Angie
Angie
About
- Username
- Angie
- Joined
- Visits
- 43
- Last Active
- Roles
- Member
Comments
-
@Ethon Lin Thanks for your reply, I finally can run the DME mode with a custom model. > What kind of information you want to get? I want to get NPU usage, memory usage during the inference runtime, like system monitor. But in the link you provid…
-
Thanks for your kind response, after reading your answer I have 2 more questions: 1. Did you provide any API to get the AI Dongle's run-time hardware usage information? 2. About the DME mode: About the "update_app_nef_model.py" issue I f…
-
@Ethon Lin, thank you for your reply. After I change the batch size to 1 then I can compile the bin files successfully. Thank you so much!
-
The EfficientNet seems too big to upload, and the model structure seems quite weird after I removed the transpose parts, so I switch to use MobileNetV2 and try again all the processes but still get the same error. In my attached zip folder contains …
-
https://www.kneron.com/forum/discussion/comment/271#Comment_271 The image dataset I was downloaded from the ImageNet official site, I have checked that the image directory is correct and the image's dimension is either 500*xxx or xxx*500, but actua…
-
This is my customized part if mode == 'customized': x /= 224. #Change this line didn't make any difference... mean = [0.485, 0.456, 0.406] std = [0.229, 0.224, 0.225] x[..., 0] -= mean[0] x[..., 1] -= mean[1] …
-
@Ethon Lin, Thanks for your quick reply. That is I want to try if using customize option can change the input dimension, I use the 'pytorch' option before but still get the same error I still didn't find out the reason.