-
-
Most of keras is compatible with numpy / scipy.
It would be awesome ( and probably competitively fast at inference on cpu) if keras was available with a numpy/scipy backend.
This would help simp…
-
Thank you for this code. How can I specify the stride just like a normal conv layer? Thanks.
-
Addition of convolution feature of two PDFs.
I have implemented here using the tf.nn.conv1d for 1D (which internally uses tf.nn.conv2d with reshaping tensors): https://drive.google.com/file/d/14wE2…
-
Dear authors,
Thank you for the contribution. Is there any implementation of depth-wise convolution like a general conv layer?
vaesl updated
3 years ago
-
You can try with these 65 (causal) filter coefficients (in time domain, pad them with zeros to 4096 size):
`0.000190, -0.000280, 0.000364, -0.000425, 0.000441, -0.000384, 0.000228, 0.000058, -0.00049…
-
I understand TensorFlow only supports CUDA. What would need to be done to add in OpenCL support?
-
I tried to substitute engine from NNPACK to XNNPACK but faced that XNNPACK 3-5x times slower than NNPACK on my nets on both arm64 and x86 devices. I took some layers from net and tried to run benchmar…
-
Just wondering, but is there a way to use `conv` and `pool` without a GPU?
I'm running a windows machine and even though I have a nvidia card installed, I failed to install CUDA. If any of you have t…
-
**Describe the bug**
While testing with `pytest-cov` we started noticing some failures due to an "internal" error. Digging deeper, it looks like somehow a shared object (.so) file has made its way …