-
> EfficientNet-lite are a set of mobile/IoT friendly image classification models. Notably, while EfficientNet-EdgeTPU that is specialized for Coral EdgeTPU, these EfficientNet-lite models run well on …
-
Running with OpenCL 1.1, I get this:
```
[2021-11-08 22:41:46.967] opencl GPU #0 compiling...
[2021-11-08 22:41:47.760] opencl error CL_BUILD_PROGRAM_FAILURE when calling clBuildProgram
BU…
-
@WongKinYiu @AlexeyAB
Hi friendly pings
> YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56.8% AP among all k…
-
## Is your feature request related to a problem?
The problem is that the GPUs.txt file is used to make assignment to GPUs. It was a good system about 10 years ago when GPUs were easier to manage. F…
-
The progress bar sown during a search is the console one and note the notebook friendly one (`tqdm.tqdm_notebook`).
```bash
keras-tuner 1.0.0 pypi_0 pypi
jup…
hadim updated
4 years ago
-
Convert to ipynb and run: https://gist.github.com/wjessup/ce49625cb551af8663059b93cbfab209
Takeaways:
Smaller network torch is 3-5x faster Forward: (45.5 µs vs 235 µs) and Training: (337 µs vs. …
-
during the hackathon several issues related to running on GPUs were understood
## stack overflow
some functions, in particular the kMatrix, allocate a lot of memory on the stack, which can exceed …
-
The guidelines for ETC1S format suggest that the applications should decode to BC7 (if available) with a fallback to BC1 (single-slice) and BC3 (dual-slice).
I'm curious, where does this recommenda…
-
aiserver.py is built around cuda. This was totally reasonable till about 3 months ago.
Now there is PyTorch support for m1 hardware
This requires recognition of torch.device('mps')...which does n…
-
First of all, thank you for providing this wonderful toolbox. I only recently started exploring it and I like it quite a bit!
I was wondering if there is any consideration to using Numba which uses…