The current version has a huge performance gap compared with the previous version #226

Closed
opened 2021-05-05 12:56:27 +02:00 by dongxuanlb · 2 comments
dongxuanlb commented 2021-05-05 12:56:27 +02:00 (Migrated from github.com)

Xavier, yolov4, fp16
At version: adac8576b0 with 33fps
At version: a638592fc7 with only 10fps

Xavier, yolov4, fp16 At version: adac8576b0faf515ad3f459b1f50fd16cef6d64d with 33fps At version: a638592fc74668471e87ac930b4695ce99dc7d43 with only 10fps
ceccocats commented 2021-05-16 22:26:07 +02:00 (Migrated from github.com)

thank you,
it was a compilation issue introduced by @perseusdg during the develop of #218 in this commit 56feb54377

I tested on my PC and on Xavier and it look ok now; tell me if the issue persist

thank you, it was a compilation issue introduced by @perseusdg during the develop of #218 in this commit 56feb54377c0678e42077fabbf84ce2fc138f4c5 I tested on my PC and on Xavier and it look ok now; tell me if the issue persist
dongxuanlb commented 2021-05-26 07:13:16 +02:00 (Migrated from github.com)

Hi, Im still got only 15fps.

dongxuan@xavier:~/workspace/tkDNN/build$ ./demo yolo4_fp16.rt ../demo/yolo_test.mp4 y
detection
yolo4_fp16.rt
New NetworkRT (TensorRT v7.13)
Float16 support: 1
Int8 support: 1
DLAs: 2
create execution context
Input/outputs numbers: 4
input index = 0 -> output index = 3
Data dim: 1 3 416 416 1
Data dim: 1 255 13 13 1
RtBuffer 0 dim: Data dim: 1 3 416 416 1
RtBuffer 1 dim: Data dim: 1 255 52 52 1
RtBuffer 2 dim: Data dim: 1 255 26 26 1
RtBuffer 3 dim: Data dim: 1 255 13 13 1
camera started
^Crequest gateway stop
detection end

Time stats:
Min: 59.4205 ms
Max: 216.611 ms
Avg: 64.0227 ms 15.6195 FPS

Hi, Im still got only 15fps. dongxuan@xavier:~/workspace/tkDNN/build$ ./demo yolo4_fp16.rt ../demo/yolo_test.mp4 y detection yolo4_fp16.rt New NetworkRT (TensorRT v7.13) Float16 support: 1 Int8 support: 1 DLAs: 2 create execution context Input/outputs numbers: 4 input index = 0 -> output index = 3 Data dim: 1 3 416 416 1 Data dim: 1 255 13 13 1 RtBuffer 0 dim: Data dim: 1 3 416 416 1 RtBuffer 1 dim: Data dim: 1 255 52 52 1 RtBuffer 2 dim: Data dim: 1 255 26 26 1 RtBuffer 3 dim: Data dim: 1 255 13 13 1 camera started ^Crequest gateway stop detection end Time stats: Min: 59.4205 ms Max: 216.611 ms Avg: 64.0227 ms 15.6195 FPS
This repo is archived. You cannot comment on issues.
1 Participants
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: mmr/tkDNN#226