You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Oct 26, 2022. It is now read-only.
I installed keras 2.2.4 and tensorflow 1.14, if I tried like this:
input = tf.ones((1, 256, 256, 32, 3), dtype=tf.float32)
x = DepthwiseConv3D(kernel_size=(3, 3, 3), depth_multiplier=2)(input)
the result is ok.
but when I tried like:
def conv_separable(net, width, ksize=ksize, s=1, d=1):
ret = DepthwiseConv3D(kernel_size=(ksize,ksize,ksize),
strides=(s, s, s),
dilation_rate=(d, d, d),
padding='SAME',
activation='relu'
)(net)
ret = conv(ret, width, 1, 1, 1)
return ret
it will record error:
inbound_layers = nest.map_structure(lambda t: t._keras_history.layer,
AttributeError: 'tuple' object has no attribute 'layer'
I don't know why.
The text was updated successfully, but these errors were encountered:
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
I installed keras 2.2.4 and tensorflow 1.14, if I tried like this:
input = tf.ones((1, 256, 256, 32, 3), dtype=tf.float32)
x = DepthwiseConv3D(kernel_size=(3, 3, 3), depth_multiplier=2)(input)
the result is ok.
but when I tried like:
def conv_separable(net, width, ksize=ksize, s=1, d=1):
ret = DepthwiseConv3D(kernel_size=(ksize,ksize,ksize),
strides=(s, s, s),
dilation_rate=(d, d, d),
padding='SAME',
activation='relu'
)(net)
ret = conv(ret, width, 1, 1, 1)
return ret
it will record error:
inbound_layers = nest.map_structure(lambda t: t._keras_history.layer,
AttributeError: 'tuple' object has no attribute 'layer'
I don't know why.
The text was updated successfully, but these errors were encountered: