-
**Describe the bug**
Yolov4 post-processing TTNN implementation is taking significant time (~7ms) compared to the whole model on TTNN
The non-32 based tensor shapes (i.e. [1,1600] or [1,400] is the ro…
-
- [ ] change output of all conv2d to ROW_MAJOR -- this will help avoid untilize in halo
- [x] use block sharding for maxpool2d -- this will enable use of larger #cores
- [x] upsample is using 1 core, …
-
Model card - #13043
The yolov4 model is already in main [path](https://github.com/tenstorrent/tt-metal/tree/main/models/experimental/yolov4).
The test files are in the [path](https://github.com/tenst…
-
I've ran my model on both this version of darknet, and the latest AlexeyAB darknet. Both have returned false positives when testing. I've also tested it on other cfgs & weights files including the def…
-
When running yolov4.py I received an error:
```
File "mypath", line 31, in
label = "%s : %f" % (class_name[classid[0]], score)
~~~~~~~^^^
IndexError: i…
-
# TensorFlow 2 YOLOv4 | loliot
YOLOv4 Implemented in Tensorflow 2.
[https://wiki.loliot.net/docs/lang/python/libraries/yolov4/python-yolov4-about](https://wiki.loliot.net/docs/lang/python/libraries/…
-
Hey, @petrohi from the [tensil.ai benchmarks](https://www.tensil.ai/docs/reference/benchmarks/), I learned that you can run YoloV4-Tiny on Pynq-z1. I was trying to recreate this on Pynq-z2 using the a…
-
I made some sample code to show how to use the NPU to run a yolo model on mp4 files.
Currently it runs in real time on my Snapdragon X Elite Dev Box. Twice as fast as the Yolov4 GPU DirectML sample w…
-
## What we know
- Beginning around Nov 8 (end of week of Nov 4), we started seeing non-deterministic hangs in GS perf pipelines and mamba in nightly FD
- This seems to start at: https://github.com/…
-
# YOLOv4 Training on Colab | loliot
YOLOv4 Training on Colab
[https://wiki.loliot.net/docs/lang/python/libraries/yolov4/python-yolov4-training](https://wiki.loliot.net/docs/lang/python/libraries/yol…