joey tussin (Rib Addi)

awhile ago the feature attribution abilities of Lucid were broken. I have found a fix! please review the following working examples I have created: https://colab.research.google.com/github/400lbhacker/several-feature-inversion-projects-python-/blob/main/FIXXED_FEATURE_ATTRIBUTION(LUCID_2022).ipynb https://colab.research.google.com/github/400lbhacker/several-feature-inversion-projects-python-/blob/main/FIXXED-feature_inversion_caffe_Places365_deepstyle.ipynb these are hosted at...

repaired fatal error: NotImplementedError: Cannot convert a symbolic Tensor (2nd_target:0) to a numpy array it is now 100% working again https://github.com/400lbhacker/Lucid-Neural-Style-Transfer/ any ideas on how to get it to work...

deepdream notebook recently broke as well... it broke during the simple upload file portion, the python3 was having issues with the dic.keys() /w uint8 numpy array conversion. The new working...

I created a public fb group for our wonderful Lucid Project. Located here: https://www.facebook.com/groups/3407100409414697 I will be focusing on trying to repair broken projects. ( I have fixed several but...

below is an error that many others have experienced.. I was able to mitigate the error by using a python2.7 enviroment. But google colab lately has gotten rid of py27...

new style transfer error (just recently started happening)

5

style transfer example requires content and style photo to be both same sized (800x,533) for example, and it requires they are in jpeg format with no transperency layer. following these...

does not work in google colab,

1

luarocks cant install it, niether does manual cmake build on google colab... query not found

has invalid type <class 'map'>,

1

recieving error. tensorflow 1. says map cannot be converted into object... it runs as if its going to work.. (main.py) prints atypical tensorflow loadings but than crashes

AttributeError: module 'keras.backend' has no attribute 'image_dim_ordering'