Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

RuntimeError: triangles.is_contiguous() INTERNAL ASSERT FAILED ,can u give some ad #9

Closed
anthonyyuan opened this issue Nov 21, 2020 · 3 comments

Comments

@anthonyyuan
Copy link

when I run:

# # 3D face reconstruction

python train.py
--data_dir $video_dir
--num_epoch 20
--serial_batches False
--display_freq 400
--print_freq 400
--batch_size 5

@anthonyyuan
Copy link
Author

./scripts/demo.sh
++ video_dir=data/video
++ audio_dir=data/test_audio
++ start_time=00:00:00
++ end_time=240
++ python train.py --data_dir data/video --num_epoch 20 --serial_batches False --display_freq 400 --print_freq 400 --batch_size 5
dataset [SingleDataset] was created
Traceback (most recent call last):
File "train.py", line 38, in
model.optimize_parameters() # calculate loss functions, get gradients, update network weights
File "/home/anthony/Downloads/AudioDVP-master/models/resnet_model.py", line 69, in optimize_parameters
self.forward()
File "/home/anthony/Downloads/AudioDVP-master/models/resnet_model.py", line 48, in forward
self.alpha, self.delta, self.beta, self.gamma, self.rotation, self.translation, self.render, self.mask, self.landmark = self.net(self.input)
File "/home/anthony/Downloads/ENTER/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/anthony/Downloads/AudioDVP-master/models/networks.py", line 174, in forward
render, mask, screen_vertices = self.face_model(self.alpha, delta, self.beta, rotation, translation, gamma)
File "/home/anthony/Downloads/ENTER/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/anthony/Downloads/AudioDVP-master/renderer/face_model.py", line 100, in forward
render_image, alpha_mask = self.renderer(clip_vertices, self.triangles, norm, tex, gamma)
File "/home/anthony/Downloads/ENTER/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/anthony/Downloads/AudioDVP-master/renderer/renderer.py", line 22, in forward
render_image, alpha_mask = self.rasterizer(clip_vertices, diffuse_colors_sh, triangles)
File "/home/anthony/Downloads/ENTER/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/anthony/Downloads/AudioDVP-master/renderer/rasterizer.py", line 53, in forward
px_triangle_ids, px_barycentric_coords, _ = RasterizeFunction.apply(clip_vertices[b, :, :], triangles, self.image_width, self.image_height)
File "/home/anthony/Downloads/AudioDVP-master/renderer/rasterizer.py", line 19, in forward
= rasterize_triangles_cpp.forward(vertices, triangles, image_width, image_height,px_triangle_ids, px_barycentric_coords, z_buffer)
RuntimeError: triangles.is_contiguous() INTERNAL ASSERT FAILED at "/home/anthony/Downloads/AudioDVP-master/renderer/kernels/rasterize_triangles.cpp":47, please report a bug to PyTorch. triangles must be contiguous

@qpoisson
Copy link

qpoisson commented Dec 1, 2020

@anthonyyuan how did you solve the issue ? thx

@ghost
Copy link

ghost commented Jan 20, 2021

@anthonyyuan how did you solve the issue ?
I meet it too.
@xinwen-cs

xinwen-cs added a commit that referenced this issue Aug 27, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants