Ask questionsGroup convolutions UnimplementedError for nightly build
I am getting the following error message while running the following code using the nightly version of tensorflow 1.14.1-dev20190524. When will this feature be available?
weights = tf.ones([3,3,1,3])
X = tf.ones([3,1024,1024,3])
Y = tf.nn.conv2d(X, weights, [1, 1, 1, 1], "VALID")
Error: UnimplementedError: Generic conv implementation does not support grouped convolutions for now. [[node Conv2D_4 (defined at <ipython-input-13-3298cb87493e>:4) ]]
Answer questions reedwm
Grouped convolutions are currently only supported on GPUs, not CPUs. You are using a grouped convolution because the input channel dimension of 3 (
X.shape) does not match the filter in-depth dimension of 1 (
weights.shape). @chsigg, any idea when support is coming for CPUs?
Also the error message is a bit unclear. I'll fix the error message.