-
Hi @hunglc007 ,
I have converted the yolov4-tiny weights into tensorflow weights and then converted it into tensorrt model using your repo. Now when trying to run detect.py file with the compressed…
-
I have developed a Jupyter extension called [SoS](http://vatlab.github.io) that allows the use of multiple kernels in a notebook. I have written a [customized Preprocessor](https://github.com/vatlab/s…
-
This occurs with the processor cores set to the performance governor.
Update as of 8JUN21:
After additional experimentation with the lab server, it seems that recent generations of Intel proces…
-
Let's discuss how operator fusion might work in dfdx. I suspect it will require a lot of work. On cuda side of things it will at least require jit compiling kernels.
_Originally posted by @jafioti …
-
I did my first try with linux-tkg on debian testing. The resulting packages are linux-image-6.6.18-tkg-eevdf_6.6.18-1_amd64.deb and linux-headers-6.6.18-tkg-eevdf_6.6.18-1_amd64.deb
But I can not …
mabod updated
8 months ago
-
### Version of Awkward Array
2.6.4
### Description and code to reproduce
Hey guys,
While playing with simple slices of ak.Arrays, I noticed the following:
```python
a = ak.Array([[[0, 1], [2…
-
**Is your feature request related to a problem or challenge? Please describe what you are trying to do.**
While working on internal project incorporating Arrow/DataFusion, we encounter some issue…
-
HI,
I'm nearly done testing all of my AMD GPUs comparing them between OpenCL and HIP environments, and today it was 7900xtx turn. Here are the results and comparison vs 6900xt:
6900xt MBA (23…
-
This is generally seeking clarifications about the requirements made on a device's support for sub-groups.
In [4.6.4.2](https://registry.khronos.org/SYCL/specs/sycl-2020/html/sycl-2020.html#_device…
-
### 🚀 The feature, motivation and pitch
Currently, it seems that in training the Pytorch autograd engine is 'optimized' only for the case where the forward and backward pass are done with tensors w…