-
i know there are special long convolutions, not sure if ONNX supports them / what would happen if I tried to export to ONNX
-
CuDNN benchmark mode can have some beefy speed increases for our cuDNN users, but we don't turn it on by default because the benchmarking process takes a long time. One possibility to alleviate this s…
-
### Semantic Segmentation
- No objects, just pixels
- Input: Image
- Output: the …
hon9g updated
5 years ago
-
Hi @jaywalnut310 ,
Many thanks for your work!
As usual this is very thorough, open and inspiring.
In your paper you publish the GPU speed benchmarks:
> We measured the synchronized elapsed t…
-
### 1. System information
- quantized integer tflite model in Window10(without Nvidia GPU)
- TensorFlow installation method pip installed tensorflow-gpu-2.2.2 and tensorflow-2.2.2.
- try to run q…
-
Relevant Applications, key technical challenge, etc.1-paragraph for each model describing why we care. (Add to reference contributing and vision):
-
Hi,
Using PTB data, the PPLs I got is
Training: 91.31
Valid: 124.51
Test: 124.12
However, PPLs are much lower (Table 2, https://arxiv.org/pdf/1611.01576.pdf). Just wondering if you have investi…
-
##### System information (version)
- OpenCV => 4.5.4
### Internal Computational Graph
The importer's graph must be lowered into a new computational graph that is specific to the CUDA backend. T…
-
### Describe your issue.
`signal.oaconvolve` uses the overlap-add method, which is supposed to significantly speed up convolution of a large array with a small kernel. The [docs](https://docs.scipy…
-
Hello,
I understand what outputs_per_step does, however, should it always be a low value (ie, around 2 or 5) or it can be about 50?
How is it possible that you set the batch size in tacotron to 32…