Closed insigh closed 5 years ago
@chengdazhi
@insigh 👍 come on!
wo should first train_rpn then test_rpn when we test_rpn we can modify the test file as train/val/test. then we can get the proposal cache at ./cache/rpndata/{}{}_rpn.pkl. :cn:
@shenyunlong :arrow_up:
@insigh Good Job 👍
Hello, I am chaojie from Renmin University of China, Beijing. Thanks for you excellent work in object detection. But i have a problem when i try it with my own data, It is all good for rcnn_attention and rcnn_dcn training and test, but when it comes rcnn_fpn symbol, I have to provide the previously generated proposals in the directory like this "./proposal/resnet_v1_101_fpn/rpndata/{}{}_rpn.pkl", so could you please give tips to me about how to generate this file for another data with annotations like COCO. I am dying to know it, thank you very much!