search

LIU-Yuxin / SyncMVD

Official PyTorch & Diffusers implementation of "Text-Guided Texturing by Synchronized Multi-View Diffusion"
MIT License
104 stars 5 forks source link

CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES: too many resources requested for launch #1

Closed jjjkkyz closed 6 months ago

jjjkkyz commented 6 months ago

DEVICE: Tesla V100 command: python run_experiment.py --config data/face/config.yaml report log is :

Traceback (most recent call last):
  File "/home/chenxh/SyncMVD/run_experiment.py", line 73, in <module>
    result_tex_rgb, textured_views, v = syncmvd(
  File "/home/chenxh/anaconda3/envs/diffusion/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/home/chenxh/SyncMVD/src/pipeline.py", line 338, in __call__
    self.initialize_pipeline(
  File "/home/chenxh/SyncMVD/src/pipeline.py", line 253, in initialize_pipeline
    self.uvp.set_cameras_and_render_settings(self.camera_poses, centers=camera_centers, camera_distance=4.0)
  File "/home/chenxh/SyncMVD/src/renderer/project.py", line 220, in set_cameras_and_render_settings
    self.calculate_cos_angle_weights(cos_maps)
  File "/home/chenxh/anaconda3/envs/diffusion/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/home/chenxh/SyncMVD/src/renderer/project.py", line 279, in calculate_cos_angle_weights
    zero_map = voronoi_solve(zero_map, self.gradient_maps[i][...,0])
  File "/home/chenxh/SyncMVD/src/renderer/voronoi.py", line 70, in voronoi_solve
    ping = JFAVoronoiDiagram(ping, pong)
  File "/home/chenxh/SyncMVD/src/renderer/voronoi.py", line 158, in JFAVoronoiDiagram
    voronoiKernel((min(x_dim, 1024),), (min(y_dim, 1024),), (step, x_dim, y_dim, ping, pong))
  File "cupy/_core/raw.pyx", line 89, in cupy._core.raw.RawKernel.__call__
  File "cupy/cuda/function.pyx", line 223, in cupy.cuda.function.Function.__call__
  File "cupy/cuda/function.pyx", line 205, in cupy.cuda.function._launch
  File "cupy_backends/cuda/api/driver.pyx", line 253, in cupy_backends.cuda.api.driver.launchKernel
  File "cupy_backends/cuda/api/driver.pyx", line 60, in cupy_backends.cuda.api.driver.check_status
cupy_backends.cuda.api.driver.CUDADriverError: CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES: too many resources requested for launch