errors with keras image_dim_ordering()

Question

errors with keras image_dim_ordering()

nyck33 opened this issue 5 years ago · 5 comments

When I try to run the second cell in predict.ipynb I get:

/media/nobu/Ubuntu Backup1/1DeepLearning/2pixelation/age-gender-estimation/wide_resnet.py in __init__(self, image_size, depth, k)
     24         self._weight_init = "he_normal"
     25 
---> 26         if K.backend.image_data_format() == "th":
     27             logging.debug("image_dim_ordering = 'th'")
     28             self._channel_axis = 1

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

Tried changing to `K.backend.imaged_data_format()` but error stays the same.

Answer 1 · 2019-09-09T15:57:19.000Z

What's the Keras and TensorFlow versions?

Answer 2 · 2019-09-09T17:09:16.000Z

I'm having the same issue. I think it's because I'm using Keras v2, where the function has been renamed to 'image_data_format()'. Not sure if @nyck33 made a spelling error (you wrote imaged instead of image) when commenting here or if he actually mistyped it.

Answer 3 · 2019-09-09T17:15:14.000Z

I've fixed it by switching to keras v2.2.4 instead of 2.2.5.

Answer 4 · 2019-09-10T02:17:10.000Z

@AlecVandenbroeck I'll have to check that but thanks!

Answer 5 · 2019-09-11T09:21:41.000Z

@yu4u

Changed line 26 of wide_resnet.py to if K.common.image_dim_ordering() == "th":
and it works.