Piotr94
Piotr94
Hi, I am adding this issue because my training hangs when specific video is in the dataset. I am using old version of DALI (0.10) because code I want to...
Hi! I have found information that it is possible to obtain stereo vision images in multiple directions: (https://sdk-forum.dji.net/hc/en-us/articles/4402082900249-Is-it-possible-for-OSDK-to-obtain-stereo-vision-images-in-multiple-directions-at-the-same-time- ) but I have difficulties with implementing it. Do you have maybe...
Hi, thank you for releasing code of your inspiring work. I have a question related to dataset preparation: 1. For MNIST dataset there are only classification labels, could you share...
Hi! I'd like to make sure if I understand correctly how the training dataset is created. During each epoch from every category three subdirectories are chosen (line 97 in dataset.py)...
I would like to ask some questions about the difference between AIMET and SNPE quantization. I am attempting to perform quantization of the video denoising model. I started with SNPE...
Recently I have started using Snapdragon Hardware Development Kit. I have followed this course ([link](https://qualcomm.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=3ad03740-020a-4a99-a1c8-b07d013b8838)), which was very helpful, but I met some problems. My question pertains to using the...
Hi! I would like to ask is it possible to check weights and/or quantization parameters of .dlc model obtained after using "snpe-dlc-quantize" ?command? Kind regards Piotr
Hi! Recently I tried to use model for enhancement on big images 1x3x720x1280 on Snapdragon 8 gen 3. I have used modified version of VisionSolution3-ImageEnhancement. I have found that whatever...
I have a question about excluding some layers from quantization. I would like to not quantize operations from one module, called warp. I obtained them using following code: ``` import...