experiencor / deep-viz-keras

Implementations of some popular Saliency Maps in Keras
https://experiencor.github.io/cnn_visual.html
164 stars 31 forks source link

InvalidArgumentError: input_1:0 is both fed and fetched. This error when I run the code for VisualBackprop #8

Closed mzmmoazam closed 5 years ago

mzmmoazam commented 5 years ago

InvalidArgumentError Traceback (most recent call last)

in () 2 visual_bprop = VisualBackprop(model) 3 ----> 4 mask = visual_bprop.get_mask(x[0]) 5 show_image(mask, ax=plt.subplot('121'), title='visual backprop') 6 6 frames /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/errors_impl.py in __exit__(self, type_arg, value_arg, traceback_arg) 526 None, None, 527 compat.as_text(c_api.TF_Message(self.status.status)), --> 528 c_api.TF_GetCode(self.status.status)) 529 # Delete the underlying status object from memory otherwise it stays alive 530 # as there is a reference to status from this from the traceback due to InvalidArgumentError: input_1:0 is both fed and fetched.
Eurus-Holmes commented 5 years ago

I have the same error...

mzmmoazam commented 5 years ago

@Eurus-Holmes I have fixed the error in my pull repository. Can check it out.