-
Hi,
I tried to configure and build a 1024 MAC NVDLA large RTL, as change the following parameters in nv_large.spec, and let the other parameters the same as default.
#define MAC_ATOMIC_C_SIZE_32
…
-
| | |
| --- | --- |
| Bugzilla Link | [39298](https://llvm.org/bz39298) |
| Version | trunk |
| OS | All |
| CC | @atamazov,@arsenm |
## Extended Description
GFX7 has only a few 16-bit opcodes, fo…
-
I'm trying to take use of the whole randint4x results (4 int32 rand number) and generate 4x 8bit rand number from each 1x 32bit rand number. (Similar trick as dropout done by [FlashAttention](https://…
bxyb updated
5 months ago
-
As a curator I want to scope my CVTs to some class(es) only
* Add array to CVT with applicable classes.
* Consider view/data semantics
-
The following line works IF you happen to get superorder as the first column after the samples.
I have to change this string depending on the job.
`stopPos
-
**Is there a design bug with the cvtcolor_bgr2gray function in the underlying library?
I wrapped the function in an AXI Stream and it fails. (Vivado HLS 2019.1)**
I run the simulation and it passe…
-
With any more than about three tags, it gets to be tedious to move configurations between this module and your application.
If we could change either this module or the CVT API compatible with each…
-
@tmmsartor
The case of a mat with one dimension equal to 1 (e.g. converting a row or a column) should be "fast" (i.e. coded explicitly in the routine and without falling back to kernels) as it is com…
-
Hello all! When using the attrib `OutputOrientation` of `pypylon.pylon.ImageFormatConverter` to manipulate image orientation,
I found the built-in integer values seemed wrong.
Please run the demo…
-
Hi,
I noticed the code for validation set generations but didn't find any code for training data augmentation. Should we follow the same procedure for generating training data? Could you provide mo…