-
Good afternoon.
Can you specify the different dependencies that you used for this code? The CUDA version, CuDNN, python libraries, theano, etc?
I'm having a lot of problems using your code.
T…
-
### Search before asking
- [X] I have searched the YOLOv5 [issues](https://github.com/ultralytics/yolov5/issues) and [discussions](https://github.com/ultralytics/yolov5/discussions) and found no simi…
-
I am implementing the [tridiagonal matrix algorithm](https://en.wikipedia.org/wiki/Tridiagonal_matrix_algorithm) (TDMA) to solve many tridiagonal systems of the same shape in two sweeps (one forward a…
-
@naibaf7 @bhack
I open this ticket in order to discuss ideas for integration libdnn to tiny-cnn.
Currently, I implemented a small interface to get native OpenCL context from tiny-cnn:
https://github…
-
First of all, thank you for making such a great library!
I'm trying to implement some [chordify](https://chordify.net/) functionality for myself, and one of the things I'd like to be able to do is …
-
## 🚀 Feature
A function `convmtx2` such that
convmtx2(kernel, image.shape[1:]) @ image.flatten() == torch.nn.functional.conv2d(image[None], kernel)[0].flatten()
for any tensors `image` of s…
-
If you apply a predetermined random pattern of sign flipping to an input array followed by the fast (Walsh) Hadamard transform you get a random projection of the input data. You can use that for unbi…
ghost updated
5 years ago
-
## 🚀 Feature
Being able to specify where the result of an op should be written to, rather than having ops allocating their own buffers.
## Motivation
I'm working with context blocks, as defined i…
-
Hi @Rayhane-mamah,
my corpus ~2.5-hour Single-Speaker Speech, Each audio file is Maximum 16 seconds Which are attached below file train.txt and hparams.py.
import tensorflow as tf
import numpy a…
-
ghost updated
5 years ago