hoangthang1607 / nfnets-tensorflow-2 Goto Github PK

Hey, first of all, thanks for your work - pretty fast :)

I just wanted to test your repository and noticed that the code fails for inference on CPU due to the grouped convolution.

Code:

model = NFNet(num_classes=1000, variant=variant)
model.build((None, 320, 320, 3))
model.load_weights(f"{variant}_NFNet/{variant}_NFNet")

test_image = tf.zeros(
    shape=(1, 320, 320, 3), dtype=tf.float32
)
model(test_image)

Error:
UnimplementedError: The Conv2D op currently does not support grouped convolutions on the CPU. A grouped convolution was attempted to be run because the input depth of 256 does not match the filter input depth of 128 [Op:Conv2D] (https://github.com/tensorflow/tensorflow/blob/669993ebe8534eac877eec61225925cff737eac2/tensorflow/core/kernels/conv_ops.cc#L160)

I already started debugging and as far as I see, the error occurs in the Second Block in conv1 when calling WSConv2D(). Here, the inputs are of shape (1, 68, 120, 256), while the weights are (3, 3, 128, 256).

I am not that familiar with grouped convolutions and NFNets in general. So I thought, you maybe already know how to solve the issue, if possible?

Edit:
Is it possible that the filters are already divided by the number of groups (in this case 2) and the inputs are not? See here

Hi there,

I haven't tested this repo yet, but I presume it would be something along the lines of just respecifying the number of classes and images, as well as your directory to images? I've not seen the model up on Tensorflow Hub yet, any ideas would be great!