Closed SrMarkLau closed 2 years ago
Hi @SrMarkLau, which version of Tensorflow are you using?
same for me tf 2.4.0
with 128x128x3 as input shape
ValueError: Invalid value in tensor used for shape: -384
same with tf2.2
i just run this command in Jupyter wavelet_cnn(input_shape=(128,128,3))
Hi, can you produce a minimal, non-working example that I could run and test?
ValueError Traceback (most recent call last)
I clone your repository master branch and next pip install .
Hi, I just pushed a commit that seems to fix this issue. Could you check if that works for you as well?
fix for me thanks a lot
All right then :+1: Thank you for pointing out the issue!
Welcome, small question: do you know how to reproduce this code with your keras module ? https://github.com/mxbastidasr/DAWN_WACV2020 (Wavelet CNN part)
Hi,
I don't have time to write the network in detail, but keep in mind that, being wave
the output of a wavelet layer working on 3 channels (e.g., RGB), its LL component is given by wave[..., :3]
, while the LH, HL and HH components are wave[..., 3:]
.
All the other layers in your network look like standard keras ones. Try to have a look at mini_cnn.py
code for an example of applying a wavelet layer on the LL component of the output of a previous wavelet layer.
Hi friend,
I ran the code of mini ccn, but python returns:
`ValueError: Exception encountered when calling layer "daub_wave_layer2d" (type DaubWaveLayer2D).
in user code:
Call arguments received: • batch=tf.Tensor(shape=(None, 224, 224, 3), dtype=float32)`
The images are RGB:
img_size= 224 channels = 3 input_shape = (img_size, img_size, channels)