Can I add data preprocessing to a rtmdet model when i convert it to onnx #2804
Unanswered
foshyjoshy
asked this question in
Q&A
Replies: 1 comment
-
|
@foshyjoshy Hi how are you going with this? I'm in a similar situation with a different model, I am wondering if the preprocessing pipeline has to now be done manually before inferencing images or is that handled by the inference SDK? For example If in my model config I am center cropping my images to 224x224, then is that something I have to now do manually to the images before inference? |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I am converting my trained model using tools/deploy.py to onnx so im able to run it using onnxruntime. Can i include the pipeline pre processing to my model. Im looking to resize and pad my input image as part of the network to match the models fixed input.
Beta Was this translation helpful? Give feedback.
All reactions