loss_bbox': tensor(0.1322, device='cuda:0'), 'train_loss_giou': tensor(0.4571, device='cuda:0'), 'train_cardinality_error': tensor(1.1250, device='cuda:0'), 'validation_loss': tensor(2.1651, device='cuda:0'), 'validation_loss_ce': tensor(0.4833, device='cuda:0'), 'validation_loss_bbox': tensor(0.1443, device='cuda:0'), 'validation_loss_giou': tensor(0.4801, device='cuda:0'), 'validation_cardinality_error': tensor(1.1159, device='cuda:0')}
{'training_loss': tensor(2.2925, device='cuda:0'), 'train_loss_ce': tensor(0.3871, device='cuda:0'), 'train_loss_bbox': tensor(0.1779, device='cuda:0'), 'train_loss_giou': tensor(0.5079, device='cuda:0'), 'train_cardinality_error': tensor(1.0625, device='cuda:0'), 'validation_loss': tensor(2.2612, device='cuda:0'), 'validation_loss_ce': tensor(0.4804, device='cuda:0'), 'validation_loss_bbox': tensor(0.1531, device='cuda:0'), 'validation_loss_giou': tensor(0.5077, device='cuda:0'), 'validation_cardinality_error': tensor(1.1159, device='cuda:0')}
Downloads last month
0
Safetensors
Model size
41.6M params
Tensor type
F32
·
Inference API
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.