size issue in anomaly score

marco-rudolph / differnet

This is the official repository to the WACV 2021 paper "Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows" by Marco Rudolph, Bastian Wandt and Bodo Rosenhahn.

215 stars 67 forks source link

size issue in anomaly score #30

Open jxzhangjhu opened 3 years ago

jxzhangjhu commented 3 years ago

Just run python main.py, I have the following issue:

"z_grouped = torch.cat(test_z, dim=0).view(-1, c.n_transforms_test, c.n_feat) RuntimeError: shape '[-1, 64, 768]' is invalid for input of size 262144"

could you help to check?

marco-rudolph commented 3 years ago

I cannot reproduce your error. Did you change config.py or anything else?