search

Wizaron / instance-segmentation-pytorch

Semantic Instance Segmentation with a Discriminative Loss Function in PyTorch
https://arxiv.org/abs/1708.02551
GNU General Public License v3.0
458 stars 95 forks source link

Segmentation fault when running pred_list.py #11

Closed cardwing closed 6 years ago

cardwing commented 6 years ago

@Wizaron , I met a problem when running pred_list.py. It throws a segmentation fault error and I found that the error is in

clustering = SpectralClustering(n_clusters=n_objects_prediction, eigen_solver=None, random_state=None, n_init=10, gamma=1.0, affinity='rbf', n_neighbors=10, eigen_tol=0.0, assign_labels='discretize', degree=3, coef0=1, kernel_params=None, n_jobs=self.n_workers).fit(embeddings)

I guess there is something wrong with the embedding matrix. The following is the embedding matrix (7974 x 18):

[[-0.41176468 -0.04313725 1.45275438 ..., 1.03580952 0.80951059 2.21847034] [-0.41176468 -0.03529412 1.40515149 ..., 1.05152631 0.84383726 2.15164399] [-0.41176468 -0.02745098 1.39228165 ..., 1.05084693 0.82528883 2.11430955] ..., [ 0.53725493 0.10588241 -0.47388145 ..., -1.35868192 -1.06612647 -0.44077876] [ 0.53725493 0.11372554 -0.46349445 ..., -1.30981684 -1.04524136 -0.45144844] [ 0.53725493 0.12156868 -0.50578374 ..., -1.34164703 -1.0359056 -0.48357934]]

Can you give me some advice on how to fix the problem? Thanks a lot!

cardwing commented 6 years ago

When I use another server it works, maybe there is something wrong with my old server.