tejagollapudi / face-detection-keras Goto Github PK

Traceback (most recent call last):
File "demo.py", line 61, in
swap_channels=swap_channels)
File "/Users/ebubeoguchi/Soccer Dataset/Fast-Multi-scale-Face-Detection-ConvNet/models/keras_ssd512.py", line 325, in ssd_512
conv4_3_norm = L2Normalization(gamma_init=20, name='conv4_3_norm')(conv4_3)
File "/Users/ebubeoguchi/Soccer Dataset/Fast-Multi-scale-Face-Detection-ConvNet/keras_layers/keras_layer_L2Normalization.py", line 47, in init
if K.image_dim_ordering() == 'tf':
AttributeError: module 'keras.backend' has no attribute 'image_dim_ordering'

No issue but any chance you can share the training notebook?