nuscenes-devkit
nuscenes-devkit copied to clipboard
lyft
Devkit for the public 2019 Lyft Level 5 AV Dataset (fork of https://github.com/nutonomy/nuscenes-devkit)
Hi all, I don't know if I did anything wrong but I see many cars in the Lyft perception dataset (Lidar) that are not labeled !!
Hi, thanks for your nice work! btw, is there any scene image in nuScenes dataset? like below in Kitti dataset. Best,
veh_trans = np.array([1048.155950230245, 1691.8102354006162, -23.304943447792454]) ego_trans = np.array([1007.2332778546752, 1725.4217301399465, -24.58000073380586]) ego_rot = np.array([[ 9.99991535e-01, -1.94042865e-03, -3.62842040e-03], [ 4.02573511e-03, 2.79013810e-01, 9.60278651e-01], [-8.50972801e-04, -9.60285129e-01, 2.79019260e-01]]) sens_trans = np.array([1.1970962545449502, 3.680498291456359e-05, 1.8279670539933053]) sens_rot =...
Hello.   Here we see that map path in train json is incorrect. Also in kernels i see this code: ``` !ln -s $DATASET_PATH/train_images images !ln -s $DATASET_PATH/train_maps maps...
Hi, Thank you for your wonderful dataset! In short, I am wondering how we may convert the masked map into the form of vector maps? The vector maps here mean...
regarding #50 issue, The same error comes up as below ``` points = scan.reshape((-1, 5))[:, : cls.nbr_dims()] ValueError: cannot reshape array of size 265728 into shape (5) ``` I am...
I am running on a server with no interface, so my rendered image cannot be displayed, what should I do to not render and save the result to the directory
This following function performs a pretty expensive computation: https://github.com/lyft/nuscenes-devkit/blob/e4efd52a9630959a5b890e1575b58cab145e2441/lyft_dataset_sdk/lyftdataset.py#L653-L715 I am curious: does this function take so much time to run because of the process of loading the lidar cloud...
Hi all, thank you very much for your code! I tried to find which sensors you used in your acquisitions but no information can be found neither on the website...
