wmn931201
wmn931201
Can I understand that the WPOD-Net is trained with the data which have been augmented, without the original data? Thank you very much!
Thank you ! @sergiomsilva . I fine-tuned my own model based on the original model you published in September last year. However, There are many false detections in the test...
The data I used for training consist of AOLP, Cars and data from my scenario. SSIG is difficult to get. and there should be no errors in my annotations. Thus,...
OK，I know. @sergiomsilva, Thank you very much!
Do you have the train images which include AOLP,SSIG and Cars? Thank you very much if you can provide me ! @linzhi123
Hi, I've tried to pretrain on sceneflow dataset,but the result is very strange, the output result is all zero. In the previous issue, someone have asked the similar questions, but...
The issue is https://github.com/ucbdrive/hd3/issues/24. Yes, I am checking dataset now. and RGBA images are the majority of the Sceneflow dataset, so they can't be ignored. Thanks!
Hi，I find the value of annotations is negative in flythings3D_subset, but the value of annotations is positive in Sceneflow dataset. In your code, when reading labels, disp = np.expand_dims(-read_pfm_file(file_name), axis=-1)...