anomalyLocalization

anomalyLocalization copied to clipboard

I couldn't get as much accuracy as the results in the paper, is there something wrong with the code? For example, are the hyperparameters different, or is the architecture different...

Sota-Miura

it seems that it doesn't work well and have a few bugs? such as the checkpoint_dir and the loss_function is not appropriate.

schuy1er

Can you tell me how to use this function in EBM？ x_t = x_t - eps * x_grad * (x_t - recon_x) ** 2 eps is not defined in train.py

CF-chen-feng-CF