search

danieltan07 / dagmm

My attempt at reproducing the paper Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection
392 stars 106 forks source link

Can anyone run this codes? #24

Open PeterKim1 opened 3 years ago

PeterKim1 commented 3 years ago

Hello. Thanks for your great works.

I use Google Colab, and in my Colab notebook, this Error occurs.

`--------------------------------------------------------------------------- AttributeError Traceback (most recent call last)

in () ----> 1 solver = main(hyperparams(defaults)) 5 frames /content/drive/MyDrive/dagmm/main.py in main(config) 23 24 if config.mode == 'train': ---> 25 solver.train() 26 elif config.mode == 'test': 27 solver.test() /content/drive/MyDrive/dagmm/solver.py in train(self) 95 input_data = self.to_var(input_data) 96 ---> 97 total_loss,sample_energy, recon_error, cov_diag = self.dagmm_step(input_data) 98 # Logging 99 loss = {} /content/drive/MyDrive/dagmm/solver.py in dagmm_step(self, input_data) 162 enc, dec, z, gamma = self.dagmm(input_data) 163 --> 164 total_loss, sample_energy, recon_error, cov_diag = self.dagmm.loss_function(input_data, dec, z, gamma, self.lambda_energy, self.lambda_cov_diag) 165 166 self.reset_grad() /content/drive/MyDrive/dagmm/model.py in loss_function(self, x, x_hat, z, gamma, lambda_energy, lambda_cov_diag) 166 167 phi, mu, cov = self.compute_gmm_params(z, gamma) --> 168 sample_energy, cov_diag = self.compute_energy(z, phi, mu, cov) 169 170 loss = recon_error + lambda_energy * sample_energy + lambda_cov_diag * cov_diag /content/drive/MyDrive/dagmm/model.py in compute_energy(self, z, phi, mu, cov, size_average) 133 cov_inverse.append(torch.inverse(cov_k).unsqueeze(0)) 134 --> 135 #det_cov.append(np.linalg.det(cov_k.data.cpu().numpy()* (2*np.pi))) 136 det_cov.append((Cholesky.apply(cov_k.cpu() * (2*np.pi)).diag().prod()).unsqueeze(0)) 137 cov_diag = cov_diag + torch.sum(1 / cov_k.diag()) /content/drive/MyDrive/dagmm/model.py in forward(ctx, a) 10 class Cholesky(torch.autograd.Function): 11 def forward(ctx, a): ---> 12 l = torch.cholesky(a, False) 13 ctx.save_for_backward(l) 14 return l AttributeError: module 'torch' has no attribute 'potrf'` After I search for this error, i knew that torch.potrf removed. it was replaced with torch.cholesky. https://github.com/pytorch/pytorch/issues/50379 But, after i change torch.potrf to torch.cholesky, same error occurs. Can anyone run this codes? help me plz.
ChungJunn commented 3 years ago

I tried to change a line inside compute_energy() and the code is running. (I am not running the code in the Colab though)

det_cov.append((Cholesky.apply(cov_k.cpu() (2np.pi)).diag().prod()).unsqueeze(0)) --> det_cov.append((torch.cholesky(cov_k (2math.pi), False).diag().prod()).unsqueeze(0))

chiachen-chang commented 1 year ago

_det_cov.append((torch.cholesky(cov_k * (2_math.pi), False).diag().prod()).unsqueeze(0))

update: solution 1： det_cov.append((torch.cholesky(cov_k * (2*math.pi), False).diag().prod()).unsqueeze(0)) solution 2： det_cov.append((torch.cholesky(cov_k * (2*np.pi), False).diag().prod()).unsqueeze(0))