could you give an example about how to calculate net-scale-factor, the formular is an abstract concept.
for example, the net is normalized(mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225]). How to compute net scale factor and offsets?
Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
Confusion about calculating net-scale-factor and offset
Accelerated ComputingIntelligent Video AnalyticsDeepStream SDK
Confusion about calculating net-scale-factor and offset
Accelerated ComputingIntelligent Video AnalyticsDeepStream SDK
3
/
3
could you give an example about how to calculate net-scale-factor, the formular is an abstract concept.
Reply
1h
- [
last reply
](Confusion about calculating net-scale-factor and offset - #4 by fanzh)
38m
- 2
replies
- 7
views
- 2
users
for example, the net is normalized(mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225]). How to compute net scale factor and offsets?
SolutionReply
fanzhModerator
Please provide complete information as applicable to your setup.
• Hardware Platform :GPU
• DeepStream Version:6.1
• JetPack Version (valid for Jetson only)
• TensorRT Version:8.2.5.1
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type:new questions
• How to reproduce the issue ?
i don’t know how to calculate net-scale-factor and offsets, the formular is an abstract concept, could you give a example with calculating offsets and net-scale-factor
• Requirement details
i don’t know how to calculate net-scale-factor and offsets, the formular is an abstract concept, could you give a example with calculating offsets and net-scale-factor. the
describe is easily，could you give a detail description， thanks.
[property]
net-scale-factor=0.0175
offsets=77.5;21.2;11.8
model-engine-file=…/model/efficientNet.plan
labelfile-path=./effLabel.txt
force-implicit-batch-dim=1
batch-size=1
infer-dims=3;224;224
network-mode=0
process-mode=2
model-color-format=0
gie-unique-id=2
operate-on-gie-id=1
operate-on-class-ids=0
network-type=1
output-blob-names=1065
classifier-async-mode=1
classifier-threshold=0.2
There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks
nvinfer plugin is opensource in DeepStream SDK, you can find net-scale-factor in the code, then check how it is used.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.