Raef Youssef
Raef Youssef
About
- Username
- Raef Youssef
- Joined
- Visits
- 94
- Last Active
- Roles
- Member
Comments
-
Eric, the convolution layer substitute is a great idea, thank you! I've forwarded it to my colleagues. Meanwhile, I've been tinkering with your ai_training repo and it seems that you have two configuration setups: yolov5s, and yolov5s_noupsample. …
-
Here's what I'm referring to in regards to YOLOv5: http://doc.kneron.com/docs/#model_training/object_detection_yolov5/.
-
Thank you Ethon, that makes sense. Is there anyway to port Yolov5s "Focus" layer? Checkout my earlier posts for a description on what it is. I believe you guys ported Yolov5 before so I'm interested to see what steps you guys took.
-
Thanks Eric, I cut the model as described. I now do the downsampling as a preprocessing step. It essentially mount to performing the following: torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x…
-
Thank you! So I can use ReLU6 but I cannot multiply it with x for example to get a new activation function: x * ReLU6? Also, I noticed that YOLOv5 has preprocessing layers to downsample (see below). How do I use the editor script to remove those lay…
-
Hey Eric, I'm considering using ReLU6 to replace the SiLU used in YOLOv5. Is the ReLU6 supported for the KL520? The link here says yes: http://doc.kneron.com/docs/#toolchain/converters/ but http://doc.kneron.com/docs/#toolchain/manual/ doesn't menti…
-
Thanks Eric, please let me know when the toolchain is fixed. I'll also try the onnx-simplifier tool you suggested.
-
Hello, I would like to revisit this thread after the toolchain upgrade allowed the support for opset 11. I exported the onnx model using the "opset_version=11, keep_initializers_As_inputs=True" flags. I then optimized the resultant model u…
-
Thanks kidd, is there anyway to implement quantization aware training (QAT) with models before exporting to Kneron?
-
Thank you, it works great!!
-
I've been having issues post-processing the output of the network. The output dimensions of 1x100x13x13 and 1x100x26x26 do not make sense. If the network was trained on VOC then the output tensor should be 1x[(5+20)*3]x13x13 = 1x75x13x13. If trained…
-
Hey Eric, I followed the tutorial. When going through ioinfo.txt, I noticed the upsampling layer has a "C" next to it. From reading the "Toolchain 520 manual", I came across the following line under FAQ 7: If you find the cpu nod…
-
Yes sure, The .weight and .cfg files were too big to attach so I attached the script that was used to download both. https://www.kneron.com/forum/uploads/123/WAT0BSH8LYHL.zip
-
I did not train this issue. I simply used the repo shared earlier to covert pre-trained weights to the ONNX format. May I ask, what do you mean that it does not work for you?
-
Yeah sure. Here's the original trained model and few images that I use for quantization. https://www.kneron.com/forum/uploads/948/B8PPHXQEVR2W.gz
-
I am running an issue when I execute fpAnalyserCompilerIpevaluator_520.py. I get the following error below. Attached is the optimized model and the input_parameters.json. @kidd @Jiyuan Liu Any ideas? input = /workspace/.tmp/updater.json Traceback (…
-
Ok I do have something similar. The only difference I have is I specify 'yolo' for preprocessing and therefore I use a radix of 7. I'll try your file. BTW, I attached a 416x416 YOLOv3 Tiny model in case you would like to try it. I verified that it c…
-
Thank you for your help. I recently had success using pytorch2onnx. I used the model from this repo: https://github.com/jkjung-avt/tensorrt_demos/tree/master/yolo. My understanding is Kneron uses onnx 1.4.1 and opset 9. Both are older than most of …