Anoop Mishra
Anoop Mishra
About
- Username
- Anoop Mishra
- Joined
- Visits
- 65
- Last Active
- Roles
- Member
Comments
-
Hi Maria, Our pre-processing function for getting the inference : def preprocess(img_file_path): image = cv2.imread(img_file_path) image = cv2.cvtColor(image, cv2.COLOR_RGB2RGBA) image = cv2.resize(image , (224, 224), interpolation=cv2.…
-
Hi Maria, Despite using the same preprocessing function and normalize mode, I have not seen any change in the accuracy of results on the device. There is a lot of difference in the results between docker and the inference from device. I am testing a…
-
https://www.kneron.com/forum/uploads/206/JPPPXU3HTAOT.zip I have attached the files here. The image is not converted to RGB again. Also, https://www.kneron.com/forum/uploads/718/XAWH0Q0ZBQD2.png Shoud we consider the ndarray generated from the raw …
-
Hi Maria, Thanks for your response. I was able to generate the nef file. However, I would like to understand how to get the inference from device, same inference as the docker version . I followed the documentation and was able to get this result fr…
-
https://www.kneron.com/forum/uploads/852/D23A5K0ABXTL.png The onnx file that was shared was already optimized as per the toolchain documentation. I could not get the oonx file compiled after running through the workflow.
-
Thanks for your response. Please find the onnx file attached. https://www.kneron.com/forum/uploads/463/H6453A6S4QD6.zip
-
Update: I took off the AUC metric from the line where I compile the model. However, now I get a error message; "killed". Please see the screenshot. https://www.kneron.com/forum/uploads/836/GBPULTFRHEYP.png
-
Hi Lin, I have checked if the model is supported and it does. However, the unknown here is if I can retrieve intermediate model feature maps (from CNNs) which can be used for post-processing from the NEF model. A workaround I could think of is havin…