search

shariqfarooq123 / AdaBins

Official implementation of Adabins: Depth Estimation using adaptive bins
GNU General Public License v3.0
730 stars 156 forks source link

RuntimeError: CUDA error: invalid device function #78

Open WangGangQiang123 opened 1 year ago

WangGangQiang123 commented 1 year ago

] Traceback (most recent call last): File "/root/autodl-tmp/AdaBins-main/train.py", line 417, in main_worker(args.gpu, ngpus_per_node, args) File "/root/autodl-tmp/AdaBins-main/train.py", line 112, in main_worker train(model, args, epochs=args.epochs, lr=args.lr, device=args.gpu, root=args.root, File "/root/autodl-tmp/AdaBins-main/train.py", line 198, in train l_chamfer = criterion_bins(bin_edges, depth) File "/root/miniconda3/envs/pytorch3d/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forwardcall(*input, **kwargs) File "/root/autodl-tmp/AdaBins-main/loss.py", line 45, in forward loss, = chamfer_distance(x=input_points, y=target_points, y_lengths=target_lengths) File "/root/autodl-tmp/pytorch3d/pytorch3d/loss/chamfer.py", line 158, in chamfer_distance x_nn = knn_points(x, y, lengths1=x_lengths, lengths2=y_lengths, norm=norm, K=1) File "/root/autodl-tmp/pytorch3d/pytorch3d/ops/knn.py", line 187, in knn_points p1_dists, p1_idx = _knn_points.apply( File "/root/autodl-tmp/pytorch3d/pytorch3d/ops/knn.py", line 72, in forward idx, dists = _C.knn_points_idx(p1, p2, lengths1, lengths2, norm, K, version) RuntimeError: CUDA error: invalid device function CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1.