search

jwyang / graph-rcnn.pytorch

[ECCV 2018] Official code for "Graph R-CNN for Scene Graph Generation"
732 stars 157 forks source link

low precision #96

Closed ZhuYun97 closed 4 years ago

ZhuYun97 commented 4 years ago

I download the pre-trained model(faster r-cnn) and change the parameter 'WEIGHT_DET' into the right path in faster_rcnn_res101.yaml file. Then I run the command 'python main.py --config-file configs/faster_rcnn_res101.yaml'. But the accuracy is pretty low. Where did I make mistakes? Could you please help me to figure it out.

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.123 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.246 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.108 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.020 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.056 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.140 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.200 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.303 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.307 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.020 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.189 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.335

ZhuYun97 commented 4 years ago

After training around 60000 iterations training with lr = 0.000005. The loss reduces to 0.97 from 1 on the training set. And the evaluation shows below. The accuracy is still low, what other methods to improve it?

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.131 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.257 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.119 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.020 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.059 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.150 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.211 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.317 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.321 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.020 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.198 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.350

khieu commented 3 years ago

I got the same issue. Do you have any suggestion on fixing this problem? Thank you!