search

tyagi-iiitv / PointPillars

GNU General Public License v3.0
105 stars 47 forks source link

Pretrained model #30

Open sivaprasadraju opened 3 years ago

sivaprasadraju commented 3 years ago

@tyagi-iiitv Did your pretrained model reached the performance according to PointPillar paper?

han1366 commented 3 years ago

I think not. I find that the code is not very similar to paper.The paper describes 9 features per point,but this code only define 7 features.

Manueljohnson063 commented 3 years ago

@han1366 @sivaprasadraju 2021-03-07 17:54:35.720682: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudnn.so.8 2021-03-07 17:54:37.690026: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublas.so.11 2021-03-07 17:54:38.183182: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublasLt.so.11 Scene 1: Box predictions with occupancy > occ_thr: 0 Traceback (most recent call last): File "point_pillars_prediction.py", line 43, in nms_boxes = rotational_nms(set_boxes, confidences, occ_threshold=0.7, nms_iou_thr=0.5) File "/content/drive/MyDrive/PointPillars/inference_utils.py", line 41, in rotational_nms assert (isinstance(set_boxes[0][0][0][0], float) or isinstance(set_boxes[0][0][0][0], int)) and \ IndexError: list index out of range

I put for files in testing folder(4-velodyne,4-calib) 000000,00001,000002,00003 Error is poping out please help !!!!!!!!!!!!!!!!!!!!

han1366 commented 3 years ago

@han1366 @sivaprasadraju 2021-03-07 17:54:35.720682: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudnn.so.8 2021-03-07 17:54:37.690026: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublas.so.11 2021-03-07 17:54:38.183182: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublasLt.so.11 Scene 1: Box predictions with occupancy > occ_thr: 0 Traceback (most recent call last): File "point_pillars_prediction.py", line 43, in nms_boxes = rotational_nms(set_boxes, confidences, occ_threshold=0.7, nms_iou_thr=0.5) File "/content/drive/MyDrive/PointPillars/inference_utils.py", line 41, in rotational_nms assert (isinstance(set_boxes[0][0][0][0], float) or isinstance(set_boxes[0][0][0][0], int)) and IndexError: list index out of range

I put for files in testing folder(4-velodyne,4-calib) 000000,00001,000002,00003 Error is poping out please help !!!!!!!!!!!!!!!!!!!!

I can't run this code, so I think you can try second.pytorch.That code run easily.

tuan97anton commented 3 years ago

@han1366
Could you share the repo git of second.pytorch ?

eddydw commented 1 year ago

[@tyagi-iiitv] (https://github.com/tyagi-iiitv) : The pre-trained model model.h5 is missing . Can you please put it on the git repo or provide a link that is not broken please? thanks in advance Eddy