search

marco-rudolph / cs-flow

This is the official repository to the WACV 2022 paper "Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection" by Marco Rudolph, Tom Wehrbein, Bodo Rosenhahn and Bastian Wandt.
111 stars 30 forks source link

AssertionError: Got single input tensor for forward pass, but expected list of 3 #2

Closed xfby2016 closed 2 years ago

xfby2016 commented 2 years ago

Hi，when I set pre_extracted = False, It report the following errors : assert len(input_vars) == 1, f"Got single input tensor for " AssertionError: Got single input tensor for forward pass, but expected list of 3 Any advice?

guyiyifeurach commented 2 years ago

How you solved your problem? I met the same problem. Thank you! @xfby2016

xfby2016 commented 2 years ago

How you solved your problem? I met the same problem. Thank you! @xfby2016

yes,marco-rudolph has solved the problem in the latest code

guyiyifeurach commented 2 years ago

I pull, and this question solve, but when pre_extracted = True,I still meet data/features/dumplings/dumplings_scale_0_train.npy can't find.

xfby2016 commented 2 years ago

extract_features.py should be execution before training.