mmdeploy
                                
                                
                                
                                    mmdeploy copied to clipboard
                            
                            
                            
                        [Enhancement] Refactor SDK pipeline
usage
det_cls.cpp
det_pose.cpp
text_det_recog.cpp
Codecov Report
Base: 49.80% // Head: 49.80% // No change to project coverage :thumbsup:
Coverage data is based on head (
82a58db) compared to base (f2bc808). Patch has no changes to coverable lines.
:exclamation: Current head 82a58db differs from pull request most recent head a31ae46. Consider uploading reports for the commit a31ae46 to get more accurate results
Additional details and impacted files
@@           Coverage Diff           @@
##           master     #938   +/-   ##
=======================================
  Coverage   49.80%   49.80%           
=======================================
  Files         305      305           
  Lines       10690    10690           
  Branches     1596     1596           
=======================================
  Hits         5324     5324           
  Misses       4987     4987           
  Partials      379      379           
| Flag | Coverage Δ | |
|---|---|---|
| unittests | 49.80% <ø> (ø) | 
Flags with carried forward coverage won't be shown. Click here to find out more.
Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.
:umbrella: View full report at Codecov.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.
Got some questions:
- How to set the batch size?
 - If one detection task is followed by two classification tasks, will the 
CropBoxnode be shared? - How to ensure that the output sequence is the same as the input sequence?
 
- How to set the batch size?
 
NetModule has nothing to do with batch size for now.
- If one detection task is followed by two classification tasks, will the
 CropBoxnode be shared?
Yes
- How to ensure that the output sequence is the same as the input sequence?
 
Ensured by the sender-receiver model