Closed lucasjinreal closed 3 years ago
Actually I tried uncomment it when inference, seems not effect the results.
Thanks for these questions. The response is given as follows:
@yanwei-li Thank u for your reply. I notice that if comment out will bring overlapped boxes but over all result seems normal. the kernel fusion step can be replaced by some common ops in pytorch? I am current want converting model inference steps to tensorrt, seems postprocessing a little challenging considering this step as well
I attempt to comment out the kernel_fusion and listed the results of PanopticFCN-R50-3x
as follows:
Method | PQ | SQ | RQ | AP | mIoU
----------------------------------------
no fusion | 42.8 | 81.1 | 51.6 | 31.3 | 42.0
fusion | 43.6 | 81.4 | 52.5 | 34.4 | 43.6
Compared with the original results with kernel_fusion, it damages the performance a lot, specifically in AP and mIoU. I have not tried some other replacements for kernel fusion. Maybe some operations like AveragePooling could work if it is utilized in an appropriate method.
@yanwei-li thank u for your suggestions!
Hi, I found that kernel_fusion only called in inference step in ThingsGenerator. May I ask what's this purpose and why only do that in inference?