search

abduallahmohamed / Social-STGCNN

Code for "Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction" CVPR 2020
MIT License
483 stars 141 forks source link

When I test my own model, some datasets work fine, but the univ dataset reports errors. The specific error message is as follows. #68

Open Jasmine302 opened 1 year ago

Jasmine302 commented 1 year ago

Traceback (most recent call last): File "test.py", line 195, in ad,fd,raw_datadic= test() File "test.py", line 69, in test mvnormal = torchdist.MultivariateNormal(mean,cov) File "/home/jnu/anaconda3/envs/xxq/lib/python3.7/site-packages/torch/distributions/multivariate_normal.py", line 146, in init super(MultivariateNormal, self).init(batch_shape, event_shape, validate_args=validate_args) File "/home/jnu/anaconda3/envs/xxq/lib/python3.7/site-packages/torch/distributions/distribution.py", line 56, in init f"Expected parameter {param} " ValueError: Expected parameter covariance_matrix (Tensor of shape (12, 57, 2, 2)) of distribution MultivariateNormal(loc: torch.Size([12, 57, 2]), covariance_matrix: torch.Size([12, 57, 2, 2])) to satisfy the constraint PositiveDefinite(), but found invalid values: tensor([[[[ 1.2511e-11, 2.6965e-10], [ 2.6965e-10, 5.8116e-09]],

abduallahmohamed commented 1 year ago

Hi, This means you predicted bad parameters that could not construct a correct covariance matrix. Try adjusting the learning rate.

On Thu, Jun 15, 2023 at 7:08 AM Jasmine @.***> wrote:

Traceback (most recent call last): File "test.py", line 195, in ad,fd,raw_datadic= test() File "test.py", line 69, in test mvnormal = torchdist.MultivariateNormal(mean,cov) File "/home/jnu/anaconda3/envs/xxq/lib/python3.7/site-packages/torch/distributions/multivariate_normal.py", line 146, in init super(MultivariateNormal, self).init(batch_shape, event_shape, validate_args=validate_args) File "/home/jnu/anaconda3/envs/xxq/lib/python3.7/site-packages/torch/distributions/distribution.py", line 56, in init f"Expected parameter {param} " ValueError: Expected parameter covariance_matrix (Tensor of shape (12, 57, 2, 2)) of distribution MultivariateNormal(loc: torch.Size([12, 57, 2]), covariance_matrix: torch.Size([12, 57, 2, 2])) to satisfy the constraint PositiveDefinite(), but found invalid values: tensor([[[[ 1.2511e-11, 2.6965e-10], [ 2.6965e-10, 5.8116e-09]],

— Reply to this email directly, view it on GitHub https://github.com/abduallahmohamed/Social-STGCNN/issues/68, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFIVLG4JDXPTL6SRH6X6BCDXLMJPHANCNFSM6AAAAAAZH5HL4Y . You are receiving this because you are subscribed to this thread.Message ID: @.***>

--

Abduallah Mohamed abduallahmohamed.com