pummi823
pummi823
Hello, dear author, i have tried to run 3Dssd model on the nescenes dataset but just get very low map of around 20%(in the paper, the result is 42.66%), could...
Dear author: you mention that you use three data augmentation strategies include: rotate, flip, and scale transfer the point clouds. But, in your code, you look like have not do...
Dear author: could you tell me how to test the unabled data? now i only can success run the eval mode, but failed on test mode, which special settings should...
Dear author: I have tried to train your code on nuscenes datset but got very low mAP, only around 20%. Could you please publish the detail parameters or the pretrained...
Hi, Dear author! I would want to know, your public results of 3DSSD+SASA whose moderate's is 85.91, is trained by"80% train+20%val" or 70&30? Waiting for your answer~~~~
Dear author: I try to implement your results in your paper, but just get mAP of 20 (the reason may be i just set the batch_size to 3 instead of...
Dear author: in your paper, for 3DSSD, you said that " The total batch size is set to 16, equally distributed on four NVIDIA V100 GPUs". But in your code...
Dear author ,have you try your code on outdoor datasets, like KITTI? How about the performance?~~~
Dear author, i train your pvrcnn_fas.yaml，only cyclist，and split the training set to 80% and 20% for training and validating, then choose the best ckpt to run the test set, but...
Dear author: i wonder where the waymo results of other methods in your paper from?? In the github of openpcdet, all of they are much higher than listed in your...